CN106326815A - Human face image recognition method - Google Patents
Human face image recognition method Download PDFInfo
- Publication number
- CN106326815A CN106326815A CN201510381767.8A CN201510381767A CN106326815A CN 106326815 A CN106326815 A CN 106326815A CN 201510381767 A CN201510381767 A CN 201510381767A CN 106326815 A CN106326815 A CN 106326815A
- Authority
- CN
- China
- Prior art keywords
- facial image
- training sample
- user
- intelligent terminal
- photograph album
- 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
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000012549 training Methods 0.000 claims abstract description 103
- 238000004891 communication Methods 0.000 claims abstract description 27
- 230000001815 facial effect Effects 0.000 claims description 92
- 230000013011 mating Effects 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 238000012790 confirmation Methods 0.000 abstract 1
- 230000006855 networking Effects 0.000 abstract 1
- 230000008878 coupling Effects 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 4
- 238000005859 coupling reaction Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000003760 hair shine Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Abstract
The invention discloses a human face image recognition method, which belongs to the technical field of image recognition. The method comprises steps: S1, a communication list and a user album are adopted for training and a first training sample is generated, and/or a friend list in a user account in a social networking site and a friend album are adopted for training, and a second training sample is generated; S2, the first training sample and/or the second training sample are combined to form an initial training sample; and S3, a human face image in the initial training sample is adopted, recognition confirmation is carried out according to the initial training sample final recognition data are perfected and formed, and an intelligent terminal executes human face image recognition operation according to the recognition data. The above technical scheme has the beneficial effects that the intelligent terminal can automatically recognize and train the human face recognition data according to the relational network of the user, the tedious operation of manually inputting a large amount of picture samples for human face recognition by the user can be avoided, and the use experience of the user is enhanced.
Description
Technical field
The present invention relates to image identification technical field, particularly relate to a kind of facial image recognition method.
Background technology
Recognition of face, as a kind of emerging identification technology, is increasingly being applied in intelligent terminal.Example
As user can be by distinguishing that face recalls some associated datas and includes name, contact method, social network
The user account etc. of network, user again may be by distinguishing that the mode of face realizes encryption and decryption operation etc..
But, existing face recognition technology, it usually needs needed for user is manually entered identification in advance
Great amount of images sample, the mode of input can be that batch imports, or production collection in advance etc..But nothing
Which kind of is manually entered mode to opinion, and the whole operation all making user is the most loaded down with trivial details, greatly reduces use
The experience of person.
Summary of the invention
According to problems of the prior art, now provide the technical scheme of a kind of facial image recognition method,
Aim to solve the problem that user needs to be manually entered a large amount of image pattern for recognition of face present in prior art
Data, and the relation of image and name is set one by one, thus cause operating the most loaded down with trivial details defect；
Technique scheme specifically includes:
A kind of facial image recognition method, it is adaptable to intelligent terminal；Wherein, including a pre-training step,
To obtain corresponding training sample；
Described pre-training step specifically includes:
Step S1, described intelligent terminal remotely obtains the communication directory in the mobile terminal being stored in user
And user's photograph album, use the facial image in described user's photograph album and the individual number of people in described communication directory
As mating, corresponding with described human head picture in described communication directory to set up described facial image
The first training sample that individual's name is associated；And/or
It is corresponding that described intelligent terminal remotely searches and obtain the default user account being associated with social networks
Buddy list and good friend's photograph album, and according to the facial image in described good friend's photograph album and described buddy list
In individual human head picture mate, to set up the described individual in described facial image and described buddy list
The second training sample that the corresponding individual name of head portrait is associated；
Step S2, preliminary to form one in conjunction with described first training sample and/or described second training sample
Training sample；
Step S3, uses and is included in the described facial image in described initial training sample, and according to described
Initial training sample is identified confirming, to improve and to form final identification data；
After forming described identification data, described intelligent terminal gather need identify facial image, and according to
Described identification data are identified, and export recognition result.
Preferably, this facial image recognition method, wherein, in described step S1, form described first
The step of training sample specifically includes:
Step S11a, remotely obtains the described facial image in described user's photograph album；
Step S12a, remotely obtains described communication directory；
Step S13a, uses described facial image to mate in described communication directory, described to find
The individual human head picture matched in communication directory；
Step S14a, by relevant for individual name corresponding to the individual human head picture matched for described facial image
Connection；
Step S15a, circulation performs described step S11a-S14a, with according to the institute in described user's photograph album
The training of described facial image is had to form described first training sample.
