CN108984638A - A kind of photo name processing method - Google Patents
A kind of photo name processing method Download PDFInfo
- Publication number
- CN108984638A CN108984638A CN201810648916.6A CN201810648916A CN108984638A CN 108984638 A CN108984638 A CN 108984638A CN 201810648916 A CN201810648916 A CN 201810648916A CN 108984638 A CN108984638 A CN 108984638A
- Authority
- CN
- China
- Prior art keywords
- photo
- name
- processing method
- names
- geographic position
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Character Discrimination (AREA)
Abstract
The present invention relates to a kind of photos to name processing method.Photo of the present invention names processing method, by identifying the text for including in photo, face information, combining geographic location, time, photo is named with popular label, overcomes the trouble of traditional manual name, and the title of photo is made to associate with the content of photo, solve the time names the defect that can not reflect photo content automatically, facilitates the retrieval and arrangement of photo.
Description
Technical field
The present invention relates to a kind of photos to name processing method, belongs to the technical field of image procossing.
Background technique
Currently, the camera function of mobile phone is more and more abundant, people are also more and more in daily life to be remembered by photo
Fine moment in record life.However, the frequency of people's mobile phone photograph is higher and higher, especially when people go sight-seeing at scenic spot,
When party, it will usually shoot a large amount of photos by mobile phone.With mobile phone EMS memory storage number of pictures increase, the name of photo,
Arrangement problem also highlights.
In the prior art to the mode of photo name mainly include automatically recorded with shooting time after the completion of photograph taking,
By the pixel of photo, shooting equipment, shooting contextual model etc. in a manner of name.But these naming methods in the prior art are not
It arranges and searches conducive to the photo for carrying out the later period.
Face and character area usually are detected by object detection algorithms in the prior art, for example, document " [1] YOLOv3:
An Incremental Improvement.arXiv preprint arXiv:1804.02767,2018. " discloses related skill
Art；
Characters name corresponding with face is identified by face recognition algorithms, and the text in image is obtained by Text region
Word content belongs to the prior art；For example, document " Kan M, Kan M, Shan S, et al.Funnel-structured
cascade for multi-view face detection with alignment-awareness[J]
.Neurocomputing, 2017,221 (C): 138-145 " and " An End-to-End Trainable Neural Network
for Image-based Sequence Recognition and Its Application to Scene Text
Recognition[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,
2016, PP (99): the related algorithm that face and text information are identified in human face region and character area is disclosed in 1-1 ".
Summary of the invention
In view of the deficiencies of the prior art, the present invention provides a kind of photo name processing method.
The technical solution of the present invention is as follows:
A kind of photo name processing method, comprising:
1) it takes pictures and obtains photo to be stored；
The present invention using application terminal as executing subject, the application terminal be mobile phone with camera function, tablet computer or
Smartwatch etc..
2) shooting time and geographic position name of photo are obtained；The longitude and latitude of picture-taking location is obtained by GPS module
Degree, is then converted into geographic position name for longitude and latitude by web search；
3) it detects and identifies the face in photo and text；
Human face region and character area are detected by object detection algorithms first, then identify human face region and literal field
Characters name and text information in domain；Characters name identifies that human face region obtains by face recognition technology；
If only one character area in photo, the then text named the text information in the character area as photo
Character segment；If there are more than one character areas in photo, the corresponding text of the maximum character area of region area is selected
The word segment that information is named as photo；
4) label recommendations are generated；
The title that current geographic position corresponds to historical photograph is obtained, the tag entry in name of pictures is extracted, to different label items
The number of appearance is counted；The corresponding tag entry of every photo, tag entry is word or phrase, summarises photo content, example
Such as: " self-timer ", " taking a group photo ", " seeing sunrise " etc..The corresponding historical photograph of current geographic position usually has multiple；
5) shooting time for the historical photograph that step 4) obtains is parsed by the metadata of photo and is extracted wherein
One hour value H1；Then difference H between passing through1-H0Photo is weighted, F (H1-H0)；H0To await orders
One hour value in the name photograph taking time；
Weighted results are sorted from large to small, choose three labels of maximum weight as label recommendations item, it is selective；
6) name of pictures is generated；Photo is stored, while name of pictures upload cloud being stored；Name of pictures
Format be " tag entry _ geographic position name _ characters name _ text information _ shooting time "；Wherein tag entry by user from
It is chosen in label candidate item, can also voluntarily name label.
The photo of storage is for generating popular label, picture classification etc. in later period name；The photo for uploading cloud is used for it
He generates label recommendations when generating photo name at equipment.
It is preferred according to the present invention, with symbol " * " generation on corresponding position if the one of them of name can not obtain
It replaces.
It is preferred according to the present invention, in the step 3), if face recognition module can not identify and face information phase
Corresponding characters name then replaces corresponding characters name with " * " symbol.
Preferred according to the present invention, in the step 4), the title that current geographic position corresponds to historical photograph passes through search
Cloud storage obtains.
It is preferred according to the present invention, if if the name that current geographic position corresponds to historical photograph can not be obtained in step 4)
Claim, then by the H in step 5)1Use H2Instead of；H2For the historical record of equipment name.For example, under conditions of no network connection just
The title of historical photograph under current geographic position can not be obtained.Name of pictures can be stored in equipment after generating name of pictures by equipment
It is interior.
It is preferred according to the present invention, in the step 6), if identifying multiple characters names, by multiple characters names
By being exported behind " | " interval.
The invention has the benefit that
1. photo of the present invention names processing method, by identifying the text for including in photo, face information, in conjunction with
Geographical location, time, and popular label are named photo, overcome the trouble of traditional manual name, and make photo
Title associates with the content of photo, solves the time and names the defect that can not reflect photo content automatically, facilitates photo
Retrieval and arrangement.
Detailed description of the invention
Fig. 1 is the flow chart that photo of the present invention names processing method.
Specific embodiment
Below with reference to embodiment and Figure of description, the present invention will be further described, but not limited to this.
Embodiment 1
As shown in Figure 1.
A kind of photo name processing method, comprising:
1) it takes pictures and obtains photo to be stored；
The present invention using application terminal as executing subject, the application terminal be mobile phone with camera function, tablet computer or
Smartwatch etc..
2) shooting time and geographic position name of photo are obtained；The longitude and latitude of picture-taking location is obtained by GPS module
Degree, is then converted into geographic position name for longitude and latitude by web search；GPS module herein is the GPS positioning mould of mobile phone
Block, by calling the module to obtain latitude and longitude coordinates；
3) it detects and identifies the face in photo and text；
Human face region and character area are detected by object detection algorithms first, then identify human face region and literal field
Characters name and text information in domain；Characters name identifies that human face region obtains by face recognition technology；
If only one character area in photo, the then text named the text information in the character area as photo
Character segment；If there are more than one character areas in photo, the corresponding text of the maximum character area of region area is selected
The word segment that information is named as photo；
4) label recommendations are generated；
The title that current geographic position corresponds to historical photograph is obtained, the tag entry in name of pictures is extracted, to different label items
The number of appearance is counted；The corresponding tag entry of every photo, tag entry is word or phrase, summarises photo content, example
Such as: " self-timer ", " taking a group photo ", " seeing sunrise " etc..The corresponding historical photograph of current geographic position usually has multiple；
5) shooting time for the historical photograph that step 4) obtains is parsed by the metadata of photo and is extracted wherein
One hour value H1；That is, " HH " value in " yyyy-MM-dd HH:mm:ss " time format；Then difference H between passing through1-H0To photo
It is weighted, F (H1-H0)；H0For the one hour value in the photograph taking time to be named；
Weighted results are sorted from large to small, choose three labels of maximum weight as label recommendations item, it is selective；
6) name of pictures is generated；Photo is stored, while name of pictures upload cloud being stored；Name of pictures
Format be " tag entry _ geographic position name _ characters name _ text information _ shooting time "；Wherein tag entry by user from
It is chosen in label candidate item, can also voluntarily name label.Mountain-climbing _ gloomy inner park South-Sky Gate _ the Xiao Ming of Mount Taishan country | I _ Nan Tian
Door _ 2008010110:01:01；
The photo of storage is for generating popular label, picture classification etc. in later period name；The photo for uploading cloud is used for it
He generates label recommendations when generating photo name at equipment.
Embodiment 2
Photo as described in Example 1 names processing method, further, if the one of them of name can not obtain
It is replaced on corresponding position with symbol " * ".In the step 3), if face recognition module can not identify and face information phase
Corresponding characters name then replaces corresponding characters name with " * " symbol.
Embodiment 3
Photo as described in Example 1 names processing method, and further, current geographic position corresponds to the name of historical photograph
Claim to obtain by the storage of search cloud.
Embodiment 4
Photo as described in Example 1 names processing method, further, if if can not obtain current in step 4)
Geographical location corresponds to the title of historical photograph, then by the H in step 5)1Use H2Instead of；H2For the historical record of equipment name.Example
Such as, the title of historical photograph under current geographic position can not be just obtained under conditions of no network connection.Equipment generates photo name
Name of pictures can be stored in equipment after title.
Embodiment 5
Photo as described in Example 1 names processing method, further, in the step 6), if identified multiple
Characters name, then by multiple characters names by being exported behind " | " interval.
Claims (5)
1. a kind of photo names processing method characterized by comprising
1) it takes pictures and obtains photo to be stored；
2) shooting time and geographic position name of photo are obtained；The longitude and latitude of picture-taking location is obtained by GPS module, so
Longitude and latitude is converted by geographic position name by web search afterwards；
3) it detects and identifies the face in photo and text；
Human face region and character area are detected by object detection algorithms first, are then identified in human face region and character area
Characters name and text information；Characters name identifies that human face region obtains by face recognition technology；
If only one character area in photo, the then character portion named the text information in the character area as photo
Point；If there are more than one character areas in photo, the corresponding text information of the maximum character area of region area is selected
Word segment as photo name；
4) label recommendations are generated；
The title that current geographic position corresponds to historical photograph is obtained, the tag entry in name of pictures is extracted, occurs to different label items
Number counted；
5) shooting time for the historical photograph that step 4) obtains is parsed by the metadata of photo and is extracted therein small
Duration H1；Then difference H between passing through1-H0Photo is weighted, F (H1-H0)；H0For photograph to be named
One hour value in piece shooting time；
Weighted results are sorted from large to small, choose three labels of maximum weight as label recommendations item, it is selective；
6) name of pictures is generated；Photo is stored, while name of pictures upload cloud being stored；The lattice of name of pictures
Formula is " tag entry _ geographic position name _ characters name _ text information _ shooting time "；Wherein tag entry is by user from label
It is chosen in candidate item, can also voluntarily name label.
2. photo according to claim 1 names processing method, which is characterized in that if the one of them of name can not obtain
It obtains and is then replaced on corresponding position with symbol " * "；In the step 3), believe if face recognition module can not be identified with face
The corresponding characters name of manner of breathing then replaces corresponding characters name with " * " symbol.
3. photo according to claim 1 names processing method, which is characterized in that in the step 4), current geographic position
The title for setting corresponding historical photograph is obtained by the storage of search cloud.
4. photo according to claim 1 names processing method, which is characterized in that if if can not obtain in step 4)
Current geographic position corresponds to the title of historical photograph, then by the H in step 5)1Use H2Instead of；H2For the history note of equipment name
Record.
5. photo according to claim 1 names processing method, which is characterized in that in the step 6), if identified
Multiple characters names, then by multiple characters names by being exported behind " | " interval.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810648916.6A CN108984638B (en) | 2018-06-22 | 2018-06-22 | Photo naming processing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810648916.6A CN108984638B (en) | 2018-06-22 | 2018-06-22 | Photo naming processing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108984638A true CN108984638A (en) | 2018-12-11 |
| CN108984638B CN108984638B (en) | 2020-05-19 |
Family
ID=64538111
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810648916.6A Expired - Fee Related CN108984638B (en) | 2018-06-22 | 2018-06-22 | Photo naming processing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108984638B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111382744A (en) * | 2018-12-28 | 2020-07-07 | Tcl集团股份有限公司 | Shop information acquisition method and device, terminal equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102202173A (en) * | 2010-03-23 | 2011-09-28 | 三星电子（中国）研发中心 | Photo automatically naming method and device thereof |
| CN103259915A (en) * | 2012-02-20 | 2013-08-21 | 宇龙计算机通信科技(深圳)有限公司 | Photo naming method and mobile terminal |
| CN105528444A (en) * | 2015-12-23 | 2016-04-27 | 北京奇虎科技有限公司 | Method and device for generating photo album |
| CN105956080A (en) * | 2016-04-29 | 2016-09-21 | 乐视控股（北京）有限公司 | Photo naming processing method and apparatus |
-
2018
- 2018-06-22 CN CN201810648916.6A patent/CN108984638B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102202173A (en) * | 2010-03-23 | 2011-09-28 | 三星电子（中国）研发中心 | Photo automatically naming method and device thereof |
| CN103259915A (en) * | 2012-02-20 | 2013-08-21 | 宇龙计算机通信科技(深圳)有限公司 | Photo naming method and mobile terminal |
| CN105528444A (en) * | 2015-12-23 | 2016-04-27 | 北京奇虎科技有限公司 | Method and device for generating photo album |
| CN105956080A (en) * | 2016-04-29 | 2016-09-21 | 乐视控股（北京）有限公司 | Photo naming processing method and apparatus |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111382744A (en) * | 2018-12-28 | 2020-07-07 | Tcl集团股份有限公司 | Shop information acquisition method and device, terminal equipment and storage medium |
| CN111382744B (en) * | 2018-12-28 | 2024-06-18 | Tcl科技集团股份有限公司 | Shop information acquisition method and device, terminal equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108984638B (en) | 2020-05-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8315463B2 (en) | User interface for face recognition | |
| US7711145B2 (en) | Finding images with multiple people or objects | |
| JP5461523B2 (en) | Image classification using shooting position sequence information | |
| CN103080951B (en) | For the method and apparatus identifying the object in media content | |
| US20130170738A1 (en) | Computer-implemented method, a computer program product and a computer system for image processing | |
| CN112001347B (en) | Action recognition method based on human skeleton morphology and detection target | |
| US20070098303A1 (en) | Determining a particular person from a collection | |
| CN104331509A (en) | Picture managing method and device | |
| CN104426841A (en) | Method for arranging background image, and correlation server and system | |
| CN103412951A (en) | Individual-photo-based human network correlation analysis and management system and method | |
| US20240037142A1 (en) | Systems and methods for filtering of computer vision generated tags using natural language processing | |
| CN110297934A (en) | A kind of image processing method, device and storage medium | |
| CN103699679A (en) | Method and equipment for retrieving information of target objects | |
| CN104679879B (en) | A kind of photo intelligent storage method and device | |
| CN104239568A (en) | System and method for quickly searching photo based on description of photo | |
| CN104331515B (en) | A kind of method and system for automatically generating tourism diary | |
| WO2019218459A1 (en) | Photo storage method, storage medium, server, and apparatus | |
| CN105159976A (en) | Image file processing method and system | |
| US20130343618A1 (en) | Searching for Events by Attendants | |
| CN107967339A (en) | Image processing method, device, computer-readable recording medium and computer equipment | |
| CN109670453B (en) | Method for extracting short video theme | |
| CN103428537A (en) | Video processing method and video processing device | |
| CN105159959A (en) | Image file processing method and system | |
| CN106250396B (en) | Automatic image label generation system and method | |
| CN118015290B (en) | Image feature processing method, image comparison method, model training method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200519 Termination date: 20210622 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |