US20140046914A1 - Method for event-based semantic classification - Google Patents

Method for event-based semantic classification Download PDF

Info

Publication number
US20140046914A1
US20140046914A1 US14/054,954 US201314054954A US2014046914A1 US 20140046914 A1 US20140046914 A1 US 20140046914A1 US 201314054954 A US201314054954 A US 201314054954A US 2014046914 A1 US2014046914 A1 US 2014046914A1
Authority
US
United States
Prior art keywords
event
events
inter
images
image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Abandoned
Application number
US14/054,954
Inventor
Madirakshi Das
Alexander C. Loui
Mark D. Wood
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Monument Peak Ventures LLC
Original Assignee
Intellectual Ventures Fund 83 LLC
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Intellectual Ventures Fund 83 LLC filed Critical Intellectual Ventures Fund 83 LLC
Priority to US14/054,954 priority Critical patent/US20140046914A1/en
Publication of US20140046914A1 publication Critical patent/US20140046914A1/en
Assigned to MONUMENT PEAK VENTURES, LLC reassignment MONUMENT PEAK VENTURES, LLC ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: INTELLECTUAL VENTURES FUND 83 LLC
Assigned to MONUMENT PEAK VENTURES, LLC reassignment MONUMENT PEAK VENTURES, LLC RELEASE BY SECURED PARTY (SEE DOCUMENT FOR DETAILS). Assignors: INTELLECTUAL VENTURES FUND 83 LLC
Abandoned legal-status Critical Current

Links

Images

Classifications

    • G06F17/30598
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/28Databases characterised by their database models, e.g. relational or object models
    • G06F16/284Relational databases
    • G06F16/285Clustering or classification
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/10Terrestrial scenes
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content

Definitions

  • the invention relates generally to the field of digital image processing, and in particular to a method for classifying digital images into semantic categories.
  • low-level features such as color and texture have been proposed for use in content-based image retrieval.
  • a survey of low-level content-based techniques (“Content-based Image Retrieval at the End of the Early Years,” A. W. M. Smeulders et al, IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(12), December 2000) provides a comprehensive listing of relevant methods that can be used for content-based image retrieval.
  • the low-level features commonly described include color, local shape characteristics derived from directional color derivatives and scale space representations, image texture, image transform coefficients such as the cosine transform used in JPEG-coding and properties derived from image segmentation such as shape, contour and geometric invariants. Though these features can be efficiently computed and matched reliably, they usually have poor correlation with semantic image content.
  • WO 01/37131 A2 visual properties of salient image regions are used to classify images.
  • neural networks are used to classify some of the regions using semantic terms such as “sky” and “skin.”
  • the region-based characteristics of the images in the collection are indexed to make it easy to find other images matching the characteristics of a given query image.
  • U.S. Pat. No. 6,240,424 B1 discloses a method for classifying and querying images using primary objects in the image as a clustering center. Images matching a given unclassified image are found by formulating an appropriate query based on the primary objects in the given image.
  • U.S. Patent Application Publication No. 2003/0195883 A1 computes an image's category from a pre-defined set of possible categories, such as “cityscapes.”
  • the organization and retrieval of images and videos is a problem for the typical consumer. Automated tools are needed that can understand the content of the images and provide the ability to search the collection using semantic concepts such as events, people and places.
  • the embodiments provide automatic classification of images in a collection into semantic event categories. This will permit the consumer to search for and browse images in the collection depicting specific events.
  • the images and videos are automatically labeled with event category labels that can enable the automated generation of event-specific creative media outputs.
  • the embodiments provide the advantage of permitting users to search for images or videos in the collection that are part of specific event categories. Further, the embodiments have the advantage that images are automatically labeled with event category labels that can enable the automated generation of event-specific creative media outputs.
  • FIG. 1 is a flowchart of an exemplary method
  • FIG. 2 is a flowchart of the method for creating a hierarchical event representation from an image collection
  • FIG. 3 illustrates the Bayesian net for event classification using time-based and content-based features
  • FIG. 4 illustrates the Bayesian net for event classification with a broader set of features
  • FIG. 5 illustrates the rule-based modification of Bayesian event classifier output
  • FIG. 6 is a flowchart for training the Bayesian net for event classification.
  • FIG. 7 illustrates an exploded view of the event classifier 120 of FIG. 1 .
  • FIG. 1 a user's digital image collection 105 is grouped into an event representation by the event detector 110 .
  • FIG. 2 shows the steps in creating a hierarchical event representation that has three-levels: super-events, events and sub-events.
  • the digital image collection 105 is first grouped into temporal events and sub-events using event and sub-event detector 225 .
  • Commonly assigned U.S. Pat. No. 6,606,411 and U.S. Pat. No. 6,351,556 disclose algorithms for clustering image content by temporal events and sub-events, the disclosures of which are incorporated herein. According to U.S. Pat. No.
  • 6,606,411 events have consistent color distributions, and therefore, these pictures are likely to have been taken with the same backdrop.
  • the above two patents teach how to cluster images and videos in a digital image collection into temporal events and sub-events.
  • the terms “event” and “sub-event” are used in an objective sense to indicate the products of a computer mediated procedure that attempts to match a user's subjective perceptions of specific occurrences (corresponding to events) and divisions of those occurrences (corresponding to sub-events).
  • a collection of images is classified into one or more events determining one or more largest time differences of the collection of images based on time and/or date clustering of the images and separating the plurality of images into the events based on having one or more boundaries between events where one or more boundaries correspond to the one or more largest time differences.
  • sub-events can be determined (if any) by comparing the color histogram information of successive images as described in U.S. Pat. No. 6,351,556. This is accomplished by dividing an image into a number of blocks and then computing the color histogram for each of the blocks.
  • a block-based histogram correlation procedure is used as described in U.S. Pat. No. 6,351,556 to detect sub-event boundaries.
  • an event clustering method uses foreground and background segmentation for clustering images from a group into similar events. Initially, each image is divided into a plurality of blocks, thereby providing block-based images. Utilizing a block-by-block comparison, each block-based image is segmented into a plurality of regions comprising at least a foreground and a background. One or more luminosity, color, position or size features are extracted from the regions and the extracted features are used to estimate and compare the similarity of the regions including the foreground and background in successive images in the group. Then, a measure of the total similarity between successive images is computed, thereby providing image distance between successive images, and event clusters are delimited from the image distances.
  • the events detected continue to be chronologically ordered in a timeline from earliest to latest.
  • inter-event durations are computed for events detected by the inter-event duration calculator 230 .
  • the inter-event duration is the time duration between the last image of one event and the first image of the next event on a continuous timeline.
  • the events are then treated as single points on a time axis, separated by the inter-event durations.
  • a density-based clustering method is applied to these points (ref Data Mining Concepts and Techniques by Han and Kamber, Elsevier, 2006, pg. 418-420) by the density-based classifier 235 .
  • This algorithm grows regions with sufficiently high point density into clusters. This method enables points separated by relatively small duration gaps (for example, less than 18 hours) to be clustered together to form super-events.
  • the final three-level hierarchical event representation is generated by the event hierarchy generator 240 and includes super-events, events and sub-events. After this point, the term “event” refers to the top-level of the hierarchical event representation--which can be a super-event or an event.
  • Content-based features refer to features that are computed from image pixels and that are intended to be an indicator of image content. This includes low-level features such as color and texture, and higher level features such as detection of faces or other objects.
  • U.S. Pat. No. 6,504,951 describes a method for detecting sky in an image. Classifying a scene as indoor or outdoor using camera metadata and image content is described in commonly assigned U.S. Patent Application Publication No. 2005/0105776.
  • Scene classification (by way of example only, includes urban, field or nature scene) has been described in “Review of the state of the art in semantic scene classification,” Computer Science TR 799, University of Rochester, 2002. Detection of a number of semantic classes (such as water, grass, snow, mountain, or buildings by way of example only) using supervised learning has been described in “Supervised learning of semantic classes for image annotation and retrieval,” by Carneiro et al, IEEE Transactions on PAMI, March 2007. Using the temporal context of events during the computation of the image-level feature detection process is described in commonly assigned U.S. Patent Application Publication No. 2005/0105775.
  • a method for describing images that can contain multiple valid classes is described in “Learning multi-label scene classification” by Boutell et al in Pattern Recognition 37 (2004).
  • methods for detecting human faces are well known in the art of digital image processing, and can be used for obtaining a count of the number of faces in the image, approximate sizes of faces and locations of faces.
  • a face detection method for finding human faces in images is described in the following article: Jones, M. J.; Viola, P., “Fast Multi-view Face Detection,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2003.
  • a method for assigning a face to an age category is described in U.S. Pat. No. 5,781,650. The method uses ratios of facial measurements that are known to change with age due to bone structure development.
  • Table 1 has a list of example features that are collected from available algorithms. These features are found to be strongly correlated with the semantic event category.
  • the first column of the table shows the name of the feature.
  • the second column indicates the levels the feature can have.
  • the feature detection output can also be quantized into multiple levels to indicate either extent or degree of confidence of the feature.
  • an experimentally determined threshold is used to test presence e.g. water is present if more than 25% of the image pixels are detected to be water (as shown in Table 1). This ensures that the feature is a significant part of the image.
  • Image-level feature detection results are combined to obtain event-level content-based features.
  • the event is tagged with that feature level.
  • This threshold percentage is indicated in the third column of Table 1. For example, 15% of the images in an event would need to have a “Present” level for the feature “Grass” for the event to have the level “Present” for the feature “Grass.”
  • Time-based features refer to features computed from the capture date/time information obtained from the EXIF header of images or from similar metadata from other file formats.
  • Global time-based features refer to time-based features that are computed at the event level from the capture date/time information of images included within the event. Table 2 shows some examples of time-based features. These include the duration of the event, duration between adjacent events (inter-event duration), number of images, time of day (e.g. morning, afternoon, night) and time of year.
  • the duration of the event is computed as the difference between the capture time (as embedded in the EXIF header of the image by the camera at capture) of the first and last image of the event; the inter-event duration is the difference between the capture time of the last image of the event and the first image of the next event.
  • the time of day is determined by the image at the center of the event timeline.
  • the year is divided into the main seasons and is determined based on the month of capture of the event.
  • the time-based features are detected at the event level.
  • the third column of Table 2 shows the threshold used to determine the level for each of the features.
  • Semantic event categories are pre-determined based on studies of typical consumer picture-taking occasions and cover 80-90% of all images captured. Table 3 shows four top-level semantic event categories and their sub-categories.
  • the features computed by 112 and 114 of FIG. 1 are provided as inputs to an event classifier 120 that produces an event label(s) 122 as the output.
  • An event classifier 120 that produces an event label(s) 122 as the output.
  • a number of classifiers have been described in the literature that can be trained to produce a finite number of output classifications from a set of input features. These include support vector machines, neural networks and Bayesian networks (ref. Pattern Classification by Duda, Hart and Stork, 2.sup.nd ed., John Wiley and sons, 2000). Referring to FIG. 7 , the event classifier 120 of FIG.
  • BBN Bayesian Belief Network
  • Other types of classifiers including support vector machines and neural networks, can also be used.
  • BBN is a form of probabilistic graphical modeling that enables modeling and reasoning about uncertainty. It is a directed acyclic graph which includes nodes that represent variables and arcs that represent conditional probabilities capturing probabilistic dependencies between variables.
  • the conditional probabilities corresponding to each arc of the Bayesian belief network and the a priori probabilities of the output labels are learned.
  • the output node then produces the probability of each of the output labels given the input observations.
  • a key feature of BBN is that it is capable of handling incomplete information gracefully.
  • the features described earlier are computed for each event using correlated feature detectors 610 , which includes the content-based feature detectors 112 and the time-based feature detectors 114 of FIG. 1 .
  • This forms the training set for the Bayesian belief network.
  • the BBN is trained for the top-level event category (in one embodiment, vacation, sports, family moments and social gathering) using an event classifier training component 620 .
  • the rule-based system described later is used to determine the sub-category.
  • the system can also optionally apply heuristics or rules to validate or refine the output of the BBN of FIG. 4 .
  • the output of the BBN-based classifier 710 can be passed to a rule-based classifier 520 , where the details of the rule-based classifier are shown in FIG. 5 .
  • the rules can be based upon domain-specific knowledge, informal common sense knowledge, or formalized common sense knowledge bases such as Cyc or Open Mind Common Sense.
  • the classification “Family Moments” generated by the BBN can be validated by a rule that requires the event to portray at least one or more people that are known to be family members of the system user; if this condition does not hold, then the event is reclassified as “Social Gathering.”
  • Application of such a rule requires first use of a people recognition algorithm (U.S. Patent Application Publication No. 2008/0112621; U.S. Patent Application Publication No. 2007/0177805; and U.S. Patent Application Publication No. 2007/0098303) to determine the identity of the individuals portrayed in the assets malting up the event, and then consultation of the auxiliary factual database 116 of FIG. 1 to determine the relationship of each individual to the user of the system.
  • Such relationships can be explicitly stored in the database for every combination of user and individual; alternatively, the system can store only canonical relationships, and infer specific relationships as requested.
  • Rules are also used to further refine event categories to subcategories.
  • the BBN may not be able to significantly distinguish between the various subcategories of party for a particular event, but rules leveraging auxiliary data can make the distinction.
  • the BBN has determined a top-level category of “Social Gathering.”
  • a rule-based approach can apply the sub-category “Social Gathering-birthday” by using the results of the people recognition algorithm to determine the people portrayed in the event and applying the common sense rule that states that a social gathering is a birthday party if a person portrayed in the event has a birthday at or near the time of the event; information about individual birthdays is part of the data stored in an auxiliary factual database 116 of FIG. 1 . While this classification could also potentially be generated by the BBN of FIG. 4 given the appropriate priors, computing such priors requires sufficient training data; the use of a common sense rule eliminates the need for such data.
  • the BBN of FIG. 4 is used to compute a set of candidate event classifications along with their associated probabilities.
  • the second stage of the event classifier 120 of FIG. 1 is the rule-based classifier 520 of FIG. 5 .
  • FIG. 5 illustrates the steps applied in using rules to validate or refine event categories generated by the BBN in the preferred embodiment.
  • Validation rules 510 and refinement rules 515 are run by a rule-based classifier 520 .
  • Validation rules 510 determine if, given the additional feature data from feature extractors 530 as well as the data from the auxiliary factual database 116 , the event labels 405 are valid; the highest probability classification passing the validity test is output as the event class.
  • Refinement rules 515 refine the event labels 405 using additional features from feature extractors 530 , as well as the data from the auxiliary factual database 116 from FIG. 1 , to determine a refined semantic event sub-category.
  • the feature extractors 530 include but are not limited to content-based feature detectors 112 and time-based feature detectors 114 from FIG. 1 .
  • the rule-based system in FIG. 5 computes the sub-categories using the following rules, after the top-level category is determined using the BBN of FIG. 4 :
  • Vacation “Daytrip” if event duration is within the same calendar day, “Weekend” if event falls during the weekend days, “Getaway” if the vacation is long (greater than 4 days), “Holiday” if it falls during a holiday and the location is determined to be outside the user's home area.
  • Family Moments The category is based on the relationship of the user to the people recognized in the images.

Abstract

A method of automatically classifying images in a consumer digital image collection, includes generating an event representation of the image collection; computing global time-based features for each event within the hierarchical event representation; computing content-based features for each image in an event within the hierarchical event representation; combining content-based features for each image in an event to generate event-level content-based features; and using time-based features and content-based features for each event to classify an event into one of a pre-determined set of semantic categories.

Description

    CROSS-REFERENCE TO RELATED PATENT APPLICATIONS
  • This application is a Divisional of U.S. application Ser. No. 12/273600, filed Nov. 19, 2008, incorporated herein by reference in its entirety.
  • FIELD
  • The invention relates generally to the field of digital image processing, and in particular to a method for classifying digital images into semantic categories.
  • BACKGROUND
  • The proliferation of digital cameras and scanners has led to an explosion of digital images, creating large personal image databases. The organization and retrieval of images and videos is already a problem for the typical consumer. Currently, the length of time spanned by a typical consumer's digital image collection is only a few years. The organization and retrieval problem will continue to grow as the length of time spanned by the average digital image and video collection increases, and automated tools for efficient image indexing and retrieval will be required.
  • Many methods of image classification based on low-level features such as color and texture have been proposed for use in content-based image retrieval. A survey of low-level content-based techniques (“Content-based Image Retrieval at the End of the Early Years,” A. W. M. Smeulders et al, IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(12), December 2000) provides a comprehensive listing of relevant methods that can be used for content-based image retrieval. The low-level features commonly described include color, local shape characteristics derived from directional color derivatives and scale space representations, image texture, image transform coefficients such as the cosine transform used in JPEG-coding and properties derived from image segmentation such as shape, contour and geometric invariants. Though these features can be efficiently computed and matched reliably, they usually have poor correlation with semantic image content.
  • There have also been attempts to compute semantic-level features from images. In
  • WO 01/37131 A2, visual properties of salient image regions are used to classify images. In addition to numerical measurements of visual properties, neural networks are used to classify some of the regions using semantic terms such as “sky” and “skin.” The region-based characteristics of the images in the collection are indexed to make it easy to find other images matching the characteristics of a given query image. U.S. Pat. No. 6,240,424 B1, discloses a method for classifying and querying images using primary objects in the image as a clustering center. Images matching a given unclassified image are found by formulating an appropriate query based on the primary objects in the given image. U.S. Patent Application Publication No. 2003/0195883 A1 computes an image's category from a pre-defined set of possible categories, such as “cityscapes.”
  • These semantic-level features are also not the way users recall and search for images in their collection. Users' recollection of photographs is often based on the event that was captured. For example, photographs may be identified as “Grand Canyon vacation,” “Mom's birthday party,” “Joe's baseball league” and so on. There are mechanisms available in current software to manually enter such tags or captions to identify photographs. However, a need exists to automate this labor-intensive process, so that a user is able to search by common types of events without having to tag the images first. Further, the user can combine event type with other semantic features such as people present in the image, location or activity to narrow the search to relevant images.
  • SUMMARY
  • It is an object of the present disclosure to classify images or videos in a digital image collection into one of several event categories. This object is achieved by a method of automatically classifying images in a consumer digital image collection, comprising:
  • (a) generating an event representation of the image collection;
  • (b) computing global time-based features for each event within the hierarchical event representation;
  • (c) computing content-based features for each image in an event within the hierarchical event representation;
  • (d) combining content-based features for each image in an event to generate event-level content-based features; and
  • (e) using time-based features and content-based features for each event to classify an event into one of a pre-determined set of semantic categories.
  • The organization and retrieval of images and videos is a problem for the typical consumer. Automated tools are needed that can understand the content of the images and provide the ability to search the collection using semantic concepts such as events, people and places. The embodiments provide automatic classification of images in a collection into semantic event categories. This will permit the consumer to search for and browse images in the collection depicting specific events. The images and videos are automatically labeled with event category labels that can enable the automated generation of event-specific creative media outputs. The embodiments provide the advantage of permitting users to search for images or videos in the collection that are part of specific event categories. Further, the embodiments have the advantage that images are automatically labeled with event category labels that can enable the automated generation of event-specific creative media outputs.
  • BRIEF DESCRIPTION OF THE DRAWINGS
  • FIG. 1 is a flowchart of an exemplary method;
  • FIG. 2 is a flowchart of the method for creating a hierarchical event representation from an image collection;
  • FIG. 3 illustrates the Bayesian net for event classification using time-based and content-based features;
  • FIG. 4 illustrates the Bayesian net for event classification with a broader set of features;
  • FIG. 5 illustrates the rule-based modification of Bayesian event classifier output;
  • FIG. 6 is a flowchart for training the Bayesian net for event classification; and
  • FIG. 7 illustrates an exploded view of the event classifier 120 of FIG. 1.
  • DETAILED DESCRIPTION
  • The present disclosure can be implemented in computer systems as will be well known to those skilled in the art. The invention has been described in detail with particular reference to certain preferred embodiments thereof, but it will be understood that variations and modifications can be effected within the spirit and scope of the invention. Videos in a collection are treated as groups of keyframe images and included in the term “images” in the rest of the description.
  • Referring to FIG. 1, a user's digital image collection 105 is grouped into an event representation by the event detector 110. FIG. 2 shows the steps in creating a hierarchical event representation that has three-levels: super-events, events and sub-events. Referring to FIG. 2, the digital image collection 105 is first grouped into temporal events and sub-events using event and sub-event detector 225. Commonly assigned U.S. Pat. No. 6,606,411 and U.S. Pat. No. 6,351,556 disclose algorithms for clustering image content by temporal events and sub-events, the disclosures of which are incorporated herein. According to U.S. Pat. No. 6,606,411 events have consistent color distributions, and therefore, these pictures are likely to have been taken with the same backdrop. For each sub-event, a single color and texture representation is computed for all background areas taken together. The above two patents teach how to cluster images and videos in a digital image collection into temporal events and sub-events. The terms “event” and “sub-event” are used in an objective sense to indicate the products of a computer mediated procedure that attempts to match a user's subjective perceptions of specific occurrences (corresponding to events) and divisions of those occurrences (corresponding to sub-events). Briefly summarized, a collection of images is classified into one or more events determining one or more largest time differences of the collection of images based on time and/or date clustering of the images and separating the plurality of images into the events based on having one or more boundaries between events where one or more boundaries correspond to the one or more largest time differences. For each event, sub-events can be determined (if any) by comparing the color histogram information of successive images as described in U.S. Pat. No. 6,351,556. This is accomplished by dividing an image into a number of blocks and then computing the color histogram for each of the blocks. A block-based histogram correlation procedure is used as described in U.S. Pat. No. 6,351,556 to detect sub-event boundaries. Another method of automatically organizing images into events is disclosed in commonly assigned U.S. Pat. No. 6,915,011, which is herein incorporated by reference. Briefly summarized, according to one aspect of the above invention, an event clustering method uses foreground and background segmentation for clustering images from a group into similar events. Initially, each image is divided into a plurality of blocks, thereby providing block-based images. Utilizing a block-by-block comparison, each block-based image is segmented into a plurality of regions comprising at least a foreground and a background. One or more luminosity, color, position or size features are extracted from the regions and the extracted features are used to estimate and compare the similarity of the regions including the foreground and background in successive images in the group. Then, a measure of the total similarity between successive images is computed, thereby providing image distance between successive images, and event clusters are delimited from the image distances.
  • The events detected continue to be chronologically ordered in a timeline from earliest to latest. Using the method described above, it is not possible to detect single events that span a long period of time (days) and encompass a variety of activities and settings (for example, a long vacation covering multiple destinations) or events that occur in distinct parts separated by some hours from each other (for example, a sporting event with many matches or a wedding). Gaps in photo-taking corresponding to the overnight period also cause breaks in event continuity. Further processing is needed to detect these super-events, defined as a grouping of multiple contiguous events that may span multiple days.
  • Referring to FIG. 2, inter-event durations are computed for events detected by the inter-event duration calculator 230. The inter-event duration is the time duration between the last image of one event and the first image of the next event on a continuous timeline. The events are then treated as single points on a time axis, separated by the inter-event durations. A density-based clustering method is applied to these points (ref Data Mining Concepts and Techniques by Han and Kamber, Elsevier, 2006, pg. 418-420) by the density-based classifier 235. This algorithm grows regions with sufficiently high point density into clusters. This method enables points separated by relatively small duration gaps (for example, less than 18 hours) to be clustered together to form super-events. These typically represent longer duration or multi-part events in the user's collection. Smaller and isolated events appear as noise in this clustering method, and are left un-clustered. The final three-level hierarchical event representation is generated by the event hierarchy generator 240 and includes super-events, events and sub-events. After this point, the term “event” refers to the top-level of the hierarchical event representation--which can be a super-event or an event.
  • Referring to FIG. 1, algorithms for detecting content-based features are applied to each image in the collection using the content-based feature detectors 112. Content-based features refer to features that are computed from image pixels and that are intended to be an indicator of image content. This includes low-level features such as color and texture, and higher level features such as detection of faces or other objects. Commonly assigned U.S. Pat. No. 6,504,951 describes a method for detecting sky in an image. Classifying a scene as indoor or outdoor using camera metadata and image content is described in commonly assigned U.S. Patent Application Publication No. 2005/0105776. Scene classification (by way of example only, includes urban, field or nature scene) has been described in “Review of the state of the art in semantic scene classification,” Computer Science TR 799, University of Rochester, 2002. Detection of a number of semantic classes (such as water, grass, snow, mountain, or buildings by way of example only) using supervised learning has been described in “Supervised learning of semantic classes for image annotation and retrieval,” by Carneiro et al, IEEE Transactions on PAMI, March 2007. Using the temporal context of events during the computation of the image-level feature detection process is described in commonly assigned U.S. Patent Application Publication No. 2005/0105775. A method for describing images that can contain multiple valid classes is described in “Learning multi-label scene classification” by Boutell et al in Pattern Recognition 37 (2004). In addition, methods for detecting human faces are well known in the art of digital image processing, and can be used for obtaining a count of the number of faces in the image, approximate sizes of faces and locations of faces. For example, a face detection method for finding human faces in images is described in the following article: Jones, M. J.; Viola, P., “Fast Multi-view Face Detection,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2003. A method for assigning a face to an age category is described in U.S. Pat. No. 5,781,650. The method uses ratios of facial measurements that are known to change with age due to bone structure development.
  • Table 1 has a list of example features that are collected from available algorithms. These features are found to be strongly correlated with the semantic event category. The first column of the table shows the name of the feature. The second column indicates the levels the feature can have. For example, in the simplest case, a feature can have only two levels—present and not present. The feature detection output can also be quantized into multiple levels to indicate either extent or degree of confidence of the feature. For some features, an experimentally determined threshold is used to test presence e.g. water is present if more than 25% of the image pixels are detected to be water (as shown in Table 1). This ensures that the feature is a significant part of the image. These features are detected at the image level. Image-level feature detection results are combined to obtain event-level content-based features. If a sufficient percentage of images in an event are tagged with the (non-zero) feature level, the event is tagged with that feature level. This threshold percentage is indicated in the third column of Table 1. For example, 15% of the images in an event would need to have a “Present” level for the feature “Grass” for the event to have the level “Present” for the feature “Grass.”
