CN104375892B - A kind of intelligence quickly starts the method, device and mobile terminal for realizing recognition of face - Google Patents
A kind of intelligence quickly starts the method, device and mobile terminal for realizing recognition of face Download PDFInfo
- Publication number
- CN104375892B CN104375892B CN201410650505.2A CN201410650505A CN104375892B CN 104375892 B CN104375892 B CN 104375892B CN 201410650505 A CN201410650505 A CN 201410650505A CN 104375892 B CN104375892 B CN 104375892B
- Authority
- CN
- China
- Prior art keywords
- path
- face
- picture
- current image
- thumbnail
- 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.)
- Active
Links
Landscapes
- Processing Or Creating Images (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a kind of intelligence quickly start realize recognition of face method, device and mobile terminal, this method include obtain current image path the step of；The step of obtaining current image according to the path, generate the thumbnail of the picture；The step of thumbnail is passed to Face datection storehouse, carries out Face datection.Using the path for obtaining current image, the mode of current image is read, avoids user in quick sliding picture, apparent Caton phenomenon caused by detecting per pictures；It creates background thread and carries out picture decoding and Face datection, realize quick startup face identification functions；The thumbnail of current image is generated, adjusts the resolution ratio of current image, improves the speed of recognition of face, after quickly face is oriented, user is reminded to carry out the processing of the picture, improves the comfort level of user experience.
Description
Technical field
The present invention relates to Preprocessing Technique, particularly a kind of intelligence quickly to start the method for realizing recognition of face, dress
It puts and mobile terminal.
Background technology
As smart mobile phone is increasingly popularized, the pixel of mobile phone camera is higher and higher, and user uses mobile phone camera self-timer
Frequency is also higher and higher.It is often in need to go to compile oneself some interested picture after user's self-timer complete photo
Processing is collected, for example some positions of the face of the photo of self-timer are carried out with blush addition, eyes expand or carry out area to face
A series of effect process of makeups such as domain processing.
Inevitably to be related to the action of Face datection when being browsed to photo when carrying out above-mentioned processing, and face is examined
The faster the better for the speed needs of survey, such as when user's fast browsing and slip photo, it is necessary to quickly start Face datection, with
It can prompt the user whether that photo editing can be carried out in time.However, the startup speed of existing face identification system also has
It waits to improve, identifies that the speed of face is slower, and in continuous fast browsing photo, it may appear that apparent Caton phenomenon is used
Family experience comfort level is bad.
The content of the invention
The present invention provides a kind of intelligence and quickly starts the method, device and mobile terminal for realizing recognition of face, solves photograph
In piece navigation process, face detection system occurs apparent when starting slow slow, recognition of face speed and continuous fast browsing photo
The problem of Caton phenomenon, improves the comfort level of user experience.
The present invention quickly starts the method for realizing recognition of face to realize that above-mentioned technical problem provides a kind of intelligence, including such as
Lower step：
Obtain the path of current image；
Current image is obtained according to the path, generates the thumbnail of the picture；
The thumbnail is passed to Face datection storehouse, carries out Face datection.
Further, the path for obtaining current image includes, and obtains the path of the browsed picture of record, described
Path is sorted according to browsing order, reads path of the path as current image for coming end.
Further, the path of browsed picture is recorded using tabular array, the path is suitable according to the time of browsing
Sequence sorts；
The path that the reading comes end includes as the path of current image：Read the road for coming tabular array end
Path of the footpath as current image.
Further, described to obtain current image according to the path, generating the thumbnail of the picture includes, and creates backstage
Thread obtains current image according to the path by the background thread, decodes the picture, the decoded picture is contracted
It puts as the thumbnail of default resolution ratio.
Further, the thumbnail is passed to Face datection storehouse, carries out Face datection and include the following steps：
The code stream that the thumbnail is obtained by lossless compression is read in into memory, incoming Face datection is called by local
Storehouse；
When detecting face, the data of the current image are returned to background thread, according to drawing the data
The small icon of current image and display.
Further, the code stream that the thumbnail is obtained by lossless compression further includes before reading in memory,
Encapsulate Face datection storehouse；
It is described to be passed by local call after the code stream that the thumbnail is obtained by lossless compression reads in memory
It is further included before entering Face datection storehouse,
Thumbnail in the memory is transformed into yuv space by rgb space.
Second aspect, a kind of intelligence quickly start the device for realizing recognition of face, including：
Path acquisition module, for obtaining the path of current image；
Thumbnail generation module for obtaining current image according to the path, generates the thumbnail of the picture；
Face detection module for the thumbnail to be passed to Face datection storehouse, carries out Face datection.
Further, the path acquisition module includes path recording unit, paths ordering unit and path reading unit；
The path recording unit, for recording the path of browsed picture；
The paths ordering unit, for the path to be sorted according to browsing order；
The path reading unit, for reading path of the path as current image for coming end.
Further, the path acquisition module includes path recording unit, paths ordering unit and path reading unit；
The path recording unit, for recording the path of browsed picture using tabular array；
The paths ordering unit, for the path to be sorted according to the time sequencing of browsing；
The path reading unit, for reading path of the path as current image for coming tabular array end.
Further, the thumbnail generation module includes picture acquiring unit, picture decoding unit and picture unit for scaling；
The picture acquiring unit for creating background thread, is obtained currently by the background thread according to the path
Picture；
The picture decoding unit, for decoding the picture；
The picture unit for scaling, for the decoded picture scaling to be become to the thumbnail of default resolution ratio.
Further, the face detection module includes reading in unit, detection unit and icon drawing unit；
The code stream that the thumbnail is obtained by lossless compression is read in memory, passes through local calling by the reading unit
Incoming Face datection storehouse；
The detection unit, for when detecting face, returning to the data of the current image to background thread；
Icon drawing unit, for drawing small icon and the display of the current image according to the data.
Further, which further includes：
Storehouse package module, for encapsulating Face datection storehouse；
Format converting module, for the thumbnail in the memory to be transformed into yuv space by rgb space.
The third aspect, a kind of mobile terminal, including the above-mentioned quick device for starting realization recognition of face of intelligence.
The present invention slides the path of current image when picture stops by obtaining user；It is obtained according to the path current
Picture generates the thumbnail of the picture；The thumbnail is passed to Face datection storehouse, carries out Face datection.Worked as using obtaining
The mode of current image is read in the path of preceding picture, avoids user in quick sliding picture, caused by detecting per pictures
Apparent Caton phenomenon；It creates background thread and carries out picture decoding and Face datection, realize quick startup face identification functions；It is raw
Into the thumbnail of current image, the resolution ratio of current image is adjusted, the speed of recognition of face is improved, is quickly orienting face
Afterwards, user is reminded to carry out the processing of the picture, improves the comfort level of user experience.
Description of the drawings
Fig. 1 is that a kind of intelligence that first embodiment of the invention provides quickly starts the flow chart for realizing face identification method；
Fig. 2 is that a kind of intelligence that second embodiment of the invention provides quickly starts the flow chart for realizing face identification method；
Fig. 3 is that a kind of intelligence that third embodiment of the invention provides quickly starts the flow chart for realizing face identification method；
Fig. 4 is that a kind of intelligence that fourth embodiment of the invention provides quickly starts the flow chart for realizing face identification method；
Fig. 5 is that the structure for the device that a kind of intelligence that fifth embodiment of the invention provides quickly starts realization recognition of face is shown
It is intended to.
Specific embodiment
For make present invention solves the technical problem that, the technical solution that uses and the technique effect that reaches it is clearer, below
The technical solution of the embodiment of the present invention will be described in further detail with reference to attached drawing, it is clear that described embodiment is only
It is part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those skilled in the art exist
All other embodiments obtained under the premise of not making the creative labor, belong to the scope of protection of the invention.
First embodiment
With reference to shown in Fig. 1, the first embodiment of the present invention provides a kind of intelligence and quickly starts the method for realizing recognition of face,
This method comprises the following steps：
Step 100：Obtain the path of current image.
Current image is the picture that user stops correspondence position during browsing.Such as using smart mobile phone browsing pictures, user is slided
Motion picture cartoon makes choice, and when user, which slides into certain pictures, just to stop sliding, which is exactly current image.Current image
Path is the storage location of current image.The storage location of current image is only obtained in this method, current image is examined
It surveys rather than every browsed picture is detected.
Step 200：Current image is obtained according to the path, generates the thumbnail of the picture.
Because the path is the storage location of current image, current figure can be obtained by reading the information that the position is stored
Piece.At this point, the pixel of picture is generally large, the speed of recognition of face can be influenced.The picture is scaled to the contracting of default resolution ratio
Sketch map is conducive to improve the speed of recognition of face.The thumbnail of picture is that pixel is relatively low and comprising being directed toward complete original picture herein
Hyperlink small figure.
Step 300：The thumbnail is passed to Face datection storehouse, carries out Face datection.
Face datection storehouse is the database for human face detection and tracing.The thumbnail is read in into memory by data flow
In, Face datection storehouse is called, is compared using face recognition algorithms, realizes Face datection.
The quick method for starting realization recognition of face of intelligence that first embodiment of the invention provides, by obtaining current image
Path；Current image is obtained according to the path, generates the thumbnail of the picture；The thumbnail is passed to Face datection
Storehouse carries out Face datection.Solves user in photo navigation process by the above method, face detection system starts slow, people
Face recognition speed is slow and the problem of apparent Caton phenomenon occurs in when continuous fast browsing photo, improves the comfortable of user experience
Degree.
Second embodiment
Fig. 2 is the quick method flow diagram for starting realization recognition of face of intelligence that second embodiment of the invention provides, described
The quick method for realizing recognition of face that starts of intelligence based on first embodiment of the invention, by step 100：Obtain current figure
The path of piece is specifically optimized for：The path of the browsed picture of record is obtained, the path is sorted according to browsing order,
Read path of the path as current image for coming end.
With reference to shown in Fig. 2, the intelligence, which quickly starts, realizes that the method for recognition of face includes：
Step 110：Obtain the path of the browsed picture of record.
When user slides picture, the store path and record per pictures are obtained.Tabular array record institute may be employed
The path of browsed picture.When user stops sliding picture, by thread accesses tabular array, the road of current image is obtained
Footpath, so as to obtain the picture, without detecting all browsed pictures.
Step 120：The path is sorted according to browsing order.
The paths ordering that sequencing according to user's slip picture will be recorded.May be employed according to browsing when
Between sequentially sort.In tabular array, before the path of the picture browsed after the path of the picture first browsed is stored in, it is ensured that
The picture finally browsed is located at the end of tabular array.
Step 130：Read path of the path as current image for coming end.
Because the store path of the browsed picture of user is recorded in tabular array, and the picture finally browsed is located at
The end of array, the path that reading comes end are the path of current image.
The quick method for starting realization recognition of face of intelligence that second embodiment of the invention provides, by the institute for obtaining record
The path of browsed picture, the path are sorted according to browsing order, read the path for coming end as current image
Path can quickly position picture when user browses stopping, quickly starting recognition of face, reduce waiting system software and open
The dynamic time.
3rd embodiment
Fig. 3 is the quick method flow diagram for starting realization recognition of face of intelligence that third embodiment of the invention provides, described
The quick method for realizing recognition of face that starts of intelligence based on first embodiment of the invention, by step 200：It is described according to institute
It states path and obtains current image, the thumbnail for generating the picture is specifically optimized for：Background thread is created, by the background thread
Current image is obtained according to the path, decodes the picture, the decoded picture scaling is become into default resolution ratio
Thumbnail.
With reference to shown in Fig. 3, the intelligence, which quickly starts, realizes that the method for recognition of face includes：
Step 210：Background thread is created, current image is obtained according to the path by the background thread.
A background thread is created, for picture decoding and the human face detection and recognition of picture.When user slides into a certain
During picture, background thread starts to start, and the path at tabular array end is read, so as to obtain the path of current image, according to this
Path selection current image.Picture at this time is by compressed data stream format.
Step 220：Decode the picture.
Because picture is with the form storage of data flow, it is necessary to be carried out by the background thread created to selected current image
Decoding, obtains decoded picture.
Step 230：The decoded picture scaling is become to the thumbnail of default resolution ratio.
By decoded picture compression into the thumbnail of default resolution ratio, for example, can by decoded picture compression into
Resolution ratio is the thumbnail of 320*240, this hypertonic sketch map is used for Face datection.The speed of recognition of face and the resolution ratio of picture
Size is related, i.e. the resolution ratio of picture is bigger, and the pixel of picture is also higher, and the speed of recognition of face is slower, the resolution ratio of picture
Smaller, the pixel of picture is also lower, and the speed of recognition of face is faster.Using thumbnail as the object of recognition of face, point of picture
Resolution is low, can quickly start up face detection system.
The quick method for starting realization recognition of face of intelligence that third embodiment of the invention provides, by creating backstage line
Journey obtains current image according to the path by the background thread, decodes the picture, the decoded picture is scaled
As the thumbnail of default resolution ratio.The resolution ratio for intending detection picture is reduced by the above method, can quickly start face
Identifying system improves the speed of recognition of face.
Fourth embodiment
Fig. 4 is the quick method flow diagram for starting realization recognition of face of intelligence that fourth embodiment of the invention provides, described
The quick method for realizing recognition of face that starts of intelligence based on first embodiment of the invention, by step 300：By the breviary
The incoming Face datection storehouse of figure, carries out Face datection and is specifically optimized for：The code stream that the thumbnail is obtained by lossless compression is read
Enter memory, incoming Face datection storehouse is called by local, when detecting face, return to the data of the current image to backstage
Thread draws small icon and the display of the current image according to the data.
With reference to shown in Fig. 4, the intelligence, which quickly starts, realizes that the method for recognition of face includes：
Step 311：Face recognition database is encapsulated as Face datection storehouse.
Face datection storehouse is packaged in the database for recognition of face in system, which is packaged, bag
Include upper strata background thread calling and interlayer to the calling in storehouse.
Step 312：The code stream that the thumbnail is obtained by lossless compression is read in into memory.
Because the input parameter in Face datection storehouse is bit stream data, needs obtain the thumbnail by lossless compression
The code stream arrived reads in memory, inputs Face datection storehouse after processing, carries out recognition of face.
Step 313：Thumbnail in memory is transformed into yuv space by rgb space, then the code stream of yuv space is passed through
It is local to call incoming Face datection storehouse.
Thumbnail in memory is transformed into yuv space by rgb space, then the code stream of the yuv space is passed through into local
The incoming Face datection storehouse of calling, can be by JNI (Java Native Interface, JAVA are locally called) operation by described in
Code stream is passed to Face datection storehouse.
Step 321：Judge whether to detect face.
Using Face datection algorithm, the feature vector of the thumbnail is extracted, recognition of face storehouse is called to carry out recognition of face,
If the feature vector included in thumbnail is fallen into recognition of face storehouse in the characteristic value section for characterizing face, can determine whether as detection
To face.
Step 322：When judging to detect face, the data message of current image is returned to background thread.
Step 323：When judging face is not detected, 0 is returned to, background thread, which receives to return the result, does not do any place
Reason, jumps to step 325, the Face datection of current image is terminated.
Step 324：When judging to detect face, background thread draws the small figure of the current image according to the data
It marks and shows, prompt to detect face.The drawn small icon is shown, convenient for user is reminded to detect face, Ke Yidian
It hits the small icon to be operated accordingly, makeups and other effects processing such as is carried out to the human face region.
Step 325：Terminate the detection for current image.
Intelligence that fourth embodiment of the invention provides is quick to start the method for realizing recognition of face, by by the thumbnail
The code stream obtained by lossless compression reads in memory, and incoming Face datection storehouse is called by local；When detecting face, return
The data of the current image are to background thread, according to the small icon of the data drafting current image and display.Encapsulation
With the third-party face recognition database of calling, the difficulty of system development is reduced, Face datection storehouse is directly invoked, improves people
The speed of face identification when detecting face, draws small icon user to be reminded to detect face, can carry out next step volume
It collects and operates, add human-computer interaction, the interface of system is more friendly.
