CN103995889A - Method and device for classifying pictures - Google Patents
Method and device for classifying pictures Download PDFInfo
- Publication number
- CN103995889A CN103995889A CN201410243391.XA CN201410243391A CN103995889A CN 103995889 A CN103995889 A CN 103995889A CN 201410243391 A CN201410243391 A CN 201410243391A CN 103995889 A CN103995889 A CN 103995889A
- Authority
- CN
- China
- Prior art keywords
- picture
- along sort
- tag along
- marker feature
- under
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5838—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Abstract
The embodiment of the invention discloses a method and device for classifying pictures. The method for classifying the pictures comprises the steps that marker feature recognition is performed on the obtained pictures, according to a marker feature recognition result and set marker features under at least one classification label, corresponding classification labels are configured to the obtained pictures, and therefore classification of the obtained pictures can be completed. According to the technical scheme, the classification labels are configured to the obtained pictures to achieve classification of the pictures, and therefore pictures under target classification can be rapidly searched for from the obtained pictures, a user does not need to search for the pictures one by one and can obtain the pictures under the target classification, time consumed by picture searching can be shortened, and the searching efficiency of the pictures is improved.
Description
Technical field
The embodiment of the present invention relates to technical field of image processing, relates in particular to picture classification method and device.
Background technology
Along with developing rapidly of electronic technology, the various equipment with image collecting function arises at the historic moment, such as digital camera, smart mobile phone or panel computer etc.User can take pictures by image capture device, and then obtains a large amount of pictures.Certainly, user also can directly obtain picture by internet.
In the prior art, normally by terminal device, adopt the several modes of acquiescence to preserve obtained picture.Wherein, the several modes of acquiescence can be specially: according to title, form, size, date or shooting geographic position, obtained plurality of pictures is sorted.And then, can to obtained picture, preserve according to clooating sequence.
But, the technological deficiency that above-mentioned prior art exists is: inconvenient user finds Target Photo from stored picture, for the quantity of stored picture, be particularly that hundreds of is when open, user is difficult to find at short notice Target Photo, thereby makes searching of picture not only time-consuming but also require great effort.
Summary of the invention
The embodiment of the present invention provides a kind of picture classification method and device, to shorten the follow-up time spent while searching picture, improves picture searching efficiency.
First aspect, the embodiment of the present invention provides a kind of picture classification method, and the method comprises:
Obtained picture is carried out to the identification of marker feature;
According to the marker feature under at least one tag along sort of marker feature recognition result and setting, for obtained picture configures corresponding tag along sort, to complete the classification of the picture to being obtained.
Second aspect, the embodiment of the present invention also provides a kind of picture classifier, and this device comprises:
Picture identification thing feature identification unit, carries out the identification of marker feature for the picture to obtained;
Picture classification tag configurations unit, for according to the marker feature under at least one tag along sort of marker feature recognition result and setting, for obtained picture configures corresponding tag along sort, to complete the classification of the picture to being obtained.
The embodiment of the present invention realizes the classification to picture by the picture configuration tag along sort to obtained, thereby can from accessed many pictures, retrieve fast the picture under target classification, and by the mode of checking one by one, search the picture obtaining under target classification without user, thereby shortened the time spent while searching picture, improved picture searching efficiency.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of a kind of picture classification method of providing of the embodiment of the present invention one;
Fig. 2 is the schematic flow sheet of a kind of picture classification method of providing of the embodiment of the present invention two;
Fig. 3 is the schematic flow sheet of a kind of picture classification method of providing of the embodiment of the present invention three;
Fig. 4 is the schematic flow sheet of a kind of picture classification method of providing of the embodiment of the present invention four;
Fig. 5 is the structural representation of a kind of picture classifier of providing of the embodiment of the present invention five.
Embodiment
Below in conjunction with drawings and Examples, the present invention is described in further detail.Be understandable that, specific embodiment described herein is only for explaining the present invention, but not limitation of the invention.It also should be noted that, for convenience of description, in accompanying drawing, only show part related to the present invention but not entire infrastructure.
Embodiment mono-
Fig. 1 is the schematic flow sheet of a kind of picture classification method of providing of the embodiment of the present invention one, the present embodiment is applicable to after getting plurality of pictures, the situation that obtained plurality of pictures is classified and processed, the method can be carried out by picture classifier, described picture classifier can realize by software and/or hardware, such as this device, can have for smart mobile phone, panel computer or personal digital assistant etc. the electronic equipment of processor, storer and display.Referring to Fig. 1, this picture classification method specifically comprises the steps:
Step 110, obtained picture is carried out to the identification of marker feature.
In the present embodiment, the picture that is carried out the identification of marker feature can be taken instruction indicating image collecting device according to user and carry out picture collection and obtain, and also can be connected and be acquired from other electronic equipments by wireless or cable network.Wherein, image capture device can be the part-structure element being built in picture classifier, also can carry out with picture classifier the stand-alone product of data communication.
After getting picture, can adopt image recognition technology to carry out the identification of marker feature to accessed picture, thereby can determine the marker comprising in accessed picture.Wherein, image recognition technology includes but not limited to the technology such as image denoising, figure image intensifying, Image space transformation, the extraction of image key feature points.In the present embodiment, marker can be one, two or more, can be people's face and/or other conspicuousness main bodys (such as being mountain, desk, fresh flower etc.).When marker behaviour face, marker feature recognition result can comprise the key feature points of people's face number and everyone face.
Step 120, according to the marker feature under at least one tag along sort of marker feature recognition result and setting, for obtained picture configures corresponding tag along sort, to complete the classification of the picture to being obtained.
Wherein, tag along sort is for identifying different classes of picture, and it is identical belonging to the tag along sort that other picture of same class is configured.For example, tag along sort is for representing the small icon (ICON) of this classification, and content shown in small icon can be the information such as the red peach heart, chopsticks, people's face.The picture of identical category is corresponding to same tag along sort, and the marker feature under tag along sort is and belongs to the marker feature comprising in such other pictures.
Concrete, the marker feature under tag along sort can be and belongs to the marker feature that such other pictures comprises, and also can be the weighting that belongs to the marker feature that such other each pictures comprises, and the present embodiment is not construed as limiting this.In the present embodiment, the marker feature under tag along sort can calculate according to pre-stored each pictures that disposes tag along sort, but also directly acquire.
For example, smiling face's small icon is configured to the picture that includes fresh flower, make all pictures that include fresh flower be divided into a class; Red peach heart small icon is configured to the picture that includes user oneself and certain relatives, make all pictures that include user oneself and certain relatives be divided into a class.
The technical scheme that the present embodiment provides, by the picture configuration tag along sort to obtained, realize the classification to picture, thereby can from accessed many pictures, retrieve fast the picture under target classification, and by the mode of checking one by one, search the picture obtaining under target classification without user, thereby shortened the time spent while searching picture, improved picture searching efficiency.
Embodiment bis-
Fig. 2 is the schematic flow sheet of a kind of picture classification method of providing of the embodiment of the present invention two, and the present embodiment, on the basis of above-described embodiment, has preferably further increased the computation process of the marker feature under at least one tag along sort of setting.Referring to Fig. 2, this picture classification method specifically comprises the steps:
Step 210, according to user input instruction, for each Target Photo of preserving in advance configures respectively corresponding tag along sort, the tag along sort that wherein configured is chosen and is obtained from least one tag along sort of setting.
Step 220, each tag along sort that traversal configures respectively, carry out image recognition to the Target Photo under the current tag along sort traversing, and according to image recognition result, obtains the marker feature under the current tag along sort traversing.
Above-mentioned steps 210 is to have realized the computation process of the marker feature under at least one tag along sort of setting with step 220, and this marker feature is to calculate according to pre-stored each pictures that disposes tag along sort.One of the present embodiment preferred embodiment in, the Target Photo under the current tag along sort traversing is carried out to image recognition, according to image recognition result, obtain the marker feature under the current tag along sort traversing, can specifically comprise:
If the number of the Target Photo under the tag along sort traversing current reaches the amount threshold of setting, the Target Photo under the current tag along sort traversing is carried out to image recognition, according to image recognition result, obtain the marker feature under the current tag along sort traversing.
Further, if the number of the Target Photo under the tag along sort traversing current does not reach the amount threshold of setting, directly read the template identification thing feature of the tag along sort of the setting of preserving in advance, the marker feature using the template identification thing feature of the tag along sort of setting as the tag along sort of setting.
Wherein, the Target Photo under the current tag along sort traversing is carried out to image recognition, according to image recognition result, obtains the marker feature under the current tag along sort traversing, can be specially:
Respectively each Target Photo under the current tag along sort traversing is carried out to image recognition, each marker feature being comprised to extract each Target Photo;
Each marker feature comprising according to each Target Photo obtains each marker feature under the current tag along sort traversing.
Concrete, when certain marker feature is comprised in multiple Target Photos simultaneously, the feature of this marker that can comprise each pictures in these Target Photos is weighted or screens, thereby obtains the feature of this marker under the current tag along sort traversing.
For example, this locality is preserved 10 Target Photos in advance, and wherein 5 Target Photos all comprise the feature of user oneself and such two markers of its mother; According to user input instruction, be respectively described 10 pictures and configure corresponding tag along sort, for example, for 5 described Target Photos, all configured red peach heart small icon; When traversing Target Photo number under red this tag along sort of peach heart small icon over 3, respectively 5 Target Photos under red peach heart small icon are carried out to image recognition, the marker that 5 Target Photos are comprised (user oneself and its mother) feature is weighted the marker feature obtaining under red peach heart small icon.
Step 230, obtained picture is carried out to the identification of marker feature.
Step 240, according to the marker feature under at least one tag along sort of marker feature recognition result and setting, for obtained picture configures corresponding tag along sort, to complete the classification of the picture to being obtained.
The technical scheme that the present embodiment provides, on the one hand, according to user instruction, be that the Target Photo of preserving in advance configures the tag along sort of setting, and by Target Photo, obtain setting the marker feature of tag along sort, can well meet consumers' demand like this, follow-up accessed picture can be configured to the desirable tag along sort of user; By the picture configuration tag along sort to obtained, realize the classification to picture on the other hand, thereby can from accessed many pictures, retrieve fast the picture under target classification, and by the mode of checking one by one, search the picture obtaining under target classification without user, thereby shortened the time spent while searching picture, improved picture searching efficiency.
Embodiment tri-
Fig. 3 is the schematic flow sheet of a kind of picture classification method of providing of the embodiment of the present invention three, the present embodiment is on the basis of the various embodiments described above, " according to the marker feature under at least one tag along sort of marker feature recognition result and setting; for obtained picture configures corresponding tag along sort, to complete the classification of the picture to being obtained " this step is done further to optimize.Referring to Fig. 3, this picture classification method specifically comprises the steps:
Step 310, according to user input instruction, for each Target Photo of preserving in advance configures respectively corresponding tag along sort, the tag along sort that wherein configured is chosen and is obtained from least one tag along sort of setting;
Step 320, each tag along sort that traversal configures respectively, carry out image recognition to the Target Photo under the current tag along sort traversing, and according to image recognition result, obtains the marker feature under the current tag along sort traversing;
Step 330, obtained picture is carried out to the identification of marker feature;
Step 340, calculate respectively the similarity of the marker feature under each tag along sort of marker feature that the picture obtain comprises and setting;
The similarity of step 350, marker feature that the picture with obtained is comprised meets the tag along sort under setting threshold condition, and configuration is to obtained picture.
In embodiments of the present invention, the feature of marker can be marker some key point positions in its corresponding picture and the gray-scale value at place, key point position.Can basis: the distance between the key point position of the marker that the picture obtaining comprises and the key point position of this marker under tag along sort, and the distance between the gray-scale value located of the gray-scale value at place, the key point position of the marker that comprises of the picture obtaining and the key point position of this marker under tag along sort, these two metrics obtain similarity.
Wherein, described distance can be Euclidean distance.Distance is larger, and similarity is less.In the present embodiment, the maximal value of similarity can be 1, and minimum value is 0.Certainly, those of ordinary skills should understand, also can adopt other algorithms to calculate similarity, for example, matching degree between the contour area that the contour area that the key point of the marker that the picture that calculating is obtained comprises forms and the key point of this marker under tag along sort form, obtains similarity according to this matching degree.
Above-mentioned setting threshold condition can configure and obtain when product export, also can be by obtaining with user interactions mode the setting threshold condition that user inputs.Setting threshold condition can be an absolute condition, and similarity reaches setting threshold, and for example similarity reaches 80%; Also a relative conditon, maximum in each current calculated similarity.
The technical scheme that the present embodiment provides, on the one hand, according to user instruction, be that the Target Photo of preserving in advance configures the tag along sort of setting, and by Target Photo, obtain setting the marker feature of tag along sort, can well meet consumers' demand like this, follow-up accessed picture can be configured to the desirable tag along sort of user; By the picture configuration tag along sort to obtained, realize the classification to picture on the other hand, thereby can from accessed many pictures, retrieve fast the picture under target classification, and by the mode of checking one by one, search the picture obtaining under target classification without user, thereby shortened the time spent while searching picture, improved picture searching efficiency.Especially, the similarity of the marker feature that the picture with obtained is comprised meets the tag along sort under setting threshold condition, and configuration, can be by being obtained picture configuration tag along sort more accurately and effectively to obtained picture.
Embodiment tetra-
Fig. 4 is the schematic flow sheet of a kind of picture classification method of providing of the embodiment of the present invention four, and the present embodiment, on the basis of the various embodiments described above, has increased the process of picture retrieval.Referring to Fig. 4, this picture classification method specifically comprises the steps:
Step 410, according to user input instruction, for each Target Photo of preserving in advance configures respectively corresponding tag along sort, the tag along sort that wherein configured is chosen and is obtained from least one tag along sort of setting;
Step 420, each tag along sort that traversal configures respectively, carry out image recognition to the Target Photo under the current tag along sort traversing, and according to image recognition result, obtains the marker feature under the current tag along sort traversing;
Step 430, obtained picture is carried out to the identification of marker feature;
Step 440, calculate respectively the similarity of the marker feature under each tag along sort of marker feature that the picture obtain comprises and setting;
The similarity of step 450, marker feature that the picture with obtained is comprised meets the tag along sort under setting threshold condition, and configuration is to obtained picture;
Step 460, reception include the picture retrieval request of target classification tag identifier.
Step 470, determine the corresponding tag along sort of target classification tag identifier, the retrieval picture corresponding with determined tag along sort in accessed pictures.
In the present embodiment, target classification tag identifier be can unique expression target classification label sign, this sign character string that numeral, letter, underscore and/or other characters form of can serving as reasons.
The technical scheme that the present embodiment provides, be that obtained picture configures after tag along sort, according to received target classification tag identifier retrieving image in accessed pictures, can greatly accelerate to retrieve the speed of picture under target classification label like this, overcome in prior art because the retrieval rate by scanned picture collection comes retrieving image to bring is one by one slow, the drawback of inefficiency.
For can further accelerating picture retrieval speed, one of the present embodiment preferred embodiment in, be after obtained picture configures corresponding tag along sort, also all pictures that get under same category label can be kept in set up same file folder.Also, a tag along sort, corresponding to a file, is preserved each pictures under its corresponding tag along sort in file.Like this, receiving the picture retrieval request that includes target classification tag identifier, and determine in the situation of the corresponding tag along sort of complete target classification tag identifier, the Folder Name catalogue that can only set up by traversal, determine and the Folder Name corresponding according to the definite tag along sort obtaining of picture retrieval request, thereby retrieve the picture under determined tag along sort.
Certainly, picture retrieval process also can be user's MS manual search.For facilitating subsequent user MS manual search picture, improve MS manual search efficiency, after the picture for obtained configures corresponding tag along sort, also can further comprise: labeled bracketing label in the thumbnail of obtained picture, so that can show the tag along sort that this picture is corresponding in the thumbnail that Shows Picture.Like this, can make user to find very soon the Target Photo under corresponding classification according to the tag along sort in thumbnail.
Embodiment five
Fig. 5 is the structural representation of a kind of picture classifier of providing of the embodiment of the present invention five, and the present embodiment is applicable to after getting plurality of pictures, the situation that obtained plurality of pictures is classified and processed.Referring to Fig. 5, the concrete structure of this picture classifier comprises:
Picture identification thing feature identification unit 510 and picture classification tag configurations unit 520.
Wherein, picture identification thing feature identification unit 510, carries out the identification of marker feature for the picture to obtained;
Picture classification tag configurations unit 520, for according to the marker feature under at least one tag along sort of marker feature recognition result and setting, for obtained picture configures corresponding tag along sort, to complete the classification of the picture to being obtained.
Further, described picture classification tag configurations unit 520, can be specifically for:
The similarity of the marker feature under the marker feature that the picture that calculating is obtained respectively comprises and each tag along sort of setting;
The similarity of the marker feature that the picture with obtained is comprised meets the tag along sort under setting threshold condition, and configuration is to obtained picture.
Further, this picture classifier also can comprise:
The pre-configured unit 500 of tag along sort, for before 510 pairs of pictures that obtain of described picture identification thing feature identification unit carry out the identification of marker feature, according to user input instruction, for each Target Photo of preserving in advance configures respectively corresponding tag along sort, the tag along sort that wherein configured is chosen and is obtained from least one tag along sort of described setting;
Tag along sort marker feature determining unit 505, for traveling through respectively each tag along sort of described tag along sort pre-configured unit 500 configurations, Target Photo under the current tag along sort traversing is carried out to image recognition, according to image recognition result, obtain the marker feature under the current tag along sort traversing.
Further, described tag along sort marker feature determining unit 505, can be specifically for:
If the number of the Target Photo under the tag along sort traversing current reaches the amount threshold of setting, the Target Photo under the current tag along sort traversing is carried out to image recognition, according to image recognition result, obtain the marker feature under the current tag along sort traversing.
Further, this picture classifier also can comprise:
Picture retrieval request reception unit 530, for after described picture classification tag configurations unit 520 configures corresponding tag along sort for the picture with obtained, receives the picture retrieval request that includes target classification tag identifier;
Picture retrieval unit 540, for determining the corresponding tag along sort of described target classification tag identifier, the retrieval picture corresponding with determined tag along sort in accessed pictures.
The said goods can be carried out the method that any embodiment of the present invention provides, and possesses the corresponding functional module of manner of execution and beneficial effect.
Note, above are only preferred embodiment of the present invention and institute's application technology principle.Skilled person in the art will appreciate that and the invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art various obvious variations, readjust and substitute and can not depart from protection scope of the present invention.Therefore, although the present invention is described in further detail by above embodiment, the present invention is not limited only to above embodiment, in the situation that not departing from the present invention's design, can also comprise more other equivalent embodiment, and scope of the present invention is determined by appended claim scope.
Claims (10)
1. a picture classification method, is characterized in that, comprising:
Obtained picture is carried out to the identification of marker feature;
According to the marker feature under at least one tag along sort of marker feature recognition result and setting, for obtained picture configures corresponding tag along sort, to complete the classification of the picture to being obtained.
2. picture classification method according to claim 1, is characterized in that, according to the marker feature under at least one tag along sort of marker feature recognition result and setting, for obtained picture configures corresponding tag along sort, comprising:
The similarity of the marker feature under the marker feature that the picture that calculating is obtained respectively comprises and each tag along sort of setting;
The similarity of the marker feature that the picture with obtained is comprised meets the tag along sort of setting threshold condition, and configuration is to obtained picture.
3. picture classification method according to claim 1, is characterized in that, before the picture to obtained carries out the identification of marker feature, also comprises:
According to user input instruction, for each Target Photo of preserving in advance configures respectively corresponding tag along sort, the tag along sort that wherein configured is chosen and is obtained from least one tag along sort of described setting;
Each tag along sort of traversal configuration, carries out image recognition to the Target Photo under the current tag along sort traversing respectively, according to image recognition result, obtains the marker feature under the current tag along sort traversing.
4. picture classification method according to claim 3, is characterized in that, the Target Photo under the current tag along sort traversing is carried out to image recognition, according to image recognition result, obtains the marker feature under the current tag along sort traversing, and comprising:
If the number of the Target Photo under the tag along sort traversing current reaches the amount threshold of setting, the Target Photo under the current tag along sort traversing is carried out to image recognition, according to image recognition result, obtain the marker feature under the current tag along sort traversing.
5. according to the picture classification method described in any one in claim 1-4, it is characterized in that, is being, after obtained picture configures corresponding tag along sort, also to comprise:
Reception includes the picture retrieval request of target classification tag identifier;
Determine the corresponding tag along sort of described target classification tag identifier, the retrieval picture corresponding with determined tag along sort in accessed pictures.
6. a picture classifier, is characterized in that, comprising:
Picture identification thing feature identification unit, carries out the identification of marker feature for the picture to obtained;
Picture classification tag configurations unit, for according to the marker feature under at least one tag along sort of marker feature recognition result and setting, for obtained picture configures corresponding tag along sort, to complete the classification of the picture to being obtained.
7. picture classifier according to claim 6, is characterized in that, described picture classification tag configurations unit, specifically for:
The similarity of the marker feature under the marker feature that the picture that calculating is obtained respectively comprises and each tag along sort of setting;
The similarity of the marker feature that the picture with obtained is comprised meets the tag along sort of setting threshold condition, and configuration is to obtained picture.
8. picture classifier according to claim 6, is characterized in that, also comprises:
The pre-configured unit of tag along sort, for before described picture identification thing feature identification unit is carried out the identification of marker feature to obtained picture, according to user input instruction, for each Target Photo of preserving in advance configures respectively corresponding tag along sort, the tag along sort that wherein configured is chosen and is obtained from least one tag along sort of described setting;
Tag along sort marker feature determining unit, for traveling through respectively each tag along sort of the pre-configured cell location of described tag along sort, Target Photo under the current tag along sort traversing is carried out to image recognition, according to image recognition result, obtain the marker feature under the current tag along sort traversing.
9. picture classifier according to claim 8, is characterized in that, described tag along sort marker feature determining unit, specifically for:
If the number of the Target Photo under the tag along sort traversing current reaches the amount threshold of setting, the Target Photo under the current tag along sort traversing is carried out to image recognition, according to image recognition result, obtain the marker feature under the current tag along sort traversing.
10. according to the picture classifier described in any one in claim 6-9, it is characterized in that, also comprise:
Picture retrieval request reception unit, for after described picture classification tag configurations unit configures corresponding tag along sort for the picture with obtained, receives the picture retrieval request that includes target classification tag identifier;
Picture retrieval unit, for determining the corresponding tag along sort of described target classification tag identifier, the retrieval picture corresponding with determined tag along sort in accessed pictures.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410243391.XA CN103995889B (en) | 2014-06-03 | 2014-06-03 | Picture classification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410243391.XA CN103995889B (en) | 2014-06-03 | 2014-06-03 | Picture classification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103995889A true CN103995889A (en) | 2014-08-20 |
| CN103995889B CN103995889B (en) | 2017-11-03 |
Family
ID=51310054
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410243391.XA Active CN103995889B (en) | 2014-06-03 | 2014-06-03 | Picture classification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103995889B (en) |
Cited By (38)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104216976A (en) * | 2014-09-01 | 2014-12-17 | 广东欧珀移动通信有限公司 | Method and system for viewing pictures of mobile terminal by groups |
| CN104615769A (en) * | 2015-02-15 | 2015-05-13 | 小米科技有限责任公司 | Image classification method and device |
| CN105072337A (en) * | 2015-07-31 | 2015-11-18 | 小米科技有限责任公司 | Method and device for processing pictures |
| CN105653152A (en) * | 2015-12-23 | 2016-06-08 | 北京金山安全软件有限公司 | Picture processing method and device and electronic equipment |
| CN105824862A (en) * | 2015-10-20 | 2016-08-03 | 维沃移动通信有限公司 | Image classification method based on electronic equipment and electronic equipment |
| CN106156799A (en) * | 2016-07-25 | 2016-11-23 | 北京光年无限科技有限公司 | The object identification method of intelligent robot and device |
| CN106407383A (en) * | 2016-09-13 | 2017-02-15 | 乐视控股（北京）有限公司 | Picture ranking method and device |
| CN106407872A (en) * | 2015-07-30 | 2017-02-15 | 中兴通讯股份有限公司 | Picture processing apparatus and method thereof |
| CN106445995A (en) * | 2016-07-18 | 2017-02-22 | 腾讯科技（深圳）有限公司 | Picture classification method and apparatus |
| CN106503011A (en) * | 2015-09-07 | 2017-03-15 | 高德软件有限公司 | A kind of map data processing method and device |
| CN106844381A (en) * | 2015-12-04 | 2017-06-13 | 富士通株式会社 | Image processing apparatus and method |
| CN106873958A (en) * | 2016-07-06 | 2017-06-20 | 阿里巴巴集团控股有限公司 | The call method and device of a kind of API |
| WO2017129018A1 (en) * | 2016-01-28 | 2017-08-03 | 阿里巴巴集团控股有限公司 | Picture processing method and apparatus, and smart terminal |
| CN107133629A (en) * | 2016-02-29 | 2017-09-05 | 百度在线网络技术（北京）有限公司 | Picture classification method, device and mobile terminal |
| CN107391618A (en) * | 2017-07-05 | 2017-11-24 | Tcl移动通信科技（宁波）有限公司 | A kind of picture classification storage method, mobile terminal and storage device |
| WO2018032816A1 (en) * | 2016-08-17 | 2018-02-22 | 中兴通讯股份有限公司 | Mobile terminal-based photo search method and device |
| CN107818160A (en) * | 2017-10-31 | 2018-03-20 | 上海掌门科技有限公司 | Expression label updates and realized method, equipment and the system that expression obtains |
| CN107844548A (en) * | 2017-10-30 | 2018-03-27 | 北京锐安科技有限公司 | A kind of data label method and apparatus |
| CN107861750A (en) * | 2017-11-07 | 2018-03-30 | 广东欧珀移动通信有限公司 | A kind of label management method, tag control device and intelligent terminal |
| CN108108494A (en) * | 2018-01-18 | 2018-06-01 | 厦门理工学院 | A kind of picture classification intelligent terminal |
| CN108121816A (en) * | 2017-12-28 | 2018-06-05 | 广东欧珀移动通信有限公司 | Picture classification method, device, storage medium and electronic equipment |
| CN108173831A (en) * | 2017-12-25 | 2018-06-15 | 北京佳艺徕经贸有限责任公司 | The distribution method and device of a kind of photo |
| CN108416003A (en) * | 2018-02-27 | 2018-08-17 | 百度在线网络技术（北京）有限公司 | A kind of picture classification method and device, terminal, storage medium |
| CN108763580A (en) * | 2018-06-08 | 2018-11-06 | Oppo广东移动通信有限公司 | Image processing method and device, electronic equipment, computer storage media |
| CN108829815A (en) * | 2018-06-12 | 2018-11-16 | 四川希氏异构医疗科技有限公司 | A kind of medical image method for screening images |
| CN109033958A (en) * | 2018-06-20 | 2018-12-18 | 北京微播视界科技有限公司 | Increase the method and device of special efficacy for the face of special object |
| CN109047046A (en) * | 2018-08-17 | 2018-12-21 | 张家港康得新光电材料有限公司 | A kind of discharge port grade setting method, device, terminal and storage medium |
| WO2018232645A1 (en) * | 2017-06-21 | 2018-12-27 | 深圳支点电子智能科技有限公司 | Mobile terminal with photographing function and related product |
| CN109409235A (en) * | 2018-09-27 | 2019-03-01 | Oppo广东移动通信有限公司 | Image-recognizing method and device, electronic equipment, computer readable storage medium |
| CN109829070A (en) * | 2019-01-29 | 2019-05-31 | 维沃移动通信有限公司 | A kind of image lookup method and terminal device |
| CN109889437A (en) * | 2019-03-04 | 2019-06-14 | 上海擎语信息科技有限公司 | A kind of novel software of taking pictures |
| CN110222709A (en) * | 2019-04-29 | 2019-09-10 | 上海暖哇科技有限公司 | A kind of multi-tag intelligence marking method and system |
| CN110880011A (en) * | 2018-09-05 | 2020-03-13 | 宏达国际电子股份有限公司 | Image segmentation method, device and non-transitory computer readable medium thereof |
| CN111368111A (en) * | 2020-02-28 | 2020-07-03 | Oppo（重庆）智能科技有限公司 | Picture retrieval method and device for mobile equipment and mobile equipment |
| CN111709355A (en) * | 2020-06-12 | 2020-09-25 | 北京百度网讯科技有限公司 | Method and device for identifying target area, electronic equipment and road side equipment |
| CN111709357A (en) * | 2020-06-12 | 2020-09-25 | 北京百度网讯科技有限公司 | Method and device for identifying target area, electronic equipment and road side equipment |
| CN111738354A (en) * | 2020-07-20 | 2020-10-02 | 深圳市天和荣科技有限公司 | Automatic recognition training method, system, storage medium and computer equipment |
| CN111783786A (en) * | 2020-07-06 | 2020-10-16 | 上海摩勤智能技术有限公司 | Picture identification method and system, electronic equipment and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080243861A1 (en) * | 2007-03-29 | 2008-10-02 | Tomas Karl-Axel Wassingbo | Digital photograph content information service |
| CN101393605A (en) * | 2007-09-18 | 2009-03-25 | 索尼株式会社 | Image processing device and image processing method, and program |
| CN101414351A (en) * | 2008-11-03 | 2009-04-22 | 章毅 | Fingerprint recognition system and control method |
| US20090171783A1 (en) * | 2008-01-02 | 2009-07-02 | Raju Ruta S | Method and system for managing digital photos |
| CN101719216A (en) * | 2009-12-21 | 2010-06-02 | 西安电子科技大学 | Movement human abnormal behavior identification method based on template matching |
| US20100158356A1 (en) * | 2008-12-22 | 2010-06-24 | Yahoo! Inc. | System and method for improved classification |
| CN101944183A (en) * | 2010-09-02 | 2011-01-12 | 北京航空航天大学 | Method for identifying object by utilizing SIFT tree |
| CN102509084A (en) * | 2011-11-18 | 2012-06-20 | 中国科学院自动化研究所 | Multi-examples-learning-based method for identifying horror video scene |
| CN103207870A (en) * | 2012-01-17 | 2013-07-17 | 华为技术有限公司 | Method, server, device and system for photo sort management |
-
2014
- 2014-06-03 CN CN201410243391.XA patent/CN103995889B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080243861A1 (en) * | 2007-03-29 | 2008-10-02 | Tomas Karl-Axel Wassingbo | Digital photograph content information service |
| CN101393605A (en) * | 2007-09-18 | 2009-03-25 | 索尼株式会社 | Image processing device and image processing method, and program |
| US20090171783A1 (en) * | 2008-01-02 | 2009-07-02 | Raju Ruta S | Method and system for managing digital photos |
| CN101414351A (en) * | 2008-11-03 | 2009-04-22 | 章毅 | Fingerprint recognition system and control method |
| US20100158356A1 (en) * | 2008-12-22 | 2010-06-24 | Yahoo! Inc. | System and method for improved classification |
| CN101719216A (en) * | 2009-12-21 | 2010-06-02 | 西安电子科技大学 | Movement human abnormal behavior identification method based on template matching |
| CN101944183A (en) * | 2010-09-02 | 2011-01-12 | 北京航空航天大学 | Method for identifying object by utilizing SIFT tree |
| CN102509084A (en) * | 2011-11-18 | 2012-06-20 | 中国科学院自动化研究所 | Multi-examples-learning-based method for identifying horror video scene |
| CN103207870A (en) * | 2012-01-17 | 2013-07-17 | 华为技术有限公司 | Method, server, device and system for photo sort management |
Cited By (54)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104216976B (en) * | 2014-09-01 | 2018-09-04 | 广东欧珀移动通信有限公司 | A kind of mobile terminal picture grouping inspection method and system |
| CN104216976A (en) * | 2014-09-01 | 2014-12-17 | 广东欧珀移动通信有限公司 | Method and system for viewing pictures of mobile terminal by groups |
| CN104615769A (en) * | 2015-02-15 | 2015-05-13 | 小米科技有限责任公司 | Image classification method and device |
| CN104615769B (en) * | 2015-02-15 | 2018-10-19 | 小米科技有限责任公司 | Picture classification method and device |
| CN106407872A (en) * | 2015-07-30 | 2017-02-15 | 中兴通讯股份有限公司 | Picture processing apparatus and method thereof |
| CN105072337A (en) * | 2015-07-31 | 2015-11-18 | 小米科技有限责任公司 | Method and device for processing pictures |
| CN106503011A (en) * | 2015-09-07 | 2017-03-15 | 高德软件有限公司 | A kind of map data processing method and device |
| CN105824862A (en) * | 2015-10-20 | 2016-08-03 | 维沃移动通信有限公司 | Image classification method based on electronic equipment and electronic equipment |
| CN106844381A (en) * | 2015-12-04 | 2017-06-13 | 富士通株式会社 | Image processing apparatus and method |
| CN105653152A (en) * | 2015-12-23 | 2016-06-08 | 北京金山安全软件有限公司 | Picture processing method and device and electronic equipment |
| CN107015998A (en) * | 2016-01-28 | 2017-08-04 | 阿里巴巴集团控股有限公司 | A kind of image processing method, device and intelligent terminal |
| WO2017129018A1 (en) * | 2016-01-28 | 2017-08-03 | 阿里巴巴集团控股有限公司 | Picture processing method and apparatus, and smart terminal |
| US10846324B2 (en) | 2016-01-28 | 2020-11-24 | Alibaba Group Holding Limited | Device, method, and user interface for managing and interacting with media content |
| US20190026313A1 (en) * | 2016-01-28 | 2019-01-24 | Alibaba Group Holding Limited | Device, method, and user interface for managing and interacting with media content |
| CN107133629A (en) * | 2016-02-29 | 2017-09-05 | 百度在线网络技术（北京）有限公司 | Picture classification method, device and mobile terminal |
| CN107133629B (en) * | 2016-02-29 | 2020-09-04 | 百度在线网络技术（北京）有限公司 | Picture classification method and device and mobile terminal |
| CN106873958B (en) * | 2016-07-06 | 2020-06-23 | 阿里巴巴集团控股有限公司 | Calling method and device of application programming interface |
| CN106873958A (en) * | 2016-07-06 | 2017-06-20 | 阿里巴巴集团控股有限公司 | The call method and device of a kind of API |
| CN106445995A (en) * | 2016-07-18 | 2017-02-22 | 腾讯科技（深圳）有限公司 | Picture classification method and apparatus |
| CN106156799A (en) * | 2016-07-25 | 2016-11-23 | 北京光年无限科技有限公司 | The object identification method of intelligent robot and device |
| WO2018032816A1 (en) * | 2016-08-17 | 2018-02-22 | 中兴通讯股份有限公司 | Mobile terminal-based photo search method and device |
| CN107766357A (en) * | 2016-08-17 | 2018-03-06 | 中兴通讯股份有限公司 | Photo searching method and device based on mobile terminal |
| CN106407383A (en) * | 2016-09-13 | 2017-02-15 | 乐视控股（北京）有限公司 | Picture ranking method and device |
| WO2018232645A1 (en) * | 2017-06-21 | 2018-12-27 | 深圳支点电子智能科技有限公司 | Mobile terminal with photographing function and related product |
| CN107391618A (en) * | 2017-07-05 | 2017-11-24 | Tcl移动通信科技（宁波）有限公司 | A kind of picture classification storage method, mobile terminal and storage device |
| CN107844548A (en) * | 2017-10-30 | 2018-03-27 | 北京锐安科技有限公司 | A kind of data label method and apparatus |
| CN107818160A (en) * | 2017-10-31 | 2018-03-20 | 上海掌门科技有限公司 | Expression label updates and realized method, equipment and the system that expression obtains |
| CN107861750A (en) * | 2017-11-07 | 2018-03-30 | 广东欧珀移动通信有限公司 | A kind of label management method, tag control device and intelligent terminal |
| CN107861750B (en) * | 2017-11-07 | 2020-06-12 | Oppo广东移动通信有限公司 | Label management method, label management device and intelligent terminal |
| CN108173831A (en) * | 2017-12-25 | 2018-06-15 | 北京佳艺徕经贸有限责任公司 | The distribution method and device of a kind of photo |
| CN108121816A (en) * | 2017-12-28 | 2018-06-05 | 广东欧珀移动通信有限公司 | Picture classification method, device, storage medium and electronic equipment |
| CN108121816B (en) * | 2017-12-28 | 2020-09-08 | Oppo广东移动通信有限公司 | Picture classification method and device, storage medium and electronic equipment |
| CN108108494A (en) * | 2018-01-18 | 2018-06-01 | 厦门理工学院 | A kind of picture classification intelligent terminal |
| CN108416003A (en) * | 2018-02-27 | 2018-08-17 | 百度在线网络技术（北京）有限公司 | A kind of picture classification method and device, terminal, storage medium |
| CN108763580A (en) * | 2018-06-08 | 2018-11-06 | Oppo广东移动通信有限公司 | Image processing method and device, electronic equipment, computer storage media |
| CN108829815A (en) * | 2018-06-12 | 2018-11-16 | 四川希氏异构医疗科技有限公司 | A kind of medical image method for screening images |
| CN109033958A (en) * | 2018-06-20 | 2018-12-18 | 北京微播视界科技有限公司 | Increase the method and device of special efficacy for the face of special object |
| CN109047046A (en) * | 2018-08-17 | 2018-12-21 | 张家港康得新光电材料有限公司 | A kind of discharge port grade setting method, device, terminal and storage medium |
| CN110880011B (en) * | 2018-09-05 | 2022-08-16 | 宏达国际电子股份有限公司 | Image segmentation method, device and non-transitory computer readable medium thereof |
| CN110880011A (en) * | 2018-09-05 | 2020-03-13 | 宏达国际电子股份有限公司 | Image segmentation method, device and non-transitory computer readable medium thereof |
| CN109409235A (en) * | 2018-09-27 | 2019-03-01 | Oppo广东移动通信有限公司 | Image-recognizing method and device, electronic equipment, computer readable storage medium |
| CN109829070B (en) * | 2019-01-29 | 2021-01-08 | 维沃移动通信有限公司 | Image searching method and terminal equipment |
| CN109829070A (en) * | 2019-01-29 | 2019-05-31 | 维沃移动通信有限公司 | A kind of image lookup method and terminal device |
| US11669223B2 (en) | 2019-01-29 | 2023-06-06 | Vivo Mobile Communication Co., Ltd. | Method for searching for image and terminal device |
| CN109889437A (en) * | 2019-03-04 | 2019-06-14 | 上海擎语信息科技有限公司 | A kind of novel software of taking pictures |
| CN110222709A (en) * | 2019-04-29 | 2019-09-10 | 上海暖哇科技有限公司 | A kind of multi-tag intelligence marking method and system |
| CN110222709B (en) * | 2019-04-29 | 2022-01-25 | 上海暖哇科技有限公司 | Multi-label intelligent marking method and system |
| CN111368111A (en) * | 2020-02-28 | 2020-07-03 | Oppo（重庆）智能科技有限公司 | Picture retrieval method and device for mobile equipment and mobile equipment |
| CN111709355A (en) * | 2020-06-12 | 2020-09-25 | 北京百度网讯科技有限公司 | Method and device for identifying target area, electronic equipment and road side equipment |
| CN111709357A (en) * | 2020-06-12 | 2020-09-25 | 北京百度网讯科技有限公司 | Method and device for identifying target area, electronic equipment and road side equipment |
| CN111709357B (en) * | 2020-06-12 | 2023-07-28 | 阿波罗智联(北京)科技有限公司 | Method and device for identifying target area, electronic equipment and road side equipment |
| CN111709355B (en) * | 2020-06-12 | 2023-08-29 | 阿波罗智联(北京)科技有限公司 | Method and device for identifying target area, electronic equipment and road side equipment |
| CN111783786A (en) * | 2020-07-06 | 2020-10-16 | 上海摩勤智能技术有限公司 | Picture identification method and system, electronic equipment and storage medium |
| CN111738354A (en) * | 2020-07-20 | 2020-10-02 | 深圳市天和荣科技有限公司 | Automatic recognition training method, system, storage medium and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103995889B (en) | 2017-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103995889A (en) | Method and device for classifying pictures | |
| TWI629644B (en) | Non-transitory computer readable storage medium, methods and systems for detecting and recognizing text from images | |
| US10095925B1 (en) | Recognizing text in image data | |
| CN109284729B (en) | Method, device and medium for acquiring face recognition model training data based on video | |
| CN113255694B (en) | Training image feature extraction model and method and device for extracting image features | |
| US9298982B2 (en) | System and method for computing the visual profile of a place | |
| CN111476284A (en) | Image recognition model training method, image recognition model training device, image recognition method, image recognition device and electronic equipment | |
| US20210141826A1 (en) | Shape-based graphics search | |
| CN103927387A (en) | Image retrieval system, method and device | |
| CN106156347A (en) | Cloud photograph album classification methods of exhibiting, device and server | |
| CN104520848B (en) | According to attendant's search events | |
| CN112328823A (en) | Training method and device for multi-label classification model, electronic equipment and storage medium | |
| TW201546636A (en) | Annotation display assistance device and method of assisting annotation display | |
| Chen et al. | Learning a two-stage CNN model for multi-sized building detection in remote sensing images | |
| CN113822427A (en) | Model training method, image matching device and storage medium | |
| CN105246149B (en) | Geographical position identification method and device | |
| CN106250396B (en) | Automatic image label generation system and method | |
| CN113221918B (en) | Target detection method, training method and device of target detection model | |
| CN113239807B (en) | Method and device for training bill identification model and bill identification | |
| CN103744903A (en) | Sketch based scene image retrieval method | |
| CN110363206B (en) | Clustering of data objects, data processing and data identification method | |
| Memon et al. | IMRBS: image matching for location determination through a region-based similarity technique for CBIR | |
| CN104268504B (en) | Image identification method and device | |
| CN103678458A (en) | Method and system used for image analysis | |
| CN115482436B (en) | Training method and device for image screening model and image screening method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Patentee after: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd. Address before: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Patentee before: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder |