CN107958220A - A kind of face database compression processing method and its intelligent apparatus based on recognition of face - Google Patents
A kind of face database compression processing method and its intelligent apparatus based on recognition of face Download PDFInfo
- Publication number
- CN107958220A CN107958220A CN201711282530.XA CN201711282530A CN107958220A CN 107958220 A CN107958220 A CN 107958220A CN 201711282530 A CN201711282530 A CN 201711282530A CN 107958220 A CN107958220 A CN 107958220A
- Authority
- CN
- China
- Prior art keywords
- image information
- face image
- human face
- candid photograph
- face
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Television Signal Processing For Recording (AREA)
- Image Processing (AREA)
Abstract
This application discloses a kind of face database compression processing method and its intelligent apparatus based on recognition of face, including:Obtain the candid photograph human face image information in video flowing;Face database is identified according to the candid photograph human face image information, obtains capturing the matched contrast human face image information of human face image information with described in the face database;The picture quality of the candid photograph human face image information and the contrast human face image information is contrasted, and in the case where the candid photograph human face image information picture quality is higher than the contrast human face image information picture quality, the candid photograph human face image information is replaced into the contrast human face image information and completes compression.By the way of contrast images in the image replacement face database higher by picture quality, reach reduction amount of storage, compressed the purpose of face database, and then solved in correlation technique since candid photograph face picture is excessive, cause the technical problem that amount of storage is huge.
Description
Technical field
This application involves field of face identification, is handled in particular to a kind of face database compression based on recognition of face
Method and its intelligent apparatus.
Background technology
Video monitoring is increasing in the effect that modern safety-security area plays, and application range is more and more wider, such as in recent years in state
The safe city plan that family widelys popularize, relies on video monitoring and huge effect has been played in public safety-security area.
But the video monitoring system based on recognition of face of most of camera manufacturer and software vendor instantly, it is led
Storage is carried out into system when then needs after if using Face detection and tracking technology, facial image is detected
Capture, and face database is retrieved.Have a disadvantage in that, if same person appears in a camera more than once, meeting
Cause same person to capture the multiple face pictures of storage within the regular hour, cause amount of storage huge, so being badly in need of a kind of base
In the face database compression processing method and its intelligent apparatus of recognition of face, to solve in correlation technique due to capturing face picture mistake
It is more, cause the technical problem that amount of storage is huge.
The content of the invention
The main purpose of the application is to provide a kind of face database compression processing method and its intelligence based on recognition of face
Device, it is excessive due to capturing face picture in correlation technique to solve, cause the technical problem that amount of storage is huge.
This application provides a kind of face database compression processing method based on recognition of face, including:
Obtain the candid photograph human face image information in video flowing;
According to it is described candid photograph human face image information be identified in face database, obtain in the face database with the candid photograph people
The contrast human face image information of face image information matches;
The picture quality of the candid photograph human face image information and the contrast human face image information is contrasted;And
If the candid photograph human face image information picture quality, will higher than the contrast human face image information picture quality
The candid photograph human face image information replaces the contrast human face image information.
Further, the candid photograph human face image information obtained in video flowing, this method further include:
The plurality of pictures captured is decoded to the video flowing;
The time anchor point scope of the picture is marked;
Recognition of face is carried out to the picture described in multiple, the picture of the extraction with face characteristic is as the candid photograph
Human face image information.
Further, it is described that face database is identified according to the candid photograph human face image information, obtain the face database
In with the candid photograph matched contrast human face image information of human face image information, this method further includes:
The time shaft of the face database is divided into multiple constant time ranges, wherein, assignment is carried out to the constant time range duration;
The corresponding constant time range conduct on the face database time shaft is obtained according to the time anchor point scope of mark
Target period section;
The candid photograph human face image information is identified with the face database in the target period section, is obtained described
The matched contrast human face image information of human face image information is captured described in target period Duan Shangyu.
Further, it is described to contrast human face image information figure higher than described in the candid photograph human face image information picture quality
In the case of image quality amount, the candid photograph human face image information is replaced into the contrast human face image information and completes compression, the party
Method further includes:
The contrast human face image information in the face database is replaced with the candid photograph facial image to be stored;
The time anchor point scope of the candid photograph facial image is stored.
Further, the video flowing in real time is obtained by video monitoring system.
Further, the recognition of face is the bio-identification of face.
Present invention also provides a kind of intelligent apparatus, including:
Acquisition module, for obtaining the candid photograph human face image information in video flowing;
Identification module, for face database to be identified according to the candid photograph human face image information, obtains the face database
In with it is described candid photograph the matched contrast human face image information of human face image information;
Contrast module, for it is described candid photograph human face image information with it is described contrast human face image information picture quality into
Row contrast;
Replacement module, for contrasting human face image information figure higher than described in the candid photograph human face image information picture quality
In the case of image quality amount, the candid photograph human face image information is replaced into the contrast human face image information and completes compression.
Further, decoder module, for being decoded the plurality of pictures captured to the video flowing;
Mark module, for the time anchor point scope of the picture to be marked;
The identification module, is additionally operable to carry out the picture described in multiple recognition of face detection, extraction has face characteristic
The picture as the candid photograph human face image information.
Further, module is split, for the time shaft of the face database to be divided into multiple constant time ranges, wherein, to institute
The constant time range duration stated carries out assignment;
Acquisition module, for obtaining corresponding institute on the face database time shaft according to the time anchor point scope of mark
Constant time range is stated as target period section;
The identification module, is additionally operable to the candid photograph human face image information and the face in the target period section
Storehouse is identified, and obtains capturing the matched contrast facial image letter of human face image information described in the target period Duan Shangyu
Breath.
Further, the memory module, for the contrast human face image information in the face database to be replaced with
The candid photograph facial image is stored;It is additionally operable to be stored the time anchor point scope of the candid photograph facial image.
In the embodiment of the present application, using the side that contrast images in face database are replaced by the higher image of picture quality
Formula, has reached reduction amount of storage, compresses the purpose of face database, it is achieved thereby that when capturing multiple face pictures, extraction image quality is most
The technique effect that high picture is stored, and then solve in correlation technique since candid photograph face picture is excessive, cause to store
Measure huge technical problem.
Brief description of the drawings
The attached drawing for forming the part of the application is used for providing further understanding of the present application so that the application's is other
Feature, objects and advantages become more apparent upon.The illustrative examples attached drawing and its explanation of the application is used to explain the application, not
Form the improper restriction to the application.In the accompanying drawings:
Fig. 1 is the embodiment schematic diagram of the application compression processing method work flow diagram;And
Fig. 2 is the schematic diagram of the application intelligent apparatus Organization Chart.
Embodiment
In order to make those skilled in the art more fully understand application scheme, below in conjunction with the embodiment of the present application
Attached drawing, is clearly and completely described the technical solution in the embodiment of the present application, it is clear that described embodiment is only
The embodiment of the application part, instead of all the embodiments.Based on the embodiment in the application, ordinary skill people
Member's all other embodiments obtained without making creative work, should all belong to the model of the application protection
Enclose.
It should be noted that term " first " in the description and claims of this application and above-mentioned attached drawing, "
Two " etc. be for distinguishing similar object, without for describing specific order or precedence.It should be appreciated that so use
Data can exchange in the appropriate case, so as to embodiments herein described herein.In addition, term " comprising " and " tool
Have " and their any deformation, it is intended that cover it is non-exclusive include, for example, containing series of steps or unit
Process, method, system, product or equipment are not necessarily limited to those steps clearly listed or unit, but may include without clear
It is listing to Chu or for the intrinsic other steps of these processes, method, product or equipment or unit.
It should be noted that in the case where there is no conflict, the feature in embodiment and embodiment in the application can phase
Mutually combination.Describe the application in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
As shown in Figure 1, this method includes steps S101 to step S104:
Step S101, obtains the candid photograph human face image information in video flowing;
Step S102, according to it is described candid photograph human face image information be identified in face database, obtain in the face database with
The candid photograph matched contrast human face image information of human face image information;
Step S103, carries out pair the picture quality of the candid photograph human face image information and the contrast human face image information
Than, and
Step S104, if the candid photograph human face image information picture quality is higher than the contrast human face image information image
Quality, then replace the contrast human face image information by the candid photograph human face image information.
First, the candid photograph human face image information in the video flowing of acquisition, the image information knowledge mainly to face here
Not, it can be according to specific needs adjusted in practical application, capture image object that other needs monitor and (for example arm, match somebody with somebody
Decorations etc.).Then, according to it is described candid photograph human face image information the face database is identified, obtain in the face database with
It is described candid photograph the matched contrast human face image information of human face image information, specifically, face database herein be before by time shaft
The face picture storehouse (can also be the picture library of other main bodys) being together in series, retrieval pair is carried out according to human face image information is captured
Than identifying occurrence (i.e. described contrast human face image information).To the candid photograph human face image information and the contrast face
The picture quality of image information is contrasted, contrast at this time, and contrast is picture quality.Select the picture of a better quality
Carry out follow-up storage work.If the candid photograph human face image information quality is higher, then can be carried out replacing.Cross herein
Cheng Zhong, it is seen that face database eventually only keeps the quantity in original face database for the facial image of same people.It will not produce
The problem of raw same person is continuously increased its facial image, realizes the function of compression face database.Because the people in correlation technique
Face storehouse can constantly increase according to the candid photograph human face image information that newly obtains, in the present embodiment, data using picture as
Carrier.This method extend also to signal, data compression field in, the candid photograph human face image information herein, state pair
Only picture is also not necessarily limited to than human face image information, it is also possible to data, the form of signal.
In another alternative embodiment, the candid photograph human face image information obtained in video flowing, including:
Step a:The plurality of pictures captured is decoded to the video flowing;
Step b:The time anchor point scope of the picture is marked;
Step c:Recognition of face detection, the picture conduct of the extraction with face characteristic are carried out to the picture described in multiple
The candid photograph human face image information.
Secondly, except in above-described embodiment for image acquisition in itself in addition to, will also be to it in the video flowing
Time anchor point scope is marked, the step of for may subsequently use in.Specifically, the video flowing is decoded to obtain
Picture described in multiple, the picture herein include the picture for having face characteristic, also include the figure of no face characteristic
Piece.(picture only having powerful connections) while the picture is obtained, to it in the video flowing during specific on time shaft
Intermediate node, i.e., described time anchor point scope are marked;
After carrying out recognition of face detection to the pictorial information, using the picture with face characteristic as above-mentioned implementation
The candid photograph human face image information in example, carries out subsequent step.
It is described that face database is identified according to the candid photograph human face image information in another alternative embodiment, obtain
In the face database with it is described candid photograph the matched contrast human face image information of human face image information, including:
Step 1:The time shaft of the face database is divided into multiple constant time ranges, wherein, progress during to the constant time range
Row assignment;
Step 2:The corresponding cycle on the face database time shaft is obtained according to the time anchor point scope of mark
Duan Zuowei target period sections;
Step 3:The candid photograph human face image information is identified with the face database in the target period section,
Obtain capturing the matched contrast human face image information of human face image information described in the target period Duan Shangyu.
Again, in addition to the step in above-described embodiment, same people only has in the whole video flowing in order to prevent
One pictures (being also likely to be a data), carry out period divisions, specifically, by the people by the time shaft of whole video flowing
The time shaft in face storehouse is divided into multiple constant time ranges, wherein, assignment (assignment is assumed to be Q) is carried out to the constant time range duration;Root
Constant time range corresponding on the whole time shaft of video flowing is obtained according to the time anchor point scope marked in above-mentioned steps, should
Constant time range is the target period section;In this embodiment, it is clear that the time shaft of the face database should be with the video flowing
Time shaft correspond.Number of the people under different cycles so will be periodically preserved in whole video flowing
According to data (i.e. picture or data message).
It is described to be higher than the contrast face in the candid photograph human face image information picture quality in another alternative embodiment
In the case of image information picture quality, the candid photograph human face image information is replaced into the contrast human face image information and is completed
Compression,
The contrast human face image information in the face database is replaced with the candid photograph facial image to be stored;
The time anchor point scope of the candid photograph facial image is stored.
Except above-mentioned compression is handled, it should also record its time anchor point scope and be used for counter look into and reference.
In another alternative embodiment, including:
The video flowing in real time is obtained by video monitoring system in correlation technique, can also be by other means
Carry out acquisition information flow.
In another alternative embodiment, including:
The recognition of face is the biological identification technology of face.It is of course also possible to use other modes carry out face
Identification.
Specific embodiment is as follows:
The video flowing in real time is obtained by the video monitoring system, decoding is carried out to the video flowing and obtains multiple
Picture, carries out picture multiple described the mark of time anchor point scope one by one.Face knowledge is carried out to multiple the above-mentioned picture
Not, the step of picture with face characteristic is retained as to the candid photograph human face image information, carries out next step.It is right
The step of time anchor point scope is marked can also be placed on after recognition of face step, reduce treating capacity, just for
The picture of face characteristic is marked, and the picture of no face characteristic is then abandoned handling.The picture for possessing the face characteristic turns
Turn to the candid photograph human face image information;The candid photograph human face image information can not only exist in the form of picture, also may be used
To be related corresponding data message.
According to the candid photograph human face image information by the retrieval to face database, the data pattern in face database should use
Data model that is corresponding with the candid photograph human face image information and can contrasting.Find data (the i.e. institute of the same people of Corresponding matching
The contrast human face image information stated), if the quality of data higher captured in human face image information is (specifically, i.e. described
Picture quality higher), then, in face database it is corresponding it is described contrast human face image information be replaced renewal.In addition, such as
The picture quality higher of human face image information is contrasted described in fruit, then abandons replacing renewal, still retains original contrast people
Face image information.
Based on above-mentioned basic skills, the figure for updating a needs is only replaced in a video flowing in order to prevent
Piece or related data, omit important picture or data.So the face database is divided into constant time range, in each constant time range
Same main body (picture or data message of same face) can be stored down.Utilize the above-mentioned time to the picture
The mark of anchor point scope, the constant time range of the corresponding video flowing are contrasted, replaced, preserved.
It can be seen from the above description that the present invention realizes following technique effect:
In the embodiment of the present application, using the side that contrast images in face database are replaced by the higher image of picture quality
Formula, has reached reduction amount of storage, compresses the purpose of face database, it is achieved thereby that when capturing multiple face pictures, extraction image quality is most
The technique effect that high picture is stored, and then solve in correlation technique since candid photograph face picture is excessive, cause to store
Measure huge technical problem.
In addition, by by the carry out constant time range segmentation of the face database, it is therefore prevented that same target in the video flowing only
A picture or data are stored, omit the situation of important information.
It should be noted that step shown in the flowchart of the accompanying drawings can be in such as a group of computer-executable instructions
Performed in computer system, although also, show logical order in flow charts, in some cases, can be with not
The order being same as herein performs shown or described step.
According to embodiments of the present invention, a kind of intelligent apparatus for being used to implement above-mentioned compression method is additionally provided, such as Fig. 2 institutes
Show, which includes:
Acquisition module 101, for obtaining the candid photograph human face image information in video flowing;
Identification module 102, for face database to be identified according to the candid photograph human face image information, obtains the face
In storehouse the matched contrast human face image information of human face image information is captured with described;
Contrast module 103, for the image matter to the candid photograph human face image information and the contrast human face image information
Amount is contrasted;
Replacement module 104, for believing in the candid photograph human face image information picture quality higher than the contrast facial image
In the case of ceasing picture quality, the candid photograph human face image information is replaced into the contrast human face image information and completes compression.
Further, decoder module, for being decoded the plurality of pictures captured to the video flowing;
Mark module, for the time anchor point scope of the picture to be marked;
The identification module 102, is additionally operable to carry out the pictorial information described in multiple recognition of face detection, extraction has people
The picture of face feature is as the candid photograph human face image information.
Further, module is split, for the time shaft of the face database to be divided into multiple constant time ranges, wherein, to institute
The constant time range duration stated carries out assignment;
The acquisition module 101, for obtaining the face database time shaft according to the time anchor point scope of mark
The corresponding constant time range is as target period section;
The identification module, is additionally operable to the candid photograph human face image information and the face in the target period section
Storehouse is identified, and obtains capturing the matched contrast facial image letter of human face image information described in the target period Duan Shangyu
Breath.
Further, the memory module, for the contrast human face image information in the face database to be replaced with
The candid photograph facial image is stored;It is additionally operable to be stored the time anchor point scope of the candid photograph facial image.
Obviously, those skilled in the art should be understood that above-mentioned each module of the invention or each step can be with general
Computing device realize that they can be concentrated on single computing device, or be distributed in multiple computing devices and formed
Network on, alternatively, they can be realized with the program code that computing device can perform, it is thus possible to which they are stored
Performed in the storage device by computing device, either they are fabricated to respectively each integrated circuit modules or by they
In multiple modules or step be fabricated to single integrated circuit module to realize.In this way, the present invention be not restricted to it is any specific
Hardware and software combines.
The present invention a kind of candid photograph face database compression method and system based on recognition of face, utilize recognition of face bio-identification
Technology, matching retrieval is carried out to the history face captured in a period of time, will face figure twice if matching history face
As boil down to one opens image (with low-quality one of the substitution of picture quality high one), while record the time anchor of this candid photograph
Point range data, have access to corresponding storage video flowing data are counter and looked into for passage time anchor point scope.
The foregoing is merely the preferred embodiment of the application, the application is not limited to, for the skill of this area
For art personnel, the application can have various modifications and variations.It is all within spirit herein and principle, made any repair
Change, equivalent substitution, improvement etc., should be included within the protection domain of the application.
Claims (10)
- A kind of 1. face database compression processing method based on recognition of face, it is characterised in that including:Obtain the candid photograph human face image information in video flowing;It is identified according to the candid photograph human face image information in face database, obtains capturing face figure with described in the face database As the contrast human face image information of information matches;The picture quality of the candid photograph human face image information and the contrast human face image information is contrasted;AndIf the candid photograph human face image information picture quality is higher than the contrast human face image information picture quality, by described in Candid photograph human face image information replace the contrast human face image information.
- 2. the face database compression processing method according to claim 1 based on recognition of face, it is characterised in that the acquisition Candid photograph human face image information in video flowing, this method further include:The plurality of pictures captured is decoded to the video flowing;The time anchor point scope of the picture is marked;Recognition of face is carried out to the picture described in multiple, the picture of the extraction with face characteristic is as the candid photograph face Image information.
- 3. the face database compression processing method according to claim 2 based on recognition of face, it is characterised in that the basis Face database is identified in the candid photograph human face image information, obtains capturing human face image information with described in the face database The contrast human face image information matched somebody with somebody, this method further include:The time shaft of the face database is divided into multiple constant time ranges, wherein, the duration of the constant time range is preset;According to the corresponding constant time range on the time anchor point scope of the mark acquisition face database time shaft as target Constant time range;The candid photograph human face image information is identified with the face database in the target period section, obtains the target On constant time range the matched contrast human face image information of human face image information is captured with described.
- 4. the face database compression processing method according to claim 3 based on recognition of face, it is characterised in that described in institute State in the case of capturing human face image information picture quality higher than the contrast human face image information picture quality, described is grabbed Clap human face image information and replace the contrast human face image information completion compression, this method further includes:The contrast human face image information in the face database is replaced with the candid photograph facial image to be stored;The time anchor point scope of the candid photograph human face image information is stored.
- 5. the face database compression processing method according to claim 1 based on recognition of face, it is characterised in that pass through video Monitoring system obtains the video flowing in real time.
- 6. the face database compression processing method according to claim 2 based on recognition of face, it is characterised in that the face It is identified as the bio-identification of face.
- A kind of 7. intelligent apparatus, it is characterised in that including:Acquisition module, for obtaining the candid photograph human face image information in video flowing;Identification module, for according to it is described candid photograph human face image information face database is identified, obtain in the face database with The candid photograph matched contrast human face image information of human face image information;Contrast module, for being carried out pair to the picture quality of the candid photograph human face image information and the contrast human face image information Than;Replacement module, for contrasting human face image information image matter higher than described in the candid photograph human face image information picture quality In the case of amount, the candid photograph human face image information is replaced into the contrast human face image information and completes compression.
- 8. intelligent apparatus according to claim 7, it is characterised in thatDecoder module, for being decoded the plurality of pictures captured to the video flowing;Mark module, for the time anchor point scope of the picture to be marked;The identification module, is additionally operable to carry out the picture described in multiple recognition of face detection, institute of the extraction with face characteristic Picture is stated as the candid photograph human face image information.
- 9. intelligent apparatus according to claim 7, it is characterised in thatSplit module, for the time shaft of the face database to be divided into multiple constant time ranges, wherein, to the constant time range duration Carry out assignment;The acquisition module, for obtaining corresponding institute on the face database time shaft according to the time anchor point scope of mark Constant time range is stated as target period section;The identification module, be additionally operable to by the face database in candid photograph human face image information and the target period section into Row identification, obtains capturing the matched contrast human face image information of human face image information described in the target period Duan Shangyu.
- 10. intelligent apparatus according to claim 9, it is characterised in that;Memory module, for by the contrast human face image information in the face database replace with it is described candid photograph facial image into Row storage;It is additionally operable to be stored the time anchor point scope of the candid photograph facial image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711282530.XA CN107958220B (en) | 2017-12-06 | 2017-12-06 | Face library compression processing method based on face recognition and intelligent device thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711282530.XA CN107958220B (en) | 2017-12-06 | 2017-12-06 | Face library compression processing method based on face recognition and intelligent device thereof |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107958220A true CN107958220A (en) | 2018-04-24 |
CN107958220B CN107958220B (en) | 2021-03-12 |
Family
ID=61958230
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711282530.XA Active CN107958220B (en) | 2017-12-06 | 2017-12-06 | Face library compression processing method based on face recognition and intelligent device thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107958220B (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109903412A (en) * | 2019-02-01 | 2019-06-18 | 北京清帆科技有限公司 | A kind of intelligent check class attendance system based on face recognition technology |
CN110196924A (en) * | 2019-05-31 | 2019-09-03 | 银河水滴科技(北京)有限公司 | The building in characteristic information library, the method for tracing of target object and device |
CN110719398A (en) * | 2018-07-12 | 2020-01-21 | 浙江宇视科技有限公司 | Face snapshot object determination method and device |
CN111161206A (en) * | 2018-11-07 | 2020-05-15 | 杭州海康威视数字技术股份有限公司 | Image capturing method, monitoring camera and monitoring system |
CN111831841A (en) * | 2019-04-19 | 2020-10-27 | 杭州海康威视数字技术股份有限公司 | Information retrieval method and device, electronic equipment and storage medium |
CN112560772A (en) * | 2020-12-25 | 2021-03-26 | 北京百度网讯科技有限公司 | Face recognition method, device, equipment and storage medium |
CN112908031A (en) * | 2019-11-19 | 2021-06-04 | 丰田自动车株式会社 | Image processing system, processing device, relay device, and recording medium |
CN113283305A (en) * | 2021-04-29 | 2021-08-20 | 百度在线网络技术(北京)有限公司 | Face recognition method and device, electronic equipment and computer readable storage medium |
US20230112822A1 (en) * | 2021-10-08 | 2023-04-13 | Realtek Semiconductor Corporation | Character recognition method, character recognition device and non-transitory computer readable medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103942525A (en) * | 2013-12-27 | 2014-07-23 | 高新兴科技集团股份有限公司 | Real-time face optimal selection method based on video sequence |
JP2015011555A (en) * | 2013-06-28 | 2015-01-19 | キヤノン株式会社 | Image processing apparatus, image processing method, and program |
CN105389566A (en) * | 2015-11-13 | 2016-03-09 | 广东欧珀移动通信有限公司 | Fingerprint identification method, fingerprint template updating method, fingerprint template updating device and mobile terminal |
CN105938552A (en) * | 2016-06-29 | 2016-09-14 | 北京旷视科技有限公司 | Face recognition method capable of realizing base image automatic update and face recognition device |
CN106548148A (en) * | 2016-10-26 | 2017-03-29 | 北京意泰物联软件科技有限公司 | The recognition methodss of unknown face and system in video |
CN107358146A (en) * | 2017-05-22 | 2017-11-17 | 深圳云天励飞技术有限公司 | Method for processing video frequency, device and storage medium |
-
2017
- 2017-12-06 CN CN201711282530.XA patent/CN107958220B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2015011555A (en) * | 2013-06-28 | 2015-01-19 | キヤノン株式会社 | Image processing apparatus, image processing method, and program |
CN103942525A (en) * | 2013-12-27 | 2014-07-23 | 高新兴科技集团股份有限公司 | Real-time face optimal selection method based on video sequence |
CN105389566A (en) * | 2015-11-13 | 2016-03-09 | 广东欧珀移动通信有限公司 | Fingerprint identification method, fingerprint template updating method, fingerprint template updating device and mobile terminal |
CN105938552A (en) * | 2016-06-29 | 2016-09-14 | 北京旷视科技有限公司 | Face recognition method capable of realizing base image automatic update and face recognition device |
CN106548148A (en) * | 2016-10-26 | 2017-03-29 | 北京意泰物联软件科技有限公司 | The recognition methodss of unknown face and system in video |
CN107358146A (en) * | 2017-05-22 | 2017-11-17 | 深圳云天励飞技术有限公司 | Method for processing video frequency, device and storage medium |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110719398B (en) * | 2018-07-12 | 2021-07-20 | 浙江宇视科技有限公司 | Face snapshot object determination method and device |
CN110719398A (en) * | 2018-07-12 | 2020-01-21 | 浙江宇视科技有限公司 | Face snapshot object determination method and device |
CN111161206A (en) * | 2018-11-07 | 2020-05-15 | 杭州海康威视数字技术股份有限公司 | Image capturing method, monitoring camera and monitoring system |
CN109903412A (en) * | 2019-02-01 | 2019-06-18 | 北京清帆科技有限公司 | A kind of intelligent check class attendance system based on face recognition technology |
CN111831841A (en) * | 2019-04-19 | 2020-10-27 | 杭州海康威视数字技术股份有限公司 | Information retrieval method and device, electronic equipment and storage medium |
CN111831841B (en) * | 2019-04-19 | 2023-09-05 | 杭州海康威视数字技术股份有限公司 | Information retrieval method, device, electronic equipment and storage medium |
CN110196924A (en) * | 2019-05-31 | 2019-09-03 | 银河水滴科技(北京)有限公司 | The building in characteristic information library, the method for tracing of target object and device |
CN112908031A (en) * | 2019-11-19 | 2021-06-04 | 丰田自动车株式会社 | Image processing system, processing device, relay device, and recording medium |
CN112560772A (en) * | 2020-12-25 | 2021-03-26 | 北京百度网讯科技有限公司 | Face recognition method, device, equipment and storage medium |
CN112560772B (en) * | 2020-12-25 | 2024-05-14 | 北京百度网讯科技有限公司 | Face recognition method, device, equipment and storage medium |
CN113283305A (en) * | 2021-04-29 | 2021-08-20 | 百度在线网络技术(北京)有限公司 | Face recognition method and device, electronic equipment and computer readable storage medium |
CN113283305B (en) * | 2021-04-29 | 2024-03-26 | 百度在线网络技术(北京)有限公司 | Face recognition method, device, electronic equipment and computer readable storage medium |
US20230112822A1 (en) * | 2021-10-08 | 2023-04-13 | Realtek Semiconductor Corporation | Character recognition method, character recognition device and non-transitory computer readable medium |
US11922710B2 (en) * | 2021-10-08 | 2024-03-05 | Realtek Semiconductor Corporation | Character recognition method, character recognition device and non-transitory computer readable medium |
Also Published As
Publication number | Publication date |
---|---|
CN107958220B (en) | 2021-03-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107958220A (en) | A kind of face database compression processing method and its intelligent apparatus based on recognition of face | |
CN104794462B (en) | A kind of character image processing method and processing device | |
CN110297943B (en) | Label adding method and device, electronic equipment and storage medium | |
CN110381369A (en) | Determination method, apparatus, equipment and the storage medium of recommendation information implantation position | |
JP7261296B2 (en) | Target object recognition system, method, apparatus, electronic device, and recording medium | |
WO2020073709A1 (en) | Multi-camera multi-face video continuous acquisition device and method | |
CN110427859A (en) | A kind of method for detecting human face, device, electronic equipment and storage medium | |
Wang et al. | First-person daily activity recognition with manipulated object proposals and non-linear feature fusion | |
CN104915351A (en) | Picture sorting method and terminal | |
CN108305223B (en) | Image background blurring processing method and device | |
CN106295618A (en) | A kind of personal identification method and device based on video image | |
CN108921204A (en) | Electronic device, picture sample set creation method and computer readable storage medium | |
CN103428537A (en) | Video processing method and video processing device | |
CN106056138A (en) | Picture processing device and method | |
CN108563651A (en) | A kind of Target Searching Method, device and the equipment of more videos | |
CN113011403A (en) | Gesture recognition method, system, medium, and device | |
CN106165017A (en) | Allow to carry out the instant scene Recognition of scene associated picture amendment before image record or display | |
TWI602434B (en) | Photographing system for long-distance running event and operation method thereof | |
CN109558798A (en) | One kind being based on the matched face identification method of convolution characteristic pattern and system | |
CN104104860B (en) | Object images detection device and its control method and control program, recording medium | |
CN110019863B (en) | Object searching method and device, terminal equipment and storage medium | |
CN110245648A (en) | The alert system of wisdom list based on Identification of Images | |
CN110166836A (en) | A kind of TV program switching method, device, readable storage medium storing program for executing and terminal device | |
CN106714099A (en) | Photograph information processing and scenic spot identification method, client and server | |
CN109784218A (en) | A kind of archiving 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 |