5th embodiment
Fig. 5 is the quick structural representation for starting the device for realizing recognition of face of intelligence that fifth embodiment of the invention provides
Figure.The intelligence, which quickly starts, realizes that the device of recognition of face includes：Path acquisition module 500,510 and of thumbnail generation module
Face detection module 520.
Wherein, path acquisition module 500, for obtaining the path of current image；
Thumbnail generation module 510 for obtaining current image according to the path, generates the thumbnail of the picture；
Face detection module 520 for the thumbnail to be passed to Face datection storehouse, carries out Face datection.
The present apparatus further includes storehouse package module and format converting module.
Wherein, storehouse package module, for encapsulating Face datection storehouse；
Format converting module, for the thumbnail in the memory to be transformed into yuv space by rgb space.
The path acquisition module 500 further comprises that path recording unit 501, paths ordering unit 502 and path are read
Take unit 503；
The path recording unit 501, for recording the path of browsed picture；Tabular array can be utilized to record
Browsed picture path.
The paths ordering unit 502, for the path to be sorted according to browsing order；It can be according to the time of browsing
Order sorts, in tabular array, before the path of the picture browsed after the path of the picture first browsed is stored in, it is ensured that most
The picture browsed afterwards is located at the end of tabular array.
The path reading unit 503, for reading path of the path as current image for coming end.
The thumbnail generation module 510 further comprises picture acquiring unit 511, picture decoding unit 512 and picture
Unit for scaling 513；
The picture acquiring unit 511 for creating background thread, is obtained according to the path by the background thread and worked as
Preceding picture；
The picture decoding unit 512, for decoding the picture；
The picture unit for scaling 513, for the decoded picture scaling to be become to the thumbnail of default resolution ratio.
The face detection module 520 further comprises reading in unit 521, detection unit 522 and icon drawing unit
523；
The code stream that the thumbnail is obtained by lossless compression is read in memory, passes through local tune by the reading unit 521
With incoming Face datection storehouse；
The detection unit 522, for when detecting face, returning to the data of the current image to background thread；
Icon drawing unit 523 for drawing small icon and the display of the current image according to the data, prompts to use
Family detects face, and the processing of picture can be carried out by clicking on small icon.
Above device is integrated in mobile terminal, can realize that mobile terminal quickly starts the function of recognition of face so that
The operation of picture becomes more convenient in the terminals such as user's editing and processing smart mobile phone or tablet computer.
Above-mentioned intelligence, which quickly starts, to be realized the device of recognition of face to can perform the intelligence that the embodiment of the present invention provided quick
Start the method for realizing recognition of face, possess the corresponding function module of execution method and advantageous effect.
One of ordinary skill in the art will appreciate that hardware can be passed through by realizing all or part of step of above-described embodiment
It completes, relevant hardware can also be instructed to complete by program, which can be stored in computer readable storage medium
In, storage medium can include memory, disk or CD etc..
More than content is only presently preferred embodiments of the present invention, according to the invention for those of ordinary skill in the art
Thought, there will be changes, this specification content should not be construed as to the present invention in specific embodiments and applications
Limitation.
Claims (9)
1. a kind of intelligence quickly starts the method for realizing recognition of face, which is characterized in that includes the following steps：
When user slides picture, the path per pictures and record are obtained；
The path of the browsed picture of record is obtained, the path is sorted according to browsing order, reads the road for coming end
Path of the footpath as current image, wherein, the current image is the picture that user stops correspondence position during browsing；
Current image is obtained according to the path, generates the thumbnail of the picture, wherein, the thumbnail be pixel it is relatively low and
Include the small figure for the hyperlink for being directed toward complete original picture；
The code stream that the thumbnail is obtained by lossless compression is read in into memory, incoming Face datection storehouse is called by local, carries
The feature vector that the thumbnail is taken to include, if described eigenvector falls into Face datection storehouse the characteristic value section for characterizing face
It is interior, then it is judged as detecting face, when detecting face, the data of the current image is returned to background thread, according to institute
State small icon and display that data draw the current image.
2. intelligence according to claim 1 quickly starts the method for realizing recognition of face, which is characterized in that is arranged using array
Token records the path of browsed picture, and the path is sorted according to the time sequencing of browsing；
The path that the reading comes end includes as the path of current image：Read the path work for coming tabular array end
For the path of current image.
3. intelligence according to claim 1 quickly starts the method for realizing recognition of face, which is characterized in that described according to institute
It states path and obtains current image, generating the thumbnail of the picture includes, and background thread is created, by the background thread according to institute
It states path and obtains current image, decode the picture, the decoded picture scaling is become to the thumbnail of default resolution ratio.
4. intelligence according to claim 1 quickly starts the method for realizing recognition of face, which is characterized in that described by described in
The code stream that thumbnail is obtained by lossless compression further includes before reading in memory,
Encapsulate Face datection storehouse；
It is described to call incoming people by local after the code stream that the thumbnail is obtained by lossless compression reads in memory
Face detection further includes before storehouse,
Thumbnail in the memory is transformed into yuv space by rgb space.
5. a kind of intelligence quickly starts the device for realizing recognition of face, which is characterized in that including：
Path acquisition module, for when user slides picture, obtaining the path per pictures and record, the institute for obtaining record is clear
The path for the picture look at, the path are sorted according to browsing order, are read and are come the path at end as current image,
In, the current image is the picture that user stops correspondence position during browsing；
Thumbnail generation module for obtaining current image according to the path, generates the thumbnail of the picture, wherein, institute
It is that pixel is relatively low and include the small figure for the hyperlink for being directed toward complete original picture to state thumbnail；
Face detection module, including reading in unit, detection unit and icon drawing unit；
The code stream that the thumbnail is obtained by lossless compression is read in memory, is passed to by local call by the reading unit
Face datection storehouse；
The detection unit, for extracting the feature vector that the thumbnail includes, if described eigenvector falls into Face datection
In the characteristic value section that face is characterized in storehouse, then it is judged as detecting face, when detecting face, returns to the current image
Data to background thread；
Icon drawing unit, for drawing small icon and the display of the current image according to the data.
6. intelligence according to claim 5 quickly starts the device for realizing recognition of face, which is characterized in that obtains in the path
Modulus block includes path recording unit, paths ordering unit and path reading unit；
The path recording unit, for recording the path of browsed picture using tabular array；
The paths ordering unit, for the path to be sorted according to the time sequencing of browsing；
The path reading unit, for reading path of the path as current image for coming tabular array end.
7. intelligence according to claim 5 quickly starts the device for realizing recognition of face, which is characterized in that the thumbnail
Generation module includes picture acquiring unit, picture decoding unit and picture unit for scaling；
For creating background thread, current image is obtained by the background thread according to the path for the picture acquiring unit；
The picture decoding unit, for decoding the picture；
The picture unit for scaling, for the decoded picture scaling to be become to the thumbnail of default resolution ratio.
8. intelligence according to claim 5 quickly starts the device for realizing recognition of face, which is characterized in that the device also wraps
It includes：
Storehouse package module, for encapsulating Face datection storehouse；
Format converting module, for the thumbnail in the memory to be transformed into yuv space by rgb space.
9. a kind of mobile terminal, which is characterized in that realized including quick start of the intelligence described in any bar in claim 5 to 8
The device of recognition of face.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410650505.2A CN104375892B (en) | 2014-11-14 | 2014-11-14 | A kind of intelligence quickly starts the method, device and mobile terminal for realizing recognition of face |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410650505.2A CN104375892B (en) | 2014-11-14 | 2014-11-14 | A kind of intelligence quickly starts the method, device and mobile terminal for realizing recognition of face |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104375892A CN104375892A (en) | 2015-02-25 |
| CN104375892B true CN104375892B (en) | 2018-05-25 |
Family
ID=52554829
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410650505.2A Active CN104375892B (en) | 2014-11-14 | 2014-11-14 | A kind of intelligence quickly starts the method, device and mobile terminal for realizing recognition of face |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104375892B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107729736B (en) * | 2017-10-27 | 2020-01-14 | Oppo广东移动通信有限公司 | Face recognition method and related product |
| CN107729858B (en) * | 2017-10-27 | 2020-12-04 | Oppo广东移动通信有限公司 | Face recognition method and related product |
| CN108564529A (en) * | 2018-04-23 | 2018-09-21 | 广东奥园奥买家电子商务有限公司 | A kind of implementation method of the real-time makeup of lip based on android system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101470802A (en) * | 2007-12-28 | 2009-07-01 | 清华大学 | Object detection apparatus and method thereof |
| CN101706872A (en) * | 2009-11-26 | 2010-05-12 | 上海交通大学 | Universal open type face identification system |
| CN103218600A (en) * | 2013-03-29 | 2013-07-24 | 四川长虹电器股份有限公司 | Real-time face detection algorithm |
| CN104008395A (en) * | 2014-05-20 | 2014-08-27 | 中国科学技术大学 | Intelligent bad video detection method based on face retrieval |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070127787A1 (en) * | 2005-10-24 | 2007-06-07 | Castleman Kenneth R | Face recognition system and method |
-
2014
- 2014-11-14 CN CN201410650505.2A patent/CN104375892B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101470802A (en) * | 2007-12-28 | 2009-07-01 | 清华大学 | Object detection apparatus and method thereof |
| CN101706872A (en) * | 2009-11-26 | 2010-05-12 | 上海交通大学 | Universal open type face identification system |
| CN103218600A (en) * | 2013-03-29 | 2013-07-24 | 四川长虹电器股份有限公司 | Real-time face detection algorithm |
| CN104008395A (en) * | 2014-05-20 | 2014-08-27 | 中国科学技术大学 | Intelligent bad video detection method based on face retrieval |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104375892A (en) | 2015-02-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7536090B2 (en) | Machine translation method and electronic device | |
| CN113453040B (en) | Short video generation method and device, related equipment and medium | |
| US9111255B2 (en) | Methods, apparatuses and computer program products for determining shared friends of individuals | |
| CN106777007A (en) | Photograph album Classified optimization method, device and mobile terminal | |
| CN105183837B (en) | Thumbnail list view display method and system of mobile terminal | |
| WO2018072149A1 (en) | Picture processing method, device, electronic device and graphic user interface | |
| CN112200187A (en) | Target detection method, device, machine readable medium and equipment | |
| KR20150059466A (en) | Method and apparatus for recognizing object of image in electronic device | |
| KR20110028877A (en) | Method for providing user interface and display apparatus applying the same | |
| US20110246939A1 (en) | Information Processing Method and Graphical User Interface | |
| US8744178B2 (en) | Information processing apparatus, information processing method and program | |
| US20230367464A1 (en) | Multi-Application Interaction Method | |
| CN104375892B (en) | A kind of intelligence quickly starts the method, device and mobile terminal for realizing recognition of face | |
| WO2017107855A1 (en) | Picture searching method and device | |
| CN105556947A (en) | Method and apparatus for color detection to generate text color | |
| CN106485653A (en) | User terminal and the generation method of panoramic pictures dynamic thumbnail | |
| CN108989704A (en) | Image generating method and device, terminal device | |
| WO2022160965A1 (en) | Video processing method, and electronic device | |
| CN110020082A (en) | A kind of searching method and device | |
| CN114529926A (en) | Character selection method and device for curved text and terminal equipment | |
| EP4284009A1 (en) | Method for acquiring image, and electronic device | |
| US7706577B1 (en) | Exporting extracted faces | |
| US20240046504A1 (en) | Image processing method and electronic device | |
| CN117499526B (en) | Shooting method, electronic device, chip system and computer readable storage medium | |
| JP2005057360A (en) | Picture photographing apparatus and program |
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 | ||
| 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. |