Preferably, this facial image recognition method, wherein, in described step S1, form described second
The step of training sample specifically includes:
Step S11b, by being associated with the described user account of at least one social network sites, remotely obtains institute
State the described facial image in described good friend's photograph album that user account is associated；
Step S12b, by being associated with the described user account of at least one social network sites, remotely obtains institute
State the buddy list that user account is associated；
Step S13b, uses described facial image to mate in described buddy list, described to find
The individual human head picture matched in buddy list；
Step S14b, described facial image is corresponding with the individual human head picture matched in described buddy list
Individual's name is associated；
Step S15b, circulation performs described step S11b-14b, with according to owning in described good friend's photograph album
The training of described facial image forms described second training sample.
Preferably, this facial image recognition method, wherein, in described step S1, described intelligent terminal
Access described mobile terminal by radio connection, and obtain corresponding described in described mobile terminal
Communication directory and described user's photograph album.
Preferably, this facial image recognition method, wherein, described step S3 specifically includes:
Step S31, collection in worksite is included in the facial image in described initial training sample；
Step S32, is identified confirming to described facial image according to described initial training sample:
If None-identified, then update described initial training sample according to described facial image；It is subsequently diverted to step
Rapid S33；
If being capable of identify that, then directly to step S33；
Step S33, circulation performs described step S31-32, to improve institute according to facial image multiple described
State initial training sample；
Step S34, will be integrally formed described identification data through perfect described initial training sample, and
It is stored in described intelligent terminal.
Preferably, this facial image recognition method, wherein, in described step S32, described intelligent terminal
Confirm for the user that the described facial image of collection in worksite is corresponding by sending prompt tone.
Preferably, this facial image recognition method, wherein, described intelligent terminal is for having robot outward appearance
Intelligent terminal.
Technique scheme provides the benefit that: provide a kind of facial image recognition method so that intelligence is eventually
End can identify according to the relational network of user and train facial recognition data automatically, thus avoids using
Person needs to be manually entered the troublesome operation of the picture sample needed for a large amount of recognition of face, promotes making of user
With experience.
Accompanying drawing explanation
Fig. 1-4 is in the preferred embodiment of the present invention, the flow process signal of a kind of facial image recognition method
Figure.
Detailed description of the invention
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out
Clearly and completely describe, it is clear that described embodiment is only a part of embodiment of the present invention, and
It is not all, of embodiment.Based on the embodiment in the present invention, those of ordinary skill in the art are not making
The every other embodiment obtained on the premise of going out creative work, broadly falls into the scope of protection of the invention.
It should be noted that in the case of not conflicting, the embodiment in the present invention and the spy in embodiment
Levy and can be mutually combined.
The invention will be further described with specific embodiment below in conjunction with the accompanying drawings, but not as the present invention's
Limit.
In the preferred embodiment of the present invention, based on the above-mentioned problems in the prior art, now provide one
Plant the technical scheme of facial image recognition method, it is adaptable to intelligent terminal.
In the preferred embodiment of the present invention, above-mentioned facial image recognition method includes a pre-training step
Suddenly.So-called pre-training step, refers to before intelligent terminal is put into the recognition of face operation of reality by reality,
The process of the identification data needed for foundation identification.In other words, in the preferred embodiment of the present invention, pass through
Pre-training step, can set up one in advance for the information bank identified in intelligent terminal.
Then in the preferred embodiment of the present invention, as it is shown in figure 1, above-mentioned pre-training step specifically includes:
Step S1, intelligent terminal remotely obtain the communication directory in the mobile terminal being stored in user and
User's photograph album, uses the image pattern in user's photograph album to mate with the individual human head picture in communication directory,
To set up the first training that the image pattern individual name corresponding with the individual human head picture in communication directory is associated
Sample；And/or
Intelligent terminal remotely searches and obtains the good friend that the default user account being associated with social networks is corresponding
List and good friend's photograph album, and according to the image pattern in good friend's photograph album and the individual human head picture in buddy list
Mate, relevant with the individual name setting up image pattern corresponding to the individual human head picture in buddy list
Second training sample of connection；
In one preferred embodiment of the present invention, can select only to be formed above-mentioned first training sample or
Above-mentioned second training sample.
In another preferred embodiment of the present invention, above-mentioned first training sample and can be concurrently formed
Two training samples.
