CN103093213A - Video file classification method and terminal - Google Patents
Video file classification method and terminal Download PDFInfo
- Publication number
- CN103093213A CN103093213A CN2013100327818A CN201310032781A CN103093213A CN 103093213 A CN103093213 A CN 103093213A CN 2013100327818 A CN2013100327818 A CN 2013100327818A CN 201310032781 A CN201310032781 A CN 201310032781A CN 103093213 A CN103093213 A CN 103093213A
- Authority
- CN
- China
- Prior art keywords
- video file
- image information
- human face
- face image
- bar
- 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
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Television Signal Processing For Recording (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a video file classification method which comprises the following steps: extracting all facial image information in video files; sequentially comparing the facial image information and initial record strips stored in a data bank; updating the initial record strips or generating new record strips according to compared results; and generating a corresponding folder according to the updated initial record strips or the new record strips, wherein a video file with the same facial image information is stored in each folder. Compared with the prior art, the video file classification method achieves that the video files with the same facial images are classified into the same class, users can conveniently search for all videos of a specific person, operation is easy and convenient, searching time is saved, and a user experience effect is good. The invention further discloses a video file classification terminal.
Description
Technical field
The present invention relates to the document classification technical field, relate more specifically to a kind of video file sorting technique and terminal.
Background technology
Constantly perfect along with mobile terminal function, people not only can utilize mobile terminal to take pictures, and have more realized utilizing mobile terminal to come recorded video, as are household or friend's recorded video.
Yet, present mobile terminal is generally named with the time the video that the user records, namely with time order and function to visual classification, this has just caused when having stored more video file in mobile terminal, be difficult to pick out the video of wishing the someone that sees from various video file, need the user to click one by one video and search, complex operation, lose time and the user experiences not high.
Therefore, be necessary to provide a kind of video file sorting technique and terminal to overcome defects.
Summary of the invention
The purpose of this invention is to provide a kind of video file sorting technique, thereby realize comprising that the video file of identical facial image is divided into a class, and then facilitate the user to search specific someone's video, easy and simple to handle, save time and improved user's experience.
Another object of the present invention is to provide a kind of video file classified terminal, thereby realizes comprising that the video file of identical facial image is divided into a class, and then facilitates the user to search specific someone's video, and is easy and simple to handle, save time and improved user's experience.
For achieving the above object, the invention provides a kind of video file sorting technique, comprise the following steps:
Extract all human face image information in video file;
Compare successively the original records bar of storing in described human face image information and database;
Upgrade described original records bar or generate the new record bar according to comparison result;
Generate corresponding file according to the described original records bar after upgrading or described new record bar, each described file is deposited the video file that contains identical human face image information.
compared with prior art, thereby video file sorting technique of the present invention extracts face images information in video file by video file being carried out recognition of face, successively the original records bar in each human face image information and database is compared afterwards, and upgrade the original records bar or generate the new record bar according to comparison result, new record bar according to the original records bar that upgrades or generation generates corresponding file at last, wherein store the video file that comprises identical human face image information in each file, thereby realized that the video file that will comprise identical human face image information is divided into a class and stores up in the same file folder, facilitated the user to search all video files of specific someone, easy and simple to handle, save time and improved user's experience.
Preferably, described original records bar or described new record bar comprise following information: the sign of the described video file under facial image sign, human face image information, described human face image information and the time point that described human face image information occurs in described video file.
Preferably, described " extracting all human face image information in video file " also comprises before: judge whether there is facial image in described video file, extract human face image information all in video file or add an invalid value in the attribute of described video file according to judged result.
Preferably, described " upgrade described original records bar or generate the new record bar according to comparison result " is specially:
When described human face image information is identical with human face image information in described original records bar, extract and add the sign of the described video file under described human face image information and time point that described human face image information occurs in described video file to described original records bar to realize upgrading described original records bar;
Human face image information in described human face image information and described original records bar generates described new record bar according to the sign of the described video file under the described human face image information of new facial image sign, described human face image information, extraction and the time point that described human face image information occurs not simultaneously in described video file.
Preferably, described facial image is designated numeral or letter.
Correspondingly, the present invention also provides a kind of video file classified terminal, comprising:
Database is for the file of store video files, original records bar and generation;
Extraction module is used for extracting all human face image information of video file;
Comparing module is used for comparing successively the original records bar that described human face image information that described extraction module extracts and described database are stored;
The record strip processing module is used for upgrading described original records bar or generating the new record bar to be stored in described database according to comparison result;
The file generation module is used for generating corresponding file according to the described original records bar after upgrading or described new record bar, and each described file is deposited the video file that contains identical human face image information.
Preferably, described original records bar or described new record bar comprise following information: the sign of the described video file under facial image sign, human face image information, described human face image information and the time point that described human face image information occurs in described video file.
Preferably, described terminal also comprises:
Judging treatmenting module is for whether having facial image in the described video file that judges described database and indicating described extraction module work or add an invalid value in the attribute of described video file according to judged result.
Preferably, described record strip processing module specifically comprises:
The record strip updating block, be used for human face image information when described human face image information and described original records bar when identical, extraction and add the sign of the described video file under described human face image information and time point that described human face image information occurs in described video file to described original records bar with the described original records bar of realization renewal;
The record strip generation unit, for the human face image information of working as described human face image information and described original records bar simultaneously, do not generate described new record bar according to the sign of the described video file under the described human face image information of new facial image sign, described human face image information, extraction and the time point that described human face image information occurs in described video file.
Preferably, described facial image is designated numeral or letter.
By following description also by reference to the accompanying drawings, it is more clear that the present invention will become, and these accompanying drawings are used for explaining embodiments of the invention.
Description of drawings
Fig. 1 is the process flow diagram of video file sorting technique one embodiment of the present invention.
Fig. 2 is the process flow diagram of another embodiment of video file sorting technique of the present invention.
Fig. 3 is the structured flowchart of video file classified terminal one embodiment of the present invention.
Embodiment
With reference now to accompanying drawing, describe embodiments of the invention, in accompanying drawing, similar element numbers represents similar element.
Please refer to Fig. 1, described the workflow of video file sorting technique one embodiment of the present invention.As shown in Figure 1, comprise the following steps:
Step S101 extracts all human face image information in video file; Wherein carry out recognition of face and then extract human face image information and adopted face recognition technology based on video flowing, be specially: video file is decoded into video flowing, successively each two field picture in video flowing is identified, find out all human face image information, wherein human face image information is specially each key feature dot information in facial image, as face information of people etc.;
Step S102 compares the original records bar of storing in described human face image information and database successively; The original records bar of wherein storing in database comprises following information: the sign of the video file under facial image sign, human face image information, human face image information and the time point that human face image information occurs in video file, and wherein the sign of video file can represent the arbitrary parameter of this video file for the title of video file or attribute etc.; Facial image sign can be numeral, letter or other, different facial image signs represent different human face image information, be that different facial image signs represents different people, as some record strips be: 1+aa+ video A+03:45 wherein 1 represents for people's face image identification, aa represents corresponding human face image information, video A that video file identifies, 03:45 represents that time point that human face image information occurs is the moment of 3 minutes and 45 seconds in video A; Wherein aa represents each key feature dot information in facial image;
Step S103 upgrades the original records bar or generates the new record bar according to comparison result; Be specially: when described human face image information is consistent with human face image information in described original records bar (as: record strip 1), extract described human face image information place video file sign and the time point that occurs in video file and be added in original records bar (record strip 1), realize the renewal to original records bar (record strip 1); When the human face image information in described human face image information and described original records bar is inconsistent, generate the new record bar according to the sign of the video file under new facial image sign, described human face image information, described human face image information and the time point that described human face image information occurs in video file;
Step S104, generate corresponding file according to the original records bar after upgrading or new record bar, the respectively corresponding file of original records bar after wherein each upgrades or new record bar, store all video files corresponding to human face image information in corresponding record strip in file, that is: realized that the video file that will comprise identical human face image information is stored in a file, completed video file has been classified according to facial image, facilitated the user to search.
Please refer to Fig. 2, described the process flow diagram of another embodiment of video file sorting technique of the present invention.As shown in Figure 2, comprise the following steps:
Step S201 starts mobile terminal, and all video files of storing in mobile terminal system autoscan database are also got first video file; As, store video file A, B and C in database, get first video file A;
Step S202 carries out recognition of face and judges whether there is facial image in video file video file, if not, and execution in step S203, otherwise, execution in step S204; As, video file A is carried out recognition of face and judges whether there is facial image in video file A, if not, execution in step S203, otherwise, execution in step S204;
Step S203 adds an invalid value in the attribute of video file; As, there is not facial image in step S202 judgement video file A, therefore add an invalid value in the attribute of video file A;
Step S204 extracts human face image information all in video file; As, extract two the human face image information aa and the bb that comprise in video file A;
Step S205 compares all original records bars of storing in the human face image information in video file and database successively; As, store 3 original records bars in database, be respectively: 1+aa+ video D+04:21,2+bb+ video E+03:20 and 3+cc+ video F+02:21, first 3 original records bars in the human face image information aa in video file A and database are compared successively, then 3 original records bars in the human face image information bb in video file A and database are compared successively;
Step S206 judges whether there is described human face image information in the original records bar, if exist, and execution in step S207, otherwise, execution in step S208;
Step S207, extract and add the sign of the video file under described human face image information and the time point that occurs in this video file to the original records bar that comprises described human face image information, realize the renewal to the original records bar; The time point that occurs in video file A as obtaining human face image information aa and bb and human face image information aa and bb after video file A is identified, as be respectively 04:32 and 02:13, original records bar in human face image information aa and database is compared successively, obtain comprising in database identical human face image information aa, the original records bar after upgraded original records bar 1+aa+ video D+04:21 this moment: 1+aa+ video D+04:21+ video A+04:32; Afterwards human face image information bb and 3 original records bars are compared successively, complete the original records bar according to comparison result: the renewal of 2+bb+ video E+03:20, the original records bar after being upgraded: 2+bb+ video E+03:20+ video A+02:13; That is: each record strip is corresponding to a facial image, therefore when having a plurality of facial image in video file, the sign of this video file can be present in a plurality of record strips;
Step S208 generates described new record bar according to the sign of the described video file under new facial image sign, described human face image information, described human face image information and the time point that described human face image information occurs in described video file; In the present embodiment, the facial image sign is numeral and arranges in order, as: in database in existing original records bar facial image sign comprise 1-6, in the new record bar that generates, facial image is designated 7, as: if being identified, video file A obtains human face image information dd, find not have identical human face image information dd in database after comparison, the time point that extraction human face image information dd occurs in video file A is 01:30, and generates the new record bar: 7+dd+ video A+01:30;
Step S209 judges whether described video file is last, if, execution in step S211, otherwise, execution in step S210; As, judge that whether video file A is last in database, if, execution in step S211, otherwise, execution in step S210;
Step S210 gets next video file and execution in step S202; As, get video file B;
Step S211 generates respectively corresponding file according to each the original records bar after upgrading or the new record bar of generation, stores all video files in corresponding record strip in file; As: according to the original records bar after upgrading: 1+aa+ video D+04:21+ video A+04:32 generates corresponding file, folder name is called: 1+D+A, certainly, can also be other naming rules, wherein store the concordance list of video file D and video file A in file 1+D+A, every index in this concordance list represents respectively a video file, click every index and just can open corresponding video file, and video file D and A comprises same people's face information aa; According to the new record bar: 7+dd+ video A+01:30 generates corresponding file 7+A, stores video file A in file 7+A;
Step S212 completes the assorting process to video file.
wherein, when needs are searched someone's video file, can take pictures by the camera of mobile terminal, extract corresponding human face image information and compare with the original records bar of database storage from photo, find the original records bar that comprises identical human face image information, and each original records bar is all to there being a file, store all video files that comprise described human face image information in file, and then can find all video files of this people and the time point that human face image information occurs in video file, simple to operation and saved the time.
Please refer to Fig. 3, described the structured flowchart of video file classified terminal one embodiment of the present invention.As shown in Figure 3, video file classified terminal 100 comprises:
Comparing module 12 is used for comparing successively original records bar that described human face image information that described extraction module 11 extracts and described database 10 store, judges whether there is the original records bar that comprises described human face image information in database 10;
Record strip processing module 13 is upgraded described original records bar or is generated the new record bar according to comparison result; Concrete, record strip processing module 13 comprises record strip updating block 131 and record strip generation unit 132; Record strip updating block 131 is used for human face image information at described human face image information and described original records bar when identical, that is: exist when comprising the original records bar of described human face image information in database 10, extract and add the sign of the video file under described human face image information and time point that described human face image information occurs to described original records bar in video file, completing the renewal to the original records bar; Record strip generation unit 132 is used in the human face image information of described human face image information and original records bar not simultaneously, according to the sign of the described video file under the described human face image information of new facial image sign, described human face image information, extraction and the described new record bar of time point generation that described human face image information occurs in described video file;
Judging treatmenting module 15 is used for judging whether described video file exists facial image and work or add an invalid value in the attribute of video file according to judged result indication extraction module 11, as adding invalid value 0.
Wherein, original records bar or new record bar comprise following information: the sign of the video file under facial image sign, human face image information, human face image information and the time point that described human face image information occurs in described video file, wherein facial image is designated numeral or letter.
can find out according to above description, at first video file classified terminal 100 carries out recognition of face and judges whether there is facial image in video file by 15 pairs of video files of judging treatmenting module, if exist, extract human face image information all in video file by extraction module 11, afterwards by comparing module 12 with the human face image information that identifies successively with database 10 in the original records bar compare, judge whether described human face image information is identical with human face image information in the original records bar, if identical, add the sign of the video file under described human face image information and time point that described human face image information occurs in video file to existing original records bar by record strip updating block 131, if it is not identical, generate corresponding new record bar and be saved in database 10 by record strip generation unit 132, original records bar or new record bar after upgrading generates respectively corresponding file for each by file generation module 14 again, file comprises the video file of the sign correspondence of all video files in corresponding record strip, the video file that comprises at last identical facial image is divided into a class and is stored in the same file folder, facilitated the user to search all video files of specific someone and the time point that occurs in video, save time and user's experience effect good.
Above invention has been described in conjunction with most preferred embodiment, but the present invention is not limited to the embodiment of above announcement, and should contain various modification, equivalent combinations of carrying out according to essence of the present invention.
Claims (10)
1. a video file sorting technique, is characterized in that, comprises the following steps:
Extract all human face image information in video file;
Compare successively the original records bar of storing in described human face image information and database;
Upgrade described original records bar or generate the new record bar according to comparison result;
Generate corresponding file according to the described original records bar after upgrading or described new record bar, each described file is deposited the video file that contains identical human face image information.
2. video file sorting technique as claimed in claim 1, it is characterized in that, described original records bar or described new record bar comprise following information: the sign of the described video file under facial image sign, human face image information, described human face image information and the time point that described human face image information occurs in described video file.
3. video file sorting technique as claimed in claim 2, is characterized in that, described " extracting all human face image information in video file " also comprises before:
Judge whether there is facial image in described video file, extract human face image information all in described video file or add an invalid value in the attribute of described video file according to judged result.
4. video file sorting technique as claimed in claim 2, is characterized in that, described " upgrade described original records bar or generate the new record bar according to comparison result " is specially:
When described human face image information is identical with human face image information in described original records bar, extract and add the sign of the described video file under described human face image information and time point that described human face image information occurs in described video file to described original records bar to realize upgrading described original records bar;
Human face image information in described human face image information and described original records bar generates described new record bar according to the sign of the described video file under the described human face image information of new facial image sign, described human face image information, extraction and the time point that described human face image information occurs not simultaneously in described video file.
5. video file sorting technique as claimed in claim 2, is characterized in that, described facial image is designated numeral or letter.
6. a video file classified terminal, is characterized in that, described terminal comprises:
Database is for the file of store video files, original records bar and generation;
Extraction module is used for extracting all human face image information of video file;
Comparing module is used for comparing successively the original records bar that described human face image information that described extraction module extracts and described database are stored;
The record strip processing module is used for upgrading described original records bar or generating the new record bar to be stored in described database according to comparison result;
The file generation module is used for generating corresponding file according to the described original records bar after upgrading or described new record bar, and each described file is deposited the video file that contains identical human face image information.
7. video file classified terminal as claimed in claim 6, it is characterized in that, described original records bar or described new record bar comprise following information: the sign of the described video file under facial image sign, human face image information, described human face image information and the time point that described human face image information occurs in described video file.
8. video file classified terminal as claimed in claim 7, is characterized in that, also comprises:
Judging treatmenting module is for whether having facial image in the described video file that judges described database and indicating described extraction module work or add an invalid value in the attribute of described video file according to judged result.
9. video file classified terminal as claimed in claim 7, is characterized in that, described record strip processing module specifically comprises:
The record strip updating block, be used for human face image information when described human face image information and described original records bar when identical, extraction and add the sign of the described video file under described human face image information and time point that described human face image information occurs in described video file to described original records bar with the described original records bar of realization renewal;
The record strip generation unit, be used for when the human face image information of described human face image information and described original records bar not simultaneously, according to the sign of the described video file under the described human face image information of new facial image sign, described human face image information, extraction and the described new record bar of time point generation that described human face image information occurs in described video file.
10. video file classified terminal as claimed in claim 7, is characterized in that, described facial image is designated numeral or letter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310032781.8A CN103093213B (en) | 2013-01-28 | 2013-01-28 | Video file classification method and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310032781.8A CN103093213B (en) | 2013-01-28 | 2013-01-28 | Video file classification method and terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103093213A true CN103093213A (en) | 2013-05-08 |
| CN103093213B CN103093213B (en) | 2016-11-16 |
Family
ID=48205761
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310032781.8A Active CN103093213B (en) | 2013-01-28 | 2013-01-28 | Video file classification method and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103093213B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106604051A (en) * | 2016-12-20 | 2017-04-26 | 广州华多网络科技有限公司 | Live channel recommending method and device |
| CN111553191A (en) * | 2020-03-30 | 2020-08-18 | 深圳壹账通智能科技有限公司 | Video classification method and device based on face recognition and storage medium |
| WO2020173314A1 (en) * | 2019-02-27 | 2020-09-03 | 杭州海康威视数字技术股份有限公司 | Personnel statistical method and device and electronic device |
| CN115460446A (en) * | 2022-08-19 | 2022-12-09 | 上海爱奇艺新媒体科技有限公司 | Alignment method and device for multiple paths of video signals and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101278286A (en) * | 2005-09-30 | 2008-10-01 | 皇家飞利浦电子股份有限公司 | Method and apparatus for enabling browsing of images |
| CN102355588A (en) * | 2011-08-25 | 2012-02-15 | 中兴通讯股份有限公司 | Method and system for synchronously browsing electronic photo albums |
| CN102682111A (en) * | 2012-05-11 | 2012-09-19 | 广东欧珀移动通信有限公司 | Picture retrieval method |
-
2013
- 2013-01-28 CN CN201310032781.8A patent/CN103093213B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101278286A (en) * | 2005-09-30 | 2008-10-01 | 皇家飞利浦电子股份有限公司 | Method and apparatus for enabling browsing of images |
| CN102355588A (en) * | 2011-08-25 | 2012-02-15 | 中兴通讯股份有限公司 | Method and system for synchronously browsing electronic photo albums |
| CN102682111A (en) * | 2012-05-11 | 2012-09-19 | 广东欧珀移动通信有限公司 | Picture retrieval method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106604051A (en) * | 2016-12-20 | 2017-04-26 | 广州华多网络科技有限公司 | Live channel recommending method and device |
| WO2020173314A1 (en) * | 2019-02-27 | 2020-09-03 | 杭州海康威视数字技术股份有限公司 | Personnel statistical method and device and electronic device |
| CN111553191A (en) * | 2020-03-30 | 2020-08-18 | 深圳壹账通智能科技有限公司 | Video classification method and device based on face recognition and storage medium |
| CN115460446A (en) * | 2022-08-19 | 2022-12-09 | 上海爱奇艺新媒体科技有限公司 | Alignment method and device for multiple paths of video signals and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103093213B (en) | 2016-11-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103608826B (en) | Annotated using product in the video of Web information mining | |
| CN109213882B (en) | Picture ordering method and terminal | |
| US20220172476A1 (en) | Video similarity detection method, apparatus, and device | |
| CN112287914B (en) | PPT video segment extraction method, device, equipment and medium | |
| CN108399180B (en) | Knowledge graph construction method and device and server | |
| CN106156347A (en) | Cloud photograph album classification methods of exhibiting, device and server | |
| CN104426841A (en) | Method for arranging background image, and correlation server and system | |
| CN105744292A (en) | Video data processing method and device | |
| CN102156751A (en) | Method and device for extracting video fingerprint | |
| US10380267B2 (en) | System and method for tagging multimedia content elements | |
| CN103150359B (en) | Micro-blog information display packing and device | |
| US20150278248A1 (en) | Personal Information Management Service System | |
| CN104463177A (en) | Similar face image obtaining method and device | |
| CN105243084A (en) | Photographed image file storage method and system and photographed image file search method and system | |
| CN103699679A (en) | Method and equipment for retrieving information of target objects | |
| CN108255915A (en) | File management method and device and machine-readable storage medium | |
| CN103902564A (en) | File showing method and device | |
| CN107515950A (en) | A kind of image processing method, device, terminal and computer-readable recording medium | |
| CN103093213A (en) | Video file classification method and terminal | |
| CN115062186A (en) | Video content retrieval method, device, equipment and storage medium | |
| CN102932421A (en) | Cloud back-up method and device | |
| CN113568934A (en) | Data query method and device, electronic equipment and storage medium | |
| CN104424109B (en) | Information processing method and electronic equipment | |
| CN112256836A (en) | Recording data processing method and device and server | |
| CN115983873B (en) | User data analysis management system and method based on big data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| 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 |