  • Referring to FIG. 1, global time-based features are also detected for each of the events in the collection using time-based feature detectors 114. Time-based features refer to features computed from the capture date/time information obtained from the EXIF header of images or from similar metadata from other file formats. Global time-based features refer to time-based features that are computed at the event level from the capture date/time information of images included within the event. Table 2 shows some examples of time-based features. These include the duration of the event, duration between adjacent events (inter-event duration), number of images, time of day (e.g. morning, afternoon, night) and time of year. The duration of the event is computed as the difference between the capture time (as embedded in the EXIF header of the image by the camera at capture) of the first and last image of the event; the inter-event duration is the difference between the capture time of the last image of the event and the first image of the next event. The time of day is determined by the image at the center of the event timeline. The year is divided into the main seasons and is determined based on the month of capture of the event. The time-based features are detected at the event level. The third column of Table 2 shows the threshold used to determine the level for each of the features.
  • Semantic event categories are pre-determined based on studies of typical consumer picture-taking occasions and cover 80-90% of all images captured. Table 3 shows four top-level semantic event categories and their sub-categories. The features computed by 112 and 114 of FIG. 1 are provided as inputs to an event classifier 120 that produces an event label(s) 122 as the output. A number of classifiers have been described in the literature that can be trained to produce a finite number of output classifications from a set of input features. These include support vector machines, neural networks and Bayesian networks (ref. Pattern Classification by Duda, Hart and Stork, 2.sup.nd ed., John Wiley and sons, 2000). Referring to FIG. 7, the event classifier 120 of FIG. 1 includes two stages. The preferred embodiment uses a Bayesian Belief Network (BBN) (ref Probabilistic Reasoning in Intelligent Systems by Judea Pearl, Morgan Kaufmann, 1988) as a probabilistic classifier 710. Other types of classifiers, including support vector machines and neural networks, can also be used. BBN is a form of probabilistic graphical modeling that enables modeling and reasoning about uncertainty. It is a directed acyclic graph which includes nodes that represent variables and arcs that represent conditional probabilities capturing probabilistic dependencies between variables. During the training phase, the conditional probabilities corresponding to each arc of the Bayesian belief network and the a priori probabilities of the output labels are learned. After training, the output node then produces the probability of each of the output labels given the input observations. A key feature of BBN is that it is capable of handling incomplete information gracefully.
  • The Bayesian Belief Network is set up as shown in FIG. 3. The input nodes include the time-based features detected by the time-based feature detectors 114 including but not limited to those listed in Table 2, such as duration 310; and the content-based features detected by the content-based feature detectors 112, including but not limited to those listed in Table 1, such as people present 315 and % Outdoors 320. An output node 305 computes the event labels based on the time-based and content-based image features.
  • The accuracy of the classifier may be further improved by consideration of auxiliary factual data (information) directly or indirectly associated with the captured event, illustrated as box 116 in FIG. 1. Examples of such factual information might include, but is not limited to, knowledge of familial relationships between people, personal calendars, geographic information, and data considered common sense knowledge. Such factual information also includes the non-content based capture metadata typically recorded in common image file formats such as EXIF, including the subject distance and the camera scene mode. Each of these types of information may be used to refine or validate the classification provided by the event classifier, and are included to create an extended feature set.
  • Such factual information can be applied by the system as part of the BBN. FIG. 4 illustrates how these types of data can factor into the classification. For example, training data can be collected that indicates that a greater subject distance tends to be associated with sporting events and vacations than family moments and social gatherings, helping to further improve the accuracy of the BBN. In some cases camera metadata can be combined with auxiliary knowledge bases to produce other input values for the BBN. Digital capture devices are increasingly capturing GPS coordinates at the time of capture; geolocation data can also be manually added to an image. Given the latitude and longitude of where an event occurred, such coordinates can be mapped to a geographic feature class, using an auxiliary database such as the U.S. Geological Survey's Board of Geographic Names Geographic Names Information System (GNIS). Feature classes include bodies of water as well as facilities such as schools. It is expected that a sporting event is less likely to take place at a cemetery than a school; a social gathering is more likely to take place at a church than an airport. Referring to FIG. 4, node 405 computes event labels based on the extended feature set, including but not limited to a subject distance 410 and the GNIS Feature Class 415, along with the output of node 305 of FIG. 3 that factors in the effect of time-based and content-based features described earlier. The event is then labeled with the event class that has the highest probability.
  • The BBN is trained on labeled input/output data to calculate the conditional probabilities at each arc of the network. The a priori probabilities (or priors) are also learned from the labeled training data. Referring to FIG. 6, a digital image training collection 602 spanning multiple years is collected from a number of consumers. Events and super-events are detected in the collections using the hierarchical event detector 110 from FIG. 1. The events are then labeled by a human manual event labeler 607 into one of the pre-determined set of event categories listed in Table 3 (or “Other” if none are appropriate). The features described earlier are computed for each event using correlated feature detectors 610, which includes the content-based feature detectors 112 and the time-based feature detectors 114 of FIG. 1. This forms the training set for the Bayesian belief network. The BBN is trained for the top-level event category (in one embodiment, vacation, sports, family moments and social gathering) using an event classifier training component 620. The rule-based system described later is used to determine the sub-category.
  • TABLE 1
    List of Content-based event-level features
    Name Levels % images in event
    People present None/1-2/3+ 25
    Children under 4 yrs None/1-2/3+ 25
    Indoor/outdoor Indoor/outdoor 25
    Urban NotUrban/Urban 20
    Beach NotBeach/Beach 5
    Sky <10% area/>10% 10
    Grass NotPresent/Present 15
    Water <25% area/>25% 10
    Field NotPresent/Present 25
    NatureScene NotPresent/Present 12
  • TABLE 2
    List of Time-based event-level features
    Name Levels Threshold
    Duration Short/long 1.5 hours
    Inter-event duration Short/long 2 days
    Time of day Morning/Later 12 pm
    Time of year Summer/Winter/Other Jun-Aug/Dec-Feb/Rest
    Number of Images Few/Many 15
  • TABLE 3
    List of top level event categories and their sub-categories
    Vacation Sports Family Moments Social Gathering
    Daytrip Field Children Wedding
    Weekend Water Parents Birthday
    Getaway Indoor Siblings Holiday
    Holiday Other Grandparents Party
  • Since conditional probabilities for some of the features in the extended feature set can be difficult or infeasible to obtain through training data, the system can also optionally apply heuristics or rules to validate or refine the output of the BBN of FIG. 4. Referring to FIG. 7, the output of the BBN-based classifier 710 can be passed to a rule-based classifier 520, where the details of the rule-based classifier are shown in FIG. 5. The rules can be based upon domain-specific knowledge, informal common sense knowledge, or formalized common sense knowledge bases such as Cyc or Open Mind Common Sense. For example, the classification “Family Moments” generated by the BBN can be validated by a rule that requires the event to portray at least one or more people that are known to be family members of the system user; if this condition does not hold, then the event is reclassified as “Social Gathering.” Application of such a rule requires first use of a people recognition algorithm (U.S. Patent Application Publication No. 2008/0112621; U.S. Patent Application Publication No. 2007/0177805; and U.S. Patent Application Publication No. 2007/0098303) to determine the identity of the individuals portrayed in the assets malting up the event, and then consultation of the auxiliary factual database 116 of FIG. 1 to determine the relationship of each individual to the user of the system. Such relationships can be explicitly stored in the database for every combination of user and individual; alternatively, the system can store only canonical relationships, and infer specific relationships as requested.
  • Rules are also used to further refine event categories to subcategories. For example, the BBN may not be able to significantly distinguish between the various subcategories of party for a particular event, but rules leveraging auxiliary data can make the distinction. Suppose the BBN has determined a top-level category of “Social Gathering.” A rule-based approach can apply the sub-category “Social Gathering-birthday” by using the results of the people recognition algorithm to determine the people portrayed in the event and applying the common sense rule that states that a social gathering is a birthday party if a person portrayed in the event has a birthday at or near the time of the event; information about individual birthdays is part of the data stored in an auxiliary factual database 116 of FIG. 1. While this classification could also potentially be generated by the BBN of FIG. 4 given the appropriate priors, computing such priors requires sufficient training data; the use of a common sense rule eliminates the need for such data.
  • The BBN of FIG. 4 is used to compute a set of candidate event classifications along with their associated probabilities. Referring to FIG. 7, the second stage of the event classifier 120 of FIG. 1 is the rule-based classifier 520 of FIG. 5. FIG. 5 illustrates the steps applied in using rules to validate or refine event categories generated by the BBN in the preferred embodiment. Validation rules 510 and refinement rules 515 are run by a rule-based classifier 520. Validation rules 510 determine if, given the additional feature data from feature extractors 530 as well as the data from the auxiliary factual database 116, the event labels 405 are valid; the highest probability classification passing the validity test is output as the event class. Refinement rules 515 refine the event labels 405 using additional features from feature extractors 530, as well as the data from the auxiliary factual database 116 from FIG. 1, to determine a refined semantic event sub-category. The feature extractors 530 include but are not limited to content-based feature detectors 112 and time-based feature detectors 114 from FIG. 1. In one embodiment, the rule-based system in FIG. 5 computes the sub-categories using the following rules, after the top-level category is determined using the BBN of FIG. 4:
  • Vacation: “Daytrip” if event duration is within the same calendar day, “Weekend” if event falls during the weekend days, “Getaway” if the vacation is long (greater than 4 days), “Holiday” if it falls during a holiday and the location is determined to be outside the user's home area. Sports: “Field” if results from detector for field and “grass” are positive, “Water” if result from detector for water is positive, “Indoor” if result of indoor/outdoor detector is indoor, and “Other” if none of the above detectors show positive result. Family Moments: The category is based on the relationship of the user to the people recognized in the images. Social Gathering: “Wedding” and “Birthday” are based on information from the personal calendar of a user, “Holiday” is based on the calendar and holidays observed in the user's geographic location, and “Party” is based on the presence of many people recognized by the people recognition system as being commonly occurring in the user's collection (i.e. not strangers).
  • Referring to FIG. 7, some embodiments can eliminate the probabilistic classifier 710. In this case, the rules executed by the rule-based classifier 520 do not reference the event label(s) based on the extended feature set 405 of FIG. 4. Likewise, some embodiments cannot incorporate the rule-based classifier 520, producing event labels based on the probabilistic classifier alone.
  • In addition to permitting the user to search and browse by event type, the semantic category of event can be used to author creative output for the user. This semantic information together with other contextual information (including, but not limited to image metadata, date/time, GPS, location, or any combination thereof) can be input into an automatic albuming system for generating themed and personalized album based on the type of event detected. For example, a vacation in Europe will suggest the use of a relevant background design and theme that reflects the cultural and regional characteristic of the location where the event took place. A party event will evoke the use of a fin and whimsical theme and mood for the album. Other custom output products can be created using the event information including collages, cups, T-shirts, and multimedia DVD and CD that includes audio and music. In addition, the semantic event information enables more efficient searching and browsing of the user collection. For instance, the user can easily search by text when the events have been automatically annotated by the system. Yet another application will be for targeted advertising based on the event detected. For example, when an outdoor sporting event is detected, relevant advertising of sporting goods can be targeted to the user.
  • The invention has been described in detail with particular reference to certain preferred embodiments thereof, but it will be understood that variations and modifications can be effected within the spirit and scope of the invention.
  • PARTS LIST
    • 105 Digital image collection
    • 110 Hierarchical event detector
    • 112 Content-based feature detectors
    • 114 Time-based feature detectors
    • 116 Auxiliary factual data
    • 120 Event classifier
    • 122 Event label
    • 225 Event and sub-event detector
    • 230 Inter-event duration calculator
    • 235 Density-based classifier
    • 240 Event hierarchy generator
    • 305 Event labels based on image features node
    • 310 Duration node
    • 315 People present node
    • 320 Outdoors node
    • 405 Event labels based on extended feature set node
    • 410 Subject distance node
    • 415 GNIS feature class node
    • 510 Validation rules
    • 515 Refinement rules
    • 520 Rule-based classifier
    • 530 Feature extractors
    • 602 Digital image training collection
    • 607 Manual event labeler
    • 610 Correlated feature detectors
    • 620 Event classifier training
    • 710 Probabilistic classifier . . .

Claims (20)

What is claimed is:
1. A method comprising:
generating, using a processor, time-based event boundaries detected in a plurality of images;
computing inter-event durations;
grouping events into clusters based on the inter-event durations; and
validating, using a rule-based system, that each event belongs to an associated cluster based on event level content based features.
2. The method of claim 1, wherein grouping events into clusters includes using density-based clustering.
3. The method of claim 1, wherein the inter-event durations span multiple days.
4. The method of claim 1, wherein the inter-event durations span small duration gaps.
5. The method of claim 4, wherein the small duration gaps are less than 18 hours.
6. The method of claim 1, wherein validating, using a rule-based system, comprises referencing a database of auxiliary factual information associated with subjects identified in the plurality of images.
7. The method of claim 1, further comprising determining a location for each image in an event and grouping events into clusters based upon the locations.
8. The method of claim 1, further comprising determining a subject distance for each image in an event and grouping events into clusters based upon the determined locations.
9. A system comprising:
one or more processors configured to:
generate time-based event boundaries detected in a plurality of images;
compute inter-event durations;
group events into clusters based on the inter-event durations; and
validate, using a rule-based system, that each event belongs to an associated cluster based on event level content based features.
10. The system of claim 9, wherein events are grouped into clusters using density-based clustering.
11. The system of claim 9, wherein the inter-event durations span multiple days.
12. The system of claim 9, wherein the inter-event durations span less than 18 hours.
13. The system of claim 9, wherein the validation includes referencing a database of auxiliary factual information associated with subjects identified in the plurality of images.
14. The system of claim 9, wherein the one or more processors are further configured to determine a location for each image in an event and group events into clusters based upon the locations.
15. A non-transitory computer-readable medium having instructions stored thereon, the instructions comprising:
instructions to generate time-based event boundaries detected in a plurality of images;
instructions to compute inter-event durations;
instructions to group events into clusters based on the inter-event durations; and
instructions to validate, using a rule-based system, that each event belongs to an associated super-event cluster based on event level content based features.
16. The non-transitory computer-readable medium of claim 15, wherein events are grouped into clusters using density-based clustering.
17. The non-transitory computer-readable medium of claim 15, wherein the inter-event durations span multiple days.
18. The non-transitory computer-readable medium of claim 15, wherein the inter-event durations span less than 18 hours.
19. The non-transitory computer-readable medium of claim 15, wherein the instructions to validate includes instructions to reference a database of auxiliary factual information associated with subjects identified in the plurality of images.
20. The non-transitory computer-readable medium of claim 15, further comprising instructions to determine a location for each image in an event and group events into clusters based upon the locations.
US14/054,954 2008-11-19 2013-10-16 Method for event-based semantic classification Abandoned US20140046914A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US14/054,954 US20140046914A1 (en) 2008-11-19 2013-10-16 Method for event-based semantic classification

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US12/273,600 US8611677B2 (en) 2008-11-19 2008-11-19 Method for event-based semantic classification
US14/054,954 US20140046914A1 (en) 2008-11-19 2013-10-16 Method for event-based semantic classification

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
US12/273,600 Division US8611677B2 (en) 2008-11-19 2008-11-19 Method for event-based semantic classification

Publications (1)

Publication Number Publication Date
US20140046914A1 true US20140046914A1 (en) 2014-02-13

Family

ID=41650455

Family Applications (2)

Application Number Title Priority Date Filing Date
US12/273,600 Active 2031-05-05 US8611677B2 (en) 2008-11-19 2008-11-19 Method for event-based semantic classification
US14/054,954 Abandoned US20140046914A1 (en) 2008-11-19 2013-10-16 Method for event-based semantic classification

Family Applications Before (1)

Application Number Title Priority Date Filing Date
US12/273,600 Active 2031-05-05 US8611677B2 (en) 2008-11-19 2008-11-19 Method for event-based semantic classification

Country Status (4)

Country Link
US (2) US8611677B2 (en)
EP (2) EP2347349A2 (en)
JP (1) JP5537557B2 (en)
WO (1) WO2010059188A2 (en)

Cited By (29)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150186425A1 (en) * 2013-12-30 2015-07-02 Htc Corporation Method for searching relevant images via active learning, electronic device using the same
US9367490B2 (en) 2014-06-13 2016-06-14 Microsoft Technology Licensing, Llc Reversible connector for accessory devices
US9373179B2 (en) 2014-06-23 2016-06-21 Microsoft Technology Licensing, Llc Saliency-preserving distinctive low-footprint photograph aging effect
US9384334B2 (en) 2014-05-12 2016-07-05 Microsoft Technology Licensing, Llc Content discovery in managed wireless distribution networks
US9384335B2 (en) 2014-05-12 2016-07-05 Microsoft Technology Licensing, Llc Content delivery prioritization in managed wireless distribution networks
US9430667B2 (en) 2014-05-12 2016-08-30 Microsoft Technology Licensing, Llc Managed wireless distribution network
US9460493B2 (en) 2014-06-14 2016-10-04 Microsoft Technology Licensing, Llc Automatic video quality enhancement with temporal smoothing and user override
US9614724B2 (en) 2014-04-21 2017-04-04 Microsoft Technology Licensing, Llc Session-based device configuration
US9639742B2 (en) 2014-04-28 2017-05-02 Microsoft Technology Licensing, Llc Creation of representative content based on facial analysis
WO2017104919A1 (en) * 2015-12-16 2017-06-22 Samsung Electronics Co., Ltd. Event-based image management using clustering
US9773156B2 (en) 2014-04-29 2017-09-26 Microsoft Technology Licensing, Llc Grouping and ranking images based on facial recognition data
US9874914B2 (en) 2014-05-19 2018-01-23 Microsoft Technology Licensing, Llc Power management contracts for accessory devices
US20180052855A1 (en) * 2014-12-17 2018-02-22 The Honest Company, Inc. Method for learning a latent interest taxonomy from multimedia metadata
US10007679B2 (en) 2008-08-08 2018-06-26 The Research Foundation For The State University Of New York Enhanced max margin learning on multimodal data mining in a multimedia database
US10073584B2 (en) 2016-06-12 2018-09-11 Apple Inc. User interfaces for retrieving contextually relevant media content
US10111099B2 (en) 2014-05-12 2018-10-23 Microsoft Technology Licensing, Llc Distributing content in managed wireless distribution networks
US10296166B2 (en) 2010-01-06 2019-05-21 Apple Inc. Device, method, and graphical user interface for navigating and displaying content in context
US10324973B2 (en) 2016-06-12 2019-06-18 Apple Inc. Knowledge graph metadata network based on notable moments
US10362219B2 (en) 2016-09-23 2019-07-23 Apple Inc. Avatar creation and editing
US10572132B2 (en) 2015-06-05 2020-02-25 Apple Inc. Formatting content for a reduced-size user interface
US10691445B2 (en) 2014-06-03 2020-06-23 Microsoft Technology Licensing, Llc Isolating a portion of an online computing service for testing
US10789284B2 (en) * 2018-04-13 2020-09-29 Fuji Xerox Co., Ltd. System and method for associating textual summaries with content media
US10803135B2 (en) 2018-09-11 2020-10-13 Apple Inc. Techniques for disambiguating clustered occurrence identifiers
US10846343B2 (en) 2018-09-11 2020-11-24 Apple Inc. Techniques for disambiguating clustered location identifiers
US11086935B2 (en) 2018-05-07 2021-08-10 Apple Inc. Smart updates from historical database changes
US11163941B1 (en) * 2018-03-30 2021-11-02 Snap Inc. Annotating a collection of media content items
US11243996B2 (en) * 2018-05-07 2022-02-08 Apple Inc. Digital asset search user interface
US11334209B2 (en) 2016-06-12 2022-05-17 Apple Inc. User interfaces for retrieving contextually relevant media content
US11782575B2 (en) 2018-05-07 2023-10-10 Apple Inc. User interfaces for sharing contextually relevant media content

Families Citing this family (88)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8942483B2 (en) * 2009-09-14 2015-01-27 Trimble Navigation Limited Image-based georeferencing
CN101622652B (en) 2007-02-08 2012-03-21 行为识别系统公司 Behavioral recognition system
US8200011B2 (en) 2007-09-27 2012-06-12 Behavioral Recognition Systems, Inc. Context processor for video analysis system
US8094943B2 (en) * 2007-09-27 2012-01-10 Behavioral Recognition Systems, Inc. Background-foreground module for video analysis system
US8300924B2 (en) * 2007-09-27 2012-10-30 Behavioral Recognition Systems, Inc. Tracker component for behavioral recognition system
US9152292B2 (en) * 2009-02-05 2015-10-06 Hewlett-Packard Development Company, L.P. Image collage authoring
WO2010101186A1 (en) * 2009-03-04 2010-09-10 公立大学法人大阪府立大学 Image retrieval method, image retrieval program, and image registration method
US8649594B1 (en) 2009-06-04 2014-02-11 Agilence, Inc. Active and adaptive intelligent video surveillance system
US20120109901A1 (en) * 2009-07-01 2012-05-03 Nec Corporation Content classification apparatus, content classification method, and content classification program
US8806331B2 (en) 2009-07-20 2014-08-12 Interactive Memories, Inc. System and methods for creating and editing photo-based projects on a digital network
US8644624B2 (en) * 2009-07-28 2014-02-04 Samsung Electronics Co., Ltd. System and method for indoor-outdoor scene classification
US9324003B2 (en) 2009-09-14 2016-04-26 Trimble Navigation Limited Location of image capture device and object features in a captured image
US8897541B2 (en) * 2009-09-14 2014-11-25 Trimble Navigation Limited Accurate digitization of a georeferenced image
US9009163B2 (en) * 2009-12-08 2015-04-14 Intellectual Ventures Fund 83 Llc Lazy evaluation of semantic indexing
US9497581B2 (en) * 2009-12-16 2016-11-15 Trimble Navigation Limited Incident reporting
US8339094B2 (en) * 2010-03-11 2012-12-25 GM Global Technology Operations LLC Methods, systems and apparatus for overmodulation of a five-phase machine
US8805840B1 (en) 2010-03-23 2014-08-12 Firstrain, Inc. Classification of documents
US8463789B1 (en) * 2010-03-23 2013-06-11 Firstrain, Inc. Event detection
ES2384928B1 (en) * 2010-06-25 2013-05-20 Telefónica, S.A. METHOD AND SYSTEM FOR THE QUICK AND ROBUST IDENTIFICATION OF SPECIFIC PRODUCTS IN IMAGES.
WO2012006509A1 (en) * 2010-07-09 2012-01-12 Google Inc. Table search using recovered semantic information
US9058342B2 (en) * 2010-08-04 2015-06-16 Panasonic Intellectual Property Corporation Of America Image classification device, method, program, recording media with program thereon, and integrated circuit
US8634662B2 (en) * 2010-08-25 2014-01-21 Apple Inc. Detecting recurring events in consumer image collections
US20120106854A1 (en) * 2010-10-28 2012-05-03 Feng Tang Event classification of images from fusion of classifier classifications
US8923607B1 (en) 2010-12-08 2014-12-30 Google Inc. Learning sports highlights using event detection
US8631002B2 (en) * 2010-12-09 2014-01-14 Microsoft Corporation Web-relevance based query classification
US8612441B2 (en) 2011-02-04 2013-12-17 Kodak Alaris Inc. Identifying particular images from a collection
US20120213404A1 (en) * 2011-02-18 2012-08-23 Google Inc. Automatic event recognition and cross-user photo clustering
US9082452B2 (en) 2011-02-21 2015-07-14 Kodak Alaris Inc. Method for media reliving on demand
US8879890B2 (en) 2011-02-21 2014-11-04 Kodak Alaris Inc. Method for media reliving playback
US8914483B1 (en) 2011-03-17 2014-12-16 Google Inc. System and method for event management and information sharing
JP5848336B2 (en) * 2011-04-25 2016-01-27 パナソニック インテレクチュアル プロパティ コーポレーション オブアメリカPanasonic Intellectual Property Corporation of America Image processing device
US20130022282A1 (en) * 2011-07-19 2013-01-24 Fuji Xerox Co., Ltd. Methods for clustering collections of geo-tagged photographs
US8634660B2 (en) * 2011-09-07 2014-01-21 Intellectual Ventures Fund 83 Llc Event classification method using lit candle detection
US8634661B2 (en) * 2011-09-07 2014-01-21 Intellectual Ventures Fund 83 Llc Event classification method using light source detection
US20130058577A1 (en) * 2011-09-07 2013-03-07 Peter O. Stubler Event classification method for related digital images
US20130096946A1 (en) * 2011-10-13 2013-04-18 The Board of Trustees of the Leland Stanford, Junior, University Method and System for Ontology Based Analytics
US8774504B1 (en) * 2011-10-26 2014-07-08 Hrl Laboratories, Llc System for three-dimensional object recognition and foreground extraction
US9280545B2 (en) * 2011-11-09 2016-03-08 Microsoft Technology Licensing, Llc Generating and updating event-based playback experiences
US20130144814A1 (en) * 2011-12-05 2013-06-06 International Business Machines Corporation Conditional probability operator for event processing systems
US9230187B2 (en) * 2012-03-15 2016-01-05 Qualcomm Incorporated System and method for robust estimation of color dependent measurements
US20140328570A1 (en) * 2013-01-09 2014-11-06 Sri International Identifying, describing, and sharing salient events in images and videos
US9391792B2 (en) 2012-06-27 2016-07-12 Google Inc. System and method for event content stream
KR101993241B1 (en) * 2012-08-06 2019-06-26 삼성전자주식회사 Method and system for tagging and searching additional information about image, apparatus and computer readable recording medium thereof
US9111547B2 (en) * 2012-08-22 2015-08-18 Kodak Alaris Inc. Audio signal semantic concept classification method
US8971639B2 (en) * 2012-09-27 2015-03-03 Hewlett-Packard Development Company, L.P. Semantic theme based shape collage representation for an image collection
SE538062C2 (en) 2012-09-27 2016-02-23 Silex Microsystems Ab Chemically plated metal wire through silicon
US20140096037A1 (en) 2012-09-28 2014-04-03 Interactive Memories, Inc. Methods for Dynamic Prioritization of Graphical Digital Assets for Presentation in an Electronic Interface
US8799829B2 (en) 2012-09-28 2014-08-05 Interactive Memories, Inc. Methods and systems for background uploading of media files for improved user experience in production of media-based products
US8799756B2 (en) 2012-09-28 2014-08-05 Interactive Memories, Inc. Systems and methods for generating autoflow of content based on image and user analysis as well as use case data for a media-based printable product
US9418370B2 (en) 2012-10-23 2016-08-16 Google Inc. Obtaining event reviews
US8990194B2 (en) * 2012-11-02 2015-03-24 Google Inc. Adjusting content delivery based on user submissions of photographs
DE102013007248A1 (en) 2013-04-19 2014-10-23 Rainer Lutze A procedure for collecting, aggregating, updating and disseminating post-paid, assessable, content-correctable and verifiable messages on public events of general interest
US9760803B2 (en) * 2013-05-15 2017-09-12 Google Inc. Associating classifications with images
US9026551B2 (en) * 2013-06-25 2015-05-05 Hartford Fire Insurance Company System and method for evaluating text to support multiple insurance applications
US11080318B2 (en) 2013-06-27 2021-08-03 Kodak Alaris Inc. Method for ranking and selecting events in media collections
US9420237B2 (en) * 2013-07-09 2016-08-16 Globalfoundries Inc. Insight-driven augmented auto-coordination of multiple video streams for centralized processors
US20150331930A1 (en) * 2014-05-16 2015-11-19 Here Global B.V. Method and apparatus for classification of media based on metadata
US11170037B2 (en) * 2014-06-11 2021-11-09 Kodak Alaris Inc. Method for creating view-based representations from multimedia collections
US11023737B2 (en) * 2014-06-11 2021-06-01 Arris Enterprises Llc Detection of demarcating segments in video
KR102223205B1 (en) 2014-06-11 2021-03-08 삼성전자주식회사 Image classification device, method for operating the same and electronic system comprising the image classification device
US9652745B2 (en) 2014-06-20 2017-05-16 Hirevue, Inc. Model-driven evaluator bias detection
US10572902B2 (en) 2014-07-11 2020-02-25 ProSports Technologies, LLC Camera-based digital content distribution
US8935322B1 (en) 2014-07-16 2015-01-13 Interactive Memories, Inc. Methods and systems for improved uploading of media files for use in media-rich projects
US8923551B1 (en) 2014-07-16 2014-12-30 Interactive Memories, Inc. Systems and methods for automatically creating a photo-based project based on photo analysis and image metadata
US8958662B1 (en) 2014-08-20 2015-02-17 Interactive Memories, Inc. Methods and systems for automating insertion of content into media-based projects
US8990672B1 (en) 2014-08-25 2015-03-24 Interactive Memories, Inc. Flexible design architecture for designing media-based projects in a network-based platform
WO2016039987A1 (en) 2014-09-11 2016-03-17 ProSports Technologies, LLC System to offer coupons to fans along routes to game
US9646387B2 (en) 2014-10-15 2017-05-09 Comcast Cable Communications, Llc Generation of event video frames for content
US9077823B1 (en) 2014-10-31 2015-07-07 Interactive Memories, Inc. Systems and methods for automatically generating a photo-based project having a flush photo montage on the front cover
US9219830B1 (en) 2014-10-31 2015-12-22 Interactive Memories, Inc. Methods and systems for page and spread arrangement in photo-based projects
US9507506B2 (en) 2014-11-13 2016-11-29 Interactive Memories, Inc. Automatic target box in methods and systems for editing content-rich layouts in media-based projects
EP3292738B1 (en) 2015-05-05 2020-12-30 June Life, Inc. A connected oven
US9329762B1 (en) 2015-06-02 2016-05-03 Interactive Memories, Inc. Methods and systems for reversing editing operations in media-rich projects
CN105138963A (en) * 2015-07-31 2015-12-09 小米科技有限责任公司 Picture scene judging method, picture scene judging device and server
EP3274878A1 (en) 2015-09-28 2018-01-31 Google LLC Sharing images and image albums over a communication network
US11741522B2 (en) 2015-12-31 2023-08-29 Kodak Alaris, Inc. Method for image product recommendation
US10412148B2 (en) 2016-07-21 2019-09-10 Microsoft Technology Licensing, Llc Systems and methods for event aggregation to reduce network bandwidth and improve network and activity feed server efficiency
WO2018145015A1 (en) 2017-02-06 2018-08-09 Kodak Alaris Inc. Method for creating audio tracks for accompanying visual imagery
US10432728B2 (en) 2017-05-17 2019-10-01 Google Llc Automatic image sharing with designated users over a communication network
US20180349488A1 (en) * 2017-06-02 2018-12-06 Apple Inc. Event extraction systems and methods
EP3706015A4 (en) 2017-12-05 2020-09-23 Huawei Technologies Co., Ltd. Method and device for displaying story album
US11157524B2 (en) 2018-05-18 2021-10-26 At&T Intellectual Property I, L.P. Automated learning of anomalies in media streams with external feed labels
CN112740715A (en) * 2018-09-20 2021-04-30 诺基亚技术有限公司 Device and method for artificial intelligence
JP7155074B2 (en) 2019-07-03 2022-10-18 富士フイルム株式会社 Information proposal system, information proposal method, program and recording medium
US11138477B2 (en) * 2019-08-15 2021-10-05 Collibra Nv Classification of data using aggregated information from multiple classification modules
WO2021184003A1 (en) 2020-03-13 2021-09-16 June Life, Inc. Method and system for sensor maintenance
US11593717B2 (en) 2020-03-27 2023-02-28 June Life, Inc. System and method for classification of ambiguous objects
CN113077051B (en) * 2021-04-14 2024-01-26 南京零洞数智科技有限公司 Network model training method and device, text classification model and network model

Citations (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20010046332A1 (en) * 2000-03-16 2001-11-29 The Regents Of The University Of California Perception-based image retrieval
US20020186875A1 (en) * 2001-04-09 2002-12-12 Burmer Glenna C. Computer methods for image pattern recognition in organic material
US6882997B1 (en) * 1999-08-25 2005-04-19 The Research Foundation Of Suny At Buffalo Wavelet-based clustering method for managing spatial data in very large databases
US20050111824A1 (en) * 2003-06-25 2005-05-26 Microsoft Corporation Digital video segmentation and dynamic segment labeling
US20050122397A1 (en) * 2003-12-03 2005-06-09 Safehouse International Limited Recording a sequence of images
US20050163345A1 (en) * 2003-12-03 2005-07-28 Safehouse International Limited Analysing image data
US20050280719A1 (en) * 2004-04-21 2005-12-22 Samsung Electronics Co., Ltd. Method, medium, and apparatus for detecting situation change of digital photo and method, medium, and apparatus for situation-based photo clustering in digital photo album
US20060104520A1 (en) * 2004-11-17 2006-05-18 Eastman Kodak Company Multi-tiered image clustering by event
US20070098303A1 (en) * 2005-10-31 2007-05-03 Eastman Kodak Company Determining a particular person from a collection
US7272593B1 (en) * 1999-01-26 2007-09-18 International Business Machines Corporation Method and apparatus for similarity retrieval from iterative refinement
US7337214B2 (en) * 2002-09-26 2008-02-26 Yhc Corporation Caching, clustering and aggregating server
US20080115083A1 (en) * 2006-11-10 2008-05-15 Microsoft Corporation Data object linking and browsing tool
US20080154931A1 (en) * 2005-05-23 2008-06-26 Picateers, Inc. System and Method for Automated Layout of Collaboratively Selected Images
US20080256016A1 (en) * 2007-04-11 2008-10-16 Oracle International Corporation Bayes-like classifier with fuzzy likelihood
US7636733B1 (en) * 2003-10-03 2009-12-22 Adobe Systems Incorporated Time-based image management
US7949050B2 (en) * 2004-03-23 2011-05-24 British Telecommunications Public Limited Company Method and system for semantically segmenting scenes of a video sequence
US20110123120A1 (en) * 2008-06-03 2011-05-26 Eth Zurich Method and system for generating a pictorial reference database using geographical information
US8374383B2 (en) * 2007-03-08 2013-02-12 Microscan Systems, Inc. Systems, devices, and/or methods for managing images
US8488863B2 (en) * 2008-11-06 2013-07-16 Los Alamos National Security, Llc Combinational pixel-by-pixel and object-level classifying, segmenting, and agglomerating in performing quantitative image analysis that distinguishes between healthy non-cancerous and cancerous cell nuclei and delineates nuclear, cytoplasm, and stromal material objects from stained biological tissue materials

Family Cites Families (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5781650A (en) * 1994-02-18 1998-07-14 University Of Central Florida Automatic feature detection and age classification of human faces in digital images
US6240424B1 (en) * 1998-04-22 2001-05-29 Nbc Usa, Inc. Method and system for similarity-based image classification
US6606411B1 (en) * 1998-09-30 2003-08-12 Eastman Kodak Company Method for automatically classifying images into events
US6351556B1 (en) * 1998-11-20 2002-02-26 Eastman Kodak Company Method for automatically comparing content of images for classification into events
WO2001037131A2 (en) 1999-11-16 2001-05-25 At & T Laboratories-Cambridge Limited Method of and apparatus for classifying an image
US6504951B1 (en) * 1999-11-29 2003-01-07 Eastman Kodak Company Method for detecting sky in images
US6915011B2 (en) * 2001-03-28 2005-07-05 Eastman Kodak Company Event clustering of images using foreground/background segmentation
US7043474B2 (en) * 2002-04-15 2006-05-09 International Business Machines Corporation System and method for measuring image similarity based on semantic meaning
US7680340B2 (en) * 2003-11-13 2010-03-16 Eastman Kodak Company Method of using temporal context for image classification
US7555165B2 (en) * 2003-11-13 2009-06-30 Eastman Kodak Company Method for semantic scene classification using camera metadata and content-based cues
KR100738069B1 (en) * 2004-10-04 2007-07-10 삼성전자주식회사 Method and apparatus for category-based photo clustering in digital photo album
JP2006171888A (en) 2004-12-13 2006-06-29 Konica Minolta Holdings Inc Image management device, image management method, and image management program
JP4577173B2 (en) * 2005-09-29 2010-11-10 ソニー株式会社 Information processing apparatus and method, and program
US20070141545A1 (en) * 2005-12-05 2007-06-21 Kar-Han Tan Content-Based Indexing and Retrieval Methods for Surround Video Synthesis
US7711145B2 (en) * 2006-01-27 2010-05-04 Eastman Kodak Company Finding images with multiple people or objects
JP4976036B2 (en) * 2006-03-29 2012-07-18 パナソニック株式会社 Image search support device
JP2007317077A (en) 2006-05-29 2007-12-06 Fujifilm Corp Image classification apparatus, method and program
US7869658B2 (en) * 2006-10-06 2011-01-11 Eastman Kodak Company Representative image selection based on hierarchical clustering
US8315463B2 (en) * 2006-11-14 2012-11-20 Eastman Kodak Company User interface for face recognition
US7877696B2 (en) * 2007-01-05 2011-01-25 Eastman Kodak Company Multi-frame display system with semantic image arrangement
US8358856B2 (en) * 2008-06-02 2013-01-22 Eastman Kodak Company Semantic event detection for digital content records
US8213725B2 (en) * 2009-03-20 2012-07-03 Eastman Kodak Company Semantic event detection using cross-domain knowledge

Patent Citations (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7272593B1 (en) * 1999-01-26 2007-09-18 International Business Machines Corporation Method and apparatus for similarity retrieval from iterative refinement
US6882997B1 (en) * 1999-08-25 2005-04-19 The Research Foundation Of Suny At Buffalo Wavelet-based clustering method for managing spatial data in very large databases
US20010046332A1 (en) * 2000-03-16 2001-11-29 The Regents Of The University Of California Perception-based image retrieval
US20020186875A1 (en) * 2001-04-09 2002-12-12 Burmer Glenna C. Computer methods for image pattern recognition in organic material
US7337214B2 (en) * 2002-09-26 2008-02-26 Yhc Corporation Caching, clustering and aggregating server
US20050111824A1 (en) * 2003-06-25 2005-05-26 Microsoft Corporation Digital video segmentation and dynamic segment labeling
US7636733B1 (en) * 2003-10-03 2009-12-22 Adobe Systems Incorporated Time-based image management
US20050122397A1 (en) * 2003-12-03 2005-06-09 Safehouse International Limited Recording a sequence of images
US20050163345A1 (en) * 2003-12-03 2005-07-28 Safehouse International Limited Analysing image data
US7949050B2 (en) * 2004-03-23 2011-05-24 British Telecommunications Public Limited Company Method and system for semantically segmenting scenes of a video sequence
US20050280719A1 (en) * 2004-04-21 2005-12-22 Samsung Electronics Co., Ltd. Method, medium, and apparatus for detecting situation change of digital photo and method, medium, and apparatus for situation-based photo clustering in digital photo album
US20060104520A1 (en) * 2004-11-17 2006-05-18 Eastman Kodak Company Multi-tiered image clustering by event
US20080154931A1 (en) * 2005-05-23 2008-06-26 Picateers, Inc. System and Method for Automated Layout of Collaboratively Selected Images
US20070098303A1 (en) * 2005-10-31 2007-05-03 Eastman Kodak Company Determining a particular person from a collection
US20080115083A1 (en) * 2006-11-10 2008-05-15 Microsoft Corporation Data object linking and browsing tool
US8374383B2 (en) * 2007-03-08 2013-02-12 Microscan Systems, Inc. Systems, devices, and/or methods for managing images
US20080256016A1 (en) * 2007-04-11 2008-10-16 Oracle International Corporation Bayes-like classifier with fuzzy likelihood
US20110123120A1 (en) * 2008-06-03 2011-05-26 Eth Zurich Method and system for generating a pictorial reference database using geographical information
US8488863B2 (en) * 2008-11-06 2013-07-16 Los Alamos National Security, Llc Combinational pixel-by-pixel and object-level classifying, segmenting, and agglomerating in performing quantitative image analysis that distinguishes between healthy non-cancerous and cancerous cell nuclei and delineates nuclear, cytoplasm, and stromal material objects from stained biological tissue materials

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
Sander et al, "Density-Based Clustering in Spatial Databases: The Algorithm GDBSCAN and Its Applications", February 21, 1997, 1998 Kluwer Academic Publishers. Data Mining and Knowledge Discovery 2, 169-194. *

Cited By (44)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10007679B2 (en) 2008-08-08 2018-06-26 The Research Foundation For The State University Of New York Enhanced max margin learning on multimodal data mining in a multimedia database
US11592959B2 (en) 2010-01-06 2023-02-28 Apple Inc. Device, method, and graphical user interface for navigating and displaying content in context
US11099712B2 (en) 2010-01-06 2021-08-24 Apple Inc. Device, method, and graphical user interface for navigating and displaying content in context
US10732790B2 (en) 2010-01-06 2020-08-04 Apple Inc. Device, method, and graphical user interface for navigating and displaying content in context
US10296166B2 (en) 2010-01-06 2019-05-21 Apple Inc. Device, method, and graphical user interface for navigating and displaying content in context
US20150186425A1 (en) * 2013-12-30 2015-07-02 Htc Corporation Method for searching relevant images via active learning, electronic device using the same
US10169702B2 (en) * 2013-12-30 2019-01-01 Htc Corporation Method for searching relevant images via active learning, electronic device using the same
US9614724B2 (en) 2014-04-21 2017-04-04 Microsoft Technology Licensing, Llc Session-based device configuration
US10311284B2 (en) 2014-04-28 2019-06-04 Microsoft Technology Licensing, Llc Creation of representative content based on facial analysis
US9639742B2 (en) 2014-04-28 2017-05-02 Microsoft Technology Licensing, Llc Creation of representative content based on facial analysis
US9773156B2 (en) 2014-04-29 2017-09-26 Microsoft Technology Licensing, Llc Grouping and ranking images based on facial recognition data
US10607062B2 (en) 2014-04-29 2020-03-31 Microsoft Technology Licensing, Llc Grouping and ranking images based on facial recognition data
US10111099B2 (en) 2014-05-12 2018-10-23 Microsoft Technology Licensing, Llc Distributing content in managed wireless distribution networks
US9384334B2 (en) 2014-05-12 2016-07-05 Microsoft Technology Licensing, Llc Content discovery in managed wireless distribution networks
US9384335B2 (en) 2014-05-12 2016-07-05 Microsoft Technology Licensing, Llc Content delivery prioritization in managed wireless distribution networks
US9430667B2 (en) 2014-05-12 2016-08-30 Microsoft Technology Licensing, Llc Managed wireless distribution network
US9874914B2 (en) 2014-05-19 2018-01-23 Microsoft Technology Licensing, Llc Power management contracts for accessory devices
US10691445B2 (en) 2014-06-03 2020-06-23 Microsoft Technology Licensing, Llc Isolating a portion of an online computing service for testing
US9367490B2 (en) 2014-06-13 2016-06-14 Microsoft Technology Licensing, Llc Reversible connector for accessory devices
US9477625B2 (en) 2014-06-13 2016-10-25 Microsoft Technology Licensing, Llc Reversible connector for accessory devices
US9460493B2 (en) 2014-06-14 2016-10-04 Microsoft Technology Licensing, Llc Automatic video quality enhancement with temporal smoothing and user override
US9934558B2 (en) 2014-06-14 2018-04-03 Microsoft Technology Licensing, Llc Automatic video quality enhancement with temporal smoothing and user override
US9892525B2 (en) 2014-06-23 2018-02-13 Microsoft Technology Licensing, Llc Saliency-preserving distinctive low-footprint photograph aging effects
US9373179B2 (en) 2014-06-23 2016-06-21 Microsoft Technology Licensing, Llc Saliency-preserving distinctive low-footprint photograph aging effect
US20180052855A1 (en) * 2014-12-17 2018-02-22 The Honest Company, Inc. Method for learning a latent interest taxonomy from multimedia metadata
US10572132B2 (en) 2015-06-05 2020-02-25 Apple Inc. Formatting content for a reduced-size user interface
US10140516B2 (en) 2015-12-16 2018-11-27 Samsung Electronics Co., Ltd. Event-based image management using clustering
WO2017104919A1 (en) * 2015-12-16 2017-06-22 Samsung Electronics Co., Ltd. Event-based image management using clustering
CN108369638A (en) * 2015-12-16 2018-08-03 三星电子株式会社 The image management based on event carried out using cluster
US11681408B2 (en) 2016-06-12 2023-06-20 Apple Inc. User interfaces for retrieving contextually relevant media content
US11334209B2 (en) 2016-06-12 2022-05-17 Apple Inc. User interfaces for retrieving contextually relevant media content
US10324973B2 (en) 2016-06-12 2019-06-18 Apple Inc. Knowledge graph metadata network based on notable moments
US10073584B2 (en) 2016-06-12 2018-09-11 Apple Inc. User interfaces for retrieving contextually relevant media content
US10891013B2 (en) 2016-06-12 2021-01-12 Apple Inc. User interfaces for retrieving contextually relevant media content
US10362219B2 (en) 2016-09-23 2019-07-23 Apple Inc. Avatar creation and editing
US11163941B1 (en) * 2018-03-30 2021-11-02 Snap Inc. Annotating a collection of media content items
US20220004703A1 (en) * 2018-03-30 2022-01-06 Snap Inc. Annotating a collection of media content items
US10789284B2 (en) * 2018-04-13 2020-09-29 Fuji Xerox Co., Ltd. System and method for associating textual summaries with content media
US11086935B2 (en) 2018-05-07 2021-08-10 Apple Inc. Smart updates from historical database changes
US11243996B2 (en) * 2018-05-07 2022-02-08 Apple Inc. Digital asset search user interface
US11782575B2 (en) 2018-05-07 2023-10-10 Apple Inc. User interfaces for sharing contextually relevant media content
US10846343B2 (en) 2018-09-11 2020-11-24 Apple Inc. Techniques for disambiguating clustered location identifiers
US11775590B2 (en) 2018-09-11 2023-10-03 Apple Inc. Techniques for disambiguating clustered location identifiers
US10803135B2 (en) 2018-09-11 2020-10-13 Apple Inc. Techniques for disambiguating clustered occurrence identifiers

Also Published As

Publication number Publication date
JP5537557B2 (en) 2014-07-02
WO2010059188A2 (en) 2010-05-27
WO2010059188A3 (en) 2010-08-05
US8611677B2 (en) 2013-12-17
US20100124378A1 (en) 2010-05-20
JP2012509522A (en) 2012-04-19
EP2347349A2 (en) 2011-07-27
EP2405371A1 (en) 2012-01-11

Similar Documents

Publication Publication Date Title
US8611677B2 (en) Method for event-based semantic classification
US20220004573A1 (en) Method for creating view-based representations from multimedia collections
US9524349B2 (en) Identifying particular images from a collection
US9042646B2 (en) Detecting recurring themes in consumer image collections
US9171013B2 (en) System and method for providing objectified image renderings using recognition information from images
US7809192B2 (en) System and method for recognizing objects from images and identifying relevancy amongst images and information
US7809722B2 (en) System and method for enabling search and retrieval from image files based on recognized information
US7519200B2 (en) System and method for enabling the use of captured images through recognition
US8150098B2 (en) Grouping images by location
WO2006073299A1 (en) Method and apparatus for clustering digital photos based on situation and system and method for albuming using the same
US20080002864A1 (en) Using background for searching image collections
Van Canneyt et al. Categorizing events using spatio-temporal and user features from Flickr
Manchon-Vizuete et al. Photo clustering of social events by extending PhotoTOC to a rich context
YAN et al. CONTENT AND CONTENT BASED APPROACH FOR PHOTOGRAPH ORGANIZING IN EVENTS
Das et al. Detecting recurring themes in personal media collections
Chu et al. Somebody helps me: Travel video scene detection using web-based context
Hughes A framework for automated landmark recognition in community contributed image corpora
Hibino et al. Semantics Meets UX: Mediating Intelligent Indexing of Consumers' Multimedia Collections for Multifaceted Visualization and Media Creation

Legal Events

Date Code Title Description
AS Assignment

Owner name: MONUMENT PEAK VENTURES, LLC, TEXAS

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:INTELLECTUAL VENTURES FUND 83 LLC;REEL/FRAME:041940/0462

Effective date: 20170215

STPP Information on status: patent application and granting procedure in general

Free format text: FINAL REJECTION MAILED

STPP Information on status: patent application and granting procedure in general

Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION

STPP Information on status: patent application and granting procedure in general

Free format text: NON FINAL ACTION MAILED

STPP Information on status: patent application and granting procedure in general

Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER

STPP Information on status: patent application and granting procedure in general

Free format text: FINAL REJECTION MAILED

STCB Information on status: application discontinuation

Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION

AS Assignment

Owner name: MONUMENT PEAK VENTURES, LLC, TEXAS

Free format text: RELEASE BY SECURED PARTY;ASSIGNOR:INTELLECTUAL VENTURES FUND 83 LLC;REEL/FRAME:064599/0304

Effective date: 20230728