Then in the preferred embodiment of the present invention, as in figure 2 it is shown, in above-mentioned steps S1, form first
The step of training sample specifically includes:
Step S11a, remotely obtains the facial image in user's photograph album；
In the preferred embodiment of the present invention, the facial image preset can be the facial image of collection in worksite,
The most acquired facial image completed before can also being, such as friend's the most issued on social networks
Major part shines.
Step S12a, remotely obtains communication directory；
In the preferred embodiment of the present invention, so-called communication directory, refer to preset include individual's name with
And the list of associated with it human head picture, correspondingly can include in register list that other are associated with individual
The information of people, such as contact method, and/or home address, and/or the user account etc. of social networks.
In the preferred embodiment of the present invention, above-mentioned communication directory is stored in the mobile terminal of user.
In the preferred embodiment of the present invention, intelligent terminal can remotely obtain above-mentioned communication directory.Specifically
Ground, is set up wireless connections, and is obtained by wireless connections between intelligent terminal and the mobile terminal of user
The communication directory preserved in mobile terminal, i.e. user mandate intelligent terminal remotely accesses the communication of user
Register.In the preferred embodiment of the present invention, due to logical between intelligent terminal and the mobile terminal of user
It is often that short distance connects, bluetooth connected mode therefore can be used to transmit data.Other of the present invention are implemented
In example, other radio connection are equally used to transmit data.
Step S13a, uses facial image to mate in communication directory, to find phase in communication directory
The individual human head picture of coupling；
Step S14a, is associated the individual name that facial image is corresponding with the individual human head picture matched；
Step S15a, circulation performs step S11a-S14a, with according to all face figures in user's photograph album
As training forms the first training sample.
In the preferred embodiment of the present invention, the facial image that above-mentioned user's photograph album includes, refer to user
In the photo of photograph album, it is possible to clearly identify the photo wherein with face shape.
In the preferred embodiment of the present invention, utilize each facial image in above-mentioned user's photograph album, with logical
The individual human head picture that news register includes mates one by one, to find the individual human head picture that matching degree is higher,
And individual name corresponding with this human head picture for corresponding facial image is associated.Further, this
In bright preferred embodiment, after overmatching, facial image (is included individual with corresponding personal information
User account on people's name, contact method, social networks, Email etc.) it is associated.
In the preferred embodiment of the present invention, the face images in traverse user photograph album, and end form
Become one first training sample.
In other words, in the preferred embodiment of the present invention, intelligent terminal is by accessing leading in mobile terminal
News register and user's photograph album automatically form the Sample Storehouse of a recognition of face.
In the preferred embodiment of the present invention, as it is shown on figure 3, in above-mentioned steps 1, form the second training
The method of sample specifically includes:
Step S11b, by being associated with the user account of at least one social network sites, remotely obtains user's account
Facial image in number good friend's photograph album being associated；
Step S12b, by being associated with the user account of at least one social network sites, remotely obtains user's account
Number buddy list being associated；
Step S13b, uses facial image to mate in buddy list, to find phase in buddy list
The individual human head picture of coupling；
Step S14b, the individual name corresponding with the individual human head picture matched in buddy list by facial image
It is associated；
Step S15b, circulation performs step S11b-14b, with according to all face figures in good friend's photograph album
As training forms the second training sample.
In the preferred embodiment of the present invention, above-mentioned steps S11b-15b is similar with step S11a-15a,
Difference is: intelligent terminal is by using for reference the buddy list in the user account on the social networks of user
And good friend's photograph album forms the second training sample.In the preferred embodiment of the present invention, intelligent terminal is led to
The mode crossing access the Internet is connected to social network sites, obtains the good of corresponding user account after authorizing
Friend's list and good friend's photograph album.
In the preferred embodiment of the present invention, intelligent terminal extracts the facial image in good friend's photograph album, and root
According to the individual human head picture in the facial image coupling buddy list being extracted, with by facial image with match
The individual name that individual human head picture is corresponding is associated.Further, by facial image and the individual number of people matched
As corresponding personal information (includes the user account on individual name, contact method, social networks, electricity
Sub-mail etc.) it is associated.
In the preferred embodiment of the present invention, the facial image in good friend's photograph album, it is similarly good friend's photograph album
Photo can clearly identify the image of face shape.
In the preferred embodiment of the present invention, intelligent terminal travels through in good friend's photograph album all of facial image also
Ultimately form one second training sample.
Step S2, in conjunction with the first training sample and/or the second training sample to form an initial training sample；
In one preferred embodiment of the present invention, if the only first training sample or the second training sample,
Then corresponding training sample is set to initial training sample.
In another preferred embodiment of the present invention, if concurrently forming the first training sample and the second training
Sample, then merge the two training sample, to form initial training sample.
Step S3, uses and is included in the facial image in initial training sample, and according to initial training sample
It is identified confirming, to improve and to form final identification data；
In the preferred embodiment of the present invention, as shown in Figure 4, above-mentioned steps S3 specifically includes:
Step S31, collection in worksite is included in the facial image in initial training sample；
In the preferred embodiment of the present invention, so-called collection in worksite, refer to on-the-spot to being associated with initial training
One specific people of sample carries out the collection of facial image, and such as shooting, collecting etc., subsequently by this face
Image is as input, to carry out facial image identification according to initial training sample.
In one preferred embodiment of the present invention, owing to the formation of above-mentioned training sample depends on user
Relational network (buddy list that such as communication directory is corresponding with the user account of social networks), therefore
The object of above-mentioned collection in worksite can be defined as the people that the relational network of user includes.
In another preferred embodiment of the present invention, the facial image of above-mentioned collection in worksite equally by
It is associated with a stranger, is i.e. not present in the facial image in initial training sample, so can realize
The self-learning function of initial training sample, with exptended sample storehouse.
Step S32, is identified confirming to facial image according to initial training sample:
If None-identified, then update initial training sample according to facial image；It is subsequently diverted to step S33；
If being capable of identify that, then directly to step S33；
In the preferred embodiment of the present invention, so-called recognition and verification, refer to confirm the knowledge of initial training sample
Other accuracy.An example be given below:
One facial image of collection in worksite is also input in intelligent terminal, and intelligent terminal is according to initial training sample
This coupling obtains a corresponding result (such as corresponding individual's name).Now intelligent terminal can send
One prompt tone, such as, point out user " this time to identify whether correct？”.If user confirms,
Then this time identify correct；Otherwise, this identifies mistake, needs to revise.
Step S33, circulation performs step S31-32, to improve initial training sample according to multiple facial images
This；
In the preferred embodiment of the present invention, as mentioned above it is possible, perform according to the circulation of multiple facial images
It is identified the work confirmed, if occurring identifying mistake, then user can be used to be manually entered and match
Personal information, or initial training sample carries out perfect by the mode such as data revising Sample Storehouse.Circulation
Above-mentioned steps S31-32, is identified confirming to initial training sample with relatively multiple facial images as far as possible
Perfect with Sample Storehouse.
Step S34, will be integrally formed identification data through perfect initial training sample, and is stored in intelligence
In energy terminal.
In the preferred embodiment of the present invention, through three of the above method (i.e. formed the first training sample,
Second training sample and improve training sample) training sample that acquires, by correspondence every each and every one
The image pattern sampling of people's name carries out pattern and identifies, screening reproducible results after cross-matched, and
Initial training sample through evening merges at last, to be identified that data are (after i.e. merging accordingly
The identification model formed and related information, such as personal information etc.), and these are identified data filing
In intelligent terminal.Specifically, in the preferred embodiment of the present invention, owing to initially relying on user
Relational network set up the training sample of corresponding recognition of face, therefore, these identify that data are returned the most at last
Shelves are in the relational network of the user preserved in intelligent terminal.
In the preferred embodiment of the present invention, being formed after identifying data, intelligent terminal i.e. can gather needs
The face identified, and according to identifying that data are identified, export recognition result.In other words, complete above-mentioned
A series of training samples be pre-formed operation after, intelligent terminal i.e. can use the identification number ultimately formed
It is identified according to face.
In the preferred embodiment of the present invention, above-mentioned intelligent terminal can be the intelligence with robot outward appearance
Terminal.In other words, in the preferred embodiment of the present invention, above-mentioned facial image recognition method can be answered
For carrying out in the robot device that information is mutual with user.
The foregoing is only preferred embodiment of the present invention, not thereby limit embodiments of the present invention and
Protection domain, to those skilled in the art, it should can appreciate that all utilization description of the invention
And the equivalent done by diagramatic content and the scheme obtained by obvious change, all should comprise
Within the scope of the present invention.
Claims (7)
1. a facial image recognition method, it is adaptable to intelligent terminal；It is characterized in that, instruct in advance including one
Practice step, to obtain corresponding training sample；
Described pre-training step specifically includes:
Step S1, described intelligent terminal remotely obtains the communication directory in the mobile terminal being stored in user
And user's photograph album, use the facial image in described user's photograph album and the individual number of people in described communication directory
As mating, corresponding with described human head picture in described communication directory to set up described facial image
The first training sample that individual's name is associated；And/or
It is corresponding that described intelligent terminal remotely searches and obtain the default user account being associated with social networks
Buddy list and good friend's photograph album, and according to the facial image in described good friend's photograph album and described buddy list
In individual human head picture mate, to set up the described individual in described facial image and described buddy list
The second training sample that the corresponding individual name of head portrait is associated；
Step S2, preliminary to form one in conjunction with described first training sample and/or described second training sample
Training sample；
Step S3, uses and is included in the described facial image in described initial training sample, and according to described
Initial training sample is identified confirming, to improve and to form final identification data；
After forming described identification data, described intelligent terminal gather need identify facial image, and according to
Described identification data are identified, and export recognition result.
2. facial image recognition method as claimed in claim 1, it is characterised in that described step S1
In, the step forming described first training sample specifically includes:
Step S11a, remotely obtains the described facial image in described user's photograph album；
Step S12a, remotely obtains described communication directory；
Step S13a, uses described facial image to mate in described communication directory, described to find
The individual human head picture matched in communication directory；
Step S14a, by relevant for individual name corresponding to the individual human head picture matched for described facial image
Connection；
Step S15a, circulation performs described step S11a-S14a, with according to the institute in described user's photograph album
The training of described facial image is had to form described first training sample.
3. facial image recognition method as claimed in claim 1, it is characterised in that described step S1
In, the step forming described second training sample specifically includes:
Step S11b, by being associated with the described user account of at least one social network sites, remotely obtains institute
State the described facial image in described good friend's photograph album that user account is associated；
Step S12b, by being associated with the described user account of at least one social network sites, remotely obtains institute
State the buddy list that user account is associated；
Step S13b, uses described facial image to mate in described buddy list, described to find
The individual human head picture matched in buddy list；
Step S14b, described facial image is corresponding with the individual human head picture matched in described buddy list
Individual's name is associated；
Step S15b, circulation performs described step S11b-14b, with according to owning in described good friend's photograph album
The training of described facial image forms described second training sample.
4. facial image recognition method as claimed in claim 1, it is characterised in that described step S1
In, described intelligent terminal accesses described mobile terminal by radio connection, and from described mobile terminal
The corresponding described communication directory of interior acquisition and described user's photograph album.
5. facial image recognition method as claimed in claim 1, it is characterised in that described step S3
Specifically include:
Step S31, collection in worksite is included in the facial image in described initial training sample；
Step S32, is identified confirming to described facial image according to described initial training sample:
If None-identified, then update described initial training sample according to described facial image；It is subsequently diverted to step
Rapid S33；
If being capable of identify that, then directly to step S33；
Step S33, circulation performs described step S31-32, to improve institute according to facial image multiple described
State initial training sample；
Step S34, will be integrally formed described identification data through perfect described initial training sample, and
It is stored in described intelligent terminal.
6. facial image recognition method as claimed in claim 5, it is characterised in that described step S32
In, described intelligent terminal is by sending prompt tone for use corresponding to the described facial image of collection in worksite
Person confirms.
7. facial image recognition method as claimed in claim 1, it is characterised in that described intelligent terminal
For having the intelligent terminal of robot outward appearance.
Priority Applications (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510381767.8A CN106326815B (en) | 2015-06-30 | 2015-06-30 | A kind of facial image recognition method |
| PCT/CN2016/086481 WO2017000807A1 (en) | 2015-06-30 | 2016-06-20 | Facial image recognition method |
| TW105120499A TWI579773B (en) | 2015-06-30 | 2016-06-29 | A face image recognition method |
| HK17105101.6A HK1231600A1 (en) | 2015-06-30 | 2017-05-19 | A face image recognition method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510381767.8A CN106326815B (en) | 2015-06-30 | 2015-06-30 | A kind of facial image recognition method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106326815A true CN106326815A (en) | 2017-01-11 |
| CN106326815B CN106326815B (en) | 2019-09-13 |
Family
ID=57607855
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510381767.8A Active CN106326815B (en) | 2015-06-30 | 2015-06-30 | A kind of facial image recognition method |
Country Status (4)
| Country | Link |
|---|---|
| CN (1) | CN106326815B (en) |
| HK (1) | HK1231600A1 (en) |
| TW (1) | TWI579773B (en) |
| WO (1) | WO2017000807A1 (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108241734A (en) * | 2017-12-01 | 2018-07-03 | 国政通科技股份有限公司 | A kind of information verification integral method and device based on photo library |
| CN108305146A (en) * | 2018-01-30 | 2018-07-20 | 杨太立 | A kind of hair style recommendation method and system based on image recognition |
| CN108764149A (en) * | 2018-05-29 | 2018-11-06 | 北京中庆现代技术股份有限公司 | A kind of training method for class student faceform |
| CN108985135A (en) * | 2017-06-02 | 2018-12-11 | 腾讯科技（深圳）有限公司 | A kind of human-face detector training method, device and electronic equipment |
| WO2020082831A1 (en) * | 2018-10-25 | 2020-04-30 | 阿里巴巴集团控股有限公司 | Face-based identity recognition method and apparatus, and electronic device |
| CN112364733A (en) * | 2020-10-30 | 2021-02-12 | 重庆电子工程职业学院 | Intelligent security face recognition system |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110309691B (en) * | 2018-03-27 | 2022-12-27 | 腾讯科技（深圳）有限公司 | Face recognition method, face recognition device, server and storage medium |
| TWI759731B (en) * | 2020-04-27 | 2022-04-01 | 淡江大學 | Machine learning method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7274822B2 (en) * | 2003-06-30 | 2007-09-25 | Microsoft Corporation | Face annotation for photo management |
| CN201774591U (en) * | 2010-08-12 | 2011-03-23 | 天津三星光电子有限公司 | Digital camera with address book and face recognition function |
| CN102867173A (en) * | 2012-08-28 | 2013-01-09 | 华南理工大学 | Human face recognition method and system thereof |
| US20130308836A1 (en) * | 2012-05-18 | 2013-11-21 | Primax Electronics Ltd. | Photo image managing method and photo image managing system |
| CN103793697A (en) * | 2014-02-17 | 2014-05-14 | 北京旷视科技有限公司 | Identity labeling method of face images and face identity recognition method of face images |
| CN103970830A (en) * | 2014-03-31 | 2014-08-06 | 小米科技有限责任公司 | Information recommendation method and device |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101330636B1 (en) * | 2007-01-24 | 2013-11-18 | 삼성전자주식회사 | Face view determining apparatus and method and face detection apparatus and method employing the same |
| CN102637255A (en) * | 2011-02-12 | 2012-08-15 | 北京千橡网景科技发展有限公司 | Method and device for processing faces contained in images |
| TW201423454A (en) * | 2011-12-09 | 2014-06-16 | Primax Electronics Ltd | System of photo management |
| CN102819726B (en) * | 2012-06-27 | 2016-08-24 | 宇龙计算机通信科技(深圳)有限公司 | photo processing system and method for mobile terminal |
| CN108345680A (en) * | 2012-06-29 | 2018-07-31 | 华为终端（东莞）有限公司 | Photograph album and the associated side of address list mutual information and terminal |
| CN102811286A (en) * | 2012-07-27 | 2012-12-05 | 广东欧珀移动通信有限公司 | Group creation method for address book |
| CN103399896B (en) * | 2013-07-19 | 2019-08-23 | 广州华多网络科技有限公司 | The method and system of incidence relation between identification user |
-
2015
- 2015-06-30 CN CN201510381767.8A patent/CN106326815B/en active Active
-
2016
- 2016-06-20 WO PCT/CN2016/086481 patent/WO2017000807A1/en active Application Filing
- 2016-06-29 TW TW105120499A patent/TWI579773B/en not_active IP Right Cessation
-
2017
- 2017-05-19 HK HK17105101.6A patent/HK1231600A1/en not_active IP Right Cessation
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7274822B2 (en) * | 2003-06-30 | 2007-09-25 | Microsoft Corporation | Face annotation for photo management |
| CN201774591U (en) * | 2010-08-12 | 2011-03-23 | 天津三星光电子有限公司 | Digital camera with address book and face recognition function |
| US20130308836A1 (en) * | 2012-05-18 | 2013-11-21 | Primax Electronics Ltd. | Photo image managing method and photo image managing system |
| CN102867173A (en) * | 2012-08-28 | 2013-01-09 | 华南理工大学 | Human face recognition method and system thereof |
| CN103793697A (en) * | 2014-02-17 | 2014-05-14 | 北京旷视科技有限公司 | Identity labeling method of face images and face identity recognition method of face images |
| CN103970830A (en) * | 2014-03-31 | 2014-08-06 | 小米科技有限责任公司 | Information recommendation method and device |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108985135A (en) * | 2017-06-02 | 2018-12-11 | 腾讯科技（深圳）有限公司 | A kind of human-face detector training method, device and electronic equipment |
| CN110490177A (en) * | 2017-06-02 | 2019-11-22 | 腾讯科技（深圳）有限公司 | A kind of human-face detector training method and device |
| US11594070B2 (en) | 2017-06-02 | 2023-02-28 | Tencent Technology (Shenzhen) Company Limited | Face detection training method and apparatus, and electronic device |
| CN108241734A (en) * | 2017-12-01 | 2018-07-03 | 国政通科技股份有限公司 | A kind of information verification integral method and device based on photo library |
| CN108305146A (en) * | 2018-01-30 | 2018-07-20 | 杨太立 | A kind of hair style recommendation method and system based on image recognition |
| CN108764149A (en) * | 2018-05-29 | 2018-11-06 | 北京中庆现代技术股份有限公司 | A kind of training method for class student faceform |
| CN108764149B (en) * | 2018-05-29 | 2022-02-18 | 北京中庆现代技术股份有限公司 | Training method for class student face model |
| WO2020082831A1 (en) * | 2018-10-25 | 2020-04-30 | 阿里巴巴集团控股有限公司 | Face-based identity recognition method and apparatus, and electronic device |
| CN112364733A (en) * | 2020-10-30 | 2021-02-12 | 重庆电子工程职业学院 | Intelligent security face recognition system |
| CN112364733B (en) * | 2020-10-30 | 2022-07-26 | 重庆电子工程职业学院 | Intelligent security face recognition system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106326815B (en) | 2019-09-13 |
| TW201701188A (en) | 2017-01-01 |
| TWI579773B (en) | 2017-04-21 |
| WO2017000807A1 (en) | 2017-01-05 |
| HK1231600A1 (en) | 2017-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106326815A (en) | Human face image recognition method | |
| CN205314704U (en) | Intelligence lock and system | |
| CN104582187B (en) | Based on the record of recognition of face and Expression Recognition and lamp light control system and method | |
| CN103310142B (en) | Based on the human-computer fusion safety certifying method of wearable device | |
| CN103118031B (en) | Log in method and the electronic equipment of application account | |
| CN104008325B (en) | Mobile phone wireless Wi-Fi on-Internet true name identity authentication platform based on Quick Response Code and method | |
| CN107121938A (en) | Intelligent home equipment control method, the device and system of identity-based identification | |
| WO2019000777A1 (en) | Internet-based face beautification system | |
| CN103136508A (en) | Gesture identification method and electronic equipment | |
| CN102932414A (en) | Method and system for combining address book and social network | |
| CN104935440A (en) | Authentication method and authentication device for remote opening of financial account | |
| CN106027543A (en) | Identification method and apparatus based on weight calculation | |
| CN107305549A (en) | Language data processing method, device and the device for language data processing | |
| CN106371785B (en) | A kind of processing method of display pattern, system and terminal | |
| CN103957580A (en) | Rapid WIFI networking matching method and module for smart hardware | |
| CN106249611A (en) | A kind of Smart Home localization method based on virtual reality, device and system | |
| CN105847451A (en) | Method and system for controlling intelligent access control unit by using mobile terminal | |
| CN103973550A (en) | Method, system and device for rapidly and intelligently identifying instant messaging application ID (identity) number and carrying out instant messaging | |
| CN104778392A (en) | Privilege validation method and system on basis of biological identification | |
| CN104036170A (en) | Smart glasses and a control method and device of same | |
| CN114721284A (en) | Intelligent home management system based on Internet of things | |
| CN110149618A (en) | Smart machine cut-in method, device, equipment and medium based on vocal print authorization | |
| CN103870735A (en) | Unlocking processing method and device | |
| CN104967762A (en) | Configuration method for wireless Internet camera and configuration system thereof | |
| CN105122295B (en) | Message method, message receival method, management server, message switching system, terminal and methods of terminal registration |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1231600 Country of ref document: HK |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |