CN105809154A - Face identification method and device - Google Patents
Face identification method and device Download PDFInfo
- Publication number
- CN105809154A CN105809154A CN201610306277.6A CN201610306277A CN105809154A CN 105809154 A CN105809154 A CN 105809154A CN 201610306277 A CN201610306277 A CN 201610306277A CN 105809154 A CN105809154 A CN 105809154A
- Authority
- CN
- China
- Prior art keywords
- image
- face
- sample image
- many groups
- sample
- 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.)
- Pending
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
- G06V40/168—Feature extraction; Face representation
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Collating Specific Patterns (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a face identification method and device.The face identification method includes the steps that a first to-be-detected image characteristic corresponding to a first face image of a to-be-detected target is extracted; the first to-be-detected image characteristic and the image characteristics of multiple sets of preset sample images are subjected to similarity analysis, wherein the multiple sets of preset sample images are face sample images, obtained under the preset light condition, of multiple persons; according to the result of similarity analysis, the identity corresponding to the first set of face sample images with the highest similarity serves as the first identification result of face identification.By means of the face identification method and device, the influence on the face identification accuracy rate of different light conditions can be decreased, and therefore the accuracy and the robustness of face identification are improved.
Description
Technical field
The present invention relates to computer vision and image processing field, particularly relate to a kind of face identification method and device.
Background technology
The demand that personal identification is carried out effectively identifying by various circles of society now becomes more and more urgent so that biometrics identification technology achieves development at full speed in recent decades.A kind of inherent attribute as people, face has very strong self stability and individual difference, and compared to modes such as fingerprint recognition, recognition of face is because having the advantages such as non-imposed, untouchable and concurrency, and becomes the optimal foundation of auto authentication.
Current face recognition technology has a wide range of applications in the following aspects: criminal investigation department is according to the criminal's photo being stored in advance in archives economy, when after the description of the photo or facial characteristics that get suspect, confirmation can be searched rapidly from data base, be greatly improved accuracy rate and the efficiency of criminal investigation and case detection；In the public place such as customs, airport, use face recognition technology, it is possible to achieve quickly, efficiently and the clearance service of automatization, improve the quality of current efficiency and service；The video monitoring of 24 hours can be set up, when there being blacklist personnel to enter, it is possible to carry out real-time tracking, identification and warning etc. in bank, company and public place.
But, the accuracy rate of existing recognition of face is largely influenced by the impact of illumination variation, US military data base (FERET) and recognition of face provider evaluation (FRVT) test also indicate that, illumination variation is still one of bottleneck of practical face identification system.In recent years, researcher proposes the method for many solution lighting issues, substantially can be divided into 2 kinds of thinkings: based on traditional image processing method (such as image processing methods etc. such as histogram equalization, logarithm changes)；And extract illumination invariant shape characterization method.But this existing method based on both thinkings is still without well solving the impact that illumination variation is brought, and constrains face recognition application in the effect of different illumination conditions, it is impossible to meet practical application request.
Summary of the invention
Based on this, the technical problem to be solved is: how to improve the face recognition accuracy rate under different illumination conditions and robustness.
For this purpose it is proposed, one aspect of the present invention proposes a kind of face identification method, the method includes:
Extract the first testing image feature that the first facial image of target to be measured is corresponding；
The characteristics of image that described first testing image feature and many groups preset sample image carries out similarity analysis, and described many groups preset the face sample image that sample image is the multiple personages obtained under multiple default illumination condition；
Result according to similarity analysis, using the identity corresponding for first group of the highest for similarity face sample image the first recognition result as recognition of face.
Preferably, the described characteristics of image by described first testing image feature with the default sample image of many groups carries out similarity analysis, including:
The first testing image characteristic vector is determined according to described first testing image feature, described first testing image characteristic vector is expressed as sample image eigenmatrix and first and represents the form of coefficient matrix product, solving the described first optimal solution representing coefficient matrix by optimization algorithm, described sample image eigenmatrix is preset, according to described many groups, the matrix that the characteristics of image of sample image is determined；
Represent that the optimal solution of coefficient matrix determines respectively that with the characteristics of image of the described default sample image of many groups described many groups preset the characteristics of image of the often width synthesis facial image that the default sample image of group is corresponding in sample image according to described first；
Calculate between the characteristics of image of described first testing image feature and every width synthesis facial image first respectively and represent error, and represent that using described first minimum width synthesis lineup's face image corresponding to facial image of error is as the highest first group of face sample image of similarity.
Preferably, the described characteristics of image by described first testing image feature with the default sample image of many groups also includes before carrying out similarity analysis:
Preset sample image, and extract the characteristics of image of the described default sample image of many groups for many groups that obtain the known personage of multiple identity.
Preferably, many groups of the known personage of the multiple identity of described acquisition preset sample image, including:
Obtain each personage in the known personage of multiple identity respectively and be in different several face sample images preset under illumination condition.
Preferably, obtain each personage in the known personage of multiple identity respectively and be in different several face sample images preset under illumination condition, including:
Several face sample images belonging to same personage are preset sample image as one group.
On the other hand, the invention also discloses a kind of face identification device, this device includes:
Feature extraction unit, the first testing image feature corresponding for extracting the first facial image of target to be measured；
Similarity analysis unit, for the characteristics of image that described first testing image feature and many groups preset sample image is carried out similarity analysis, described many groups preset the face sample image that sample image is the multiple personages obtained under multiple default illumination condition；
Face identification unit, for result according to similarity analysis, using the identity corresponding for first group of the highest for similarity face sample image the first recognition result as recognition of face.
Preferably, described similarity analysis unit is further used for determining the first testing image characteristic vector according to described first testing image feature, described first testing image characteristic vector is expressed as sample image eigenmatrix and first and represents the form of coefficient matrix product, solving the described first optimal solution representing coefficient matrix by optimization algorithm, described sample image eigenmatrix is preset, according to described many groups, the matrix that the characteristics of image of sample image is determined；Represent that the optimal solution of coefficient matrix determines respectively that with the characteristics of image of the described default sample image of many groups described many groups preset the characteristics of image of the often width synthesis facial image that the default sample image of group is corresponding in sample image according to described first；Calculate between the characteristics of image of described first testing image feature and every width synthesis facial image first respectively and represent error, and represent that using described first minimum width synthesis lineup's face image corresponding to facial image of error is as the highest first group of face sample image of similarity.
Preferably, this device also includes image acquisition unit, and described image acquisition unit presets sample image for many groups that obtain the known personage of multiple identity；
Described feature extraction unit is additionally operable to extract described many groups and presets the characteristics of image of sample image.
Preferably, described image acquisition unit is further used for:
Obtain each personage in the known personage of multiple identity respectively and be in different several face sample images preset under illumination condition.
Preferably, described image acquisition unit is further used for:
Several face sample images belonging to same personage are preset sample image as one group.
The present invention can reduce the different illumination conditions impact on recognition of face, thus improving accuracy rate and the robustness of recognition of face.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, the accompanying drawing used required in embodiment or description of the prior art will be briefly described below, apparently, accompanying drawing in the following describes is some embodiments of the present invention, for those of ordinary skill in the art, under the premise not paying creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 illustrates the flow chart of the face identification method of one embodiment of the invention；
Fig. 2 illustrates the flow chart of the face identification method of another embodiment of the present invention；
Fig. 3 illustrates the top view of the sample image harvester of one embodiment of the invention；
Fig. 4 illustrates the horizontal direction schematic diagram of the sample image harvester of one embodiment of the invention；
Fig. 5 illustrates the structured flowchart of the face identification device of one embodiment of the invention.
Detailed description of the invention
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearly, 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 explicitly described, it is clear that, described embodiment is a part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, the every other embodiment that those of ordinary skill in the art obtain under not making creative work premise, broadly fall into the scope of protection of the invention.
Fig. 1 illustrates the flow chart of the face identification method of one embodiment of the invention；As it is shown in figure 1, the method includes:
S1: extract the first testing image feature that the first facial image of target to be measured is corresponding；
S2: the characteristics of image that described first testing image feature and many groups preset sample image carries out similarity analysis, and described many groups preset the face sample image that sample image is the multiple personages obtained under multiple default illumination condition；
S3: the result according to similarity analysis, using the identity corresponding for first group of the highest for similarity face sample image the first recognition result as recognition of face.
The characteristics of image extracted in the present embodiment can comprise color characteristic, textural characteristics etc. can embody the feature of image individual variation, does not limit in the present embodiment.
The face identification method process of the present embodiment is simply, easily realize, it is possible to reduce the different illumination conditions impact on recognition of face, improves accuracy rate and the robustness of recognition of face.
Preferred as the present embodiment, the characteristics of image that described first testing image feature and many groups preset sample image are carried out similarity analysis by step S2, it may include:
The first testing image characteristic vector is determined according to described first testing image feature, described first testing image characteristic vector is expressed as sample image eigenmatrix and first and represents the form of coefficient matrix product, by optimization algorithm (such as, L1 norm optimization algorithm) solve the described first optimal solution representing coefficient matrix, described sample image eigenmatrix is preset, according to described many groups, the matrix that the characteristics of image of sample image is determined；
Represent that the optimal solution of coefficient matrix determines respectively that with the characteristics of image of the described default sample image of many groups described many groups preset the characteristics of image of the often width synthesis facial image that the default sample image of group is corresponding in sample image according to described first；
Calculate between the characteristics of image of described first testing image feature and every width synthesis facial image first respectively and represent error, and represent that using described first minimum width synthesis lineup's face image corresponding to facial image of error is as the highest first group of face sample image of similarity.
On this basis, Fig. 2 illustrates the flow chart of the face identification method of another embodiment of the present invention；As in figure 2 it is shown, before step S2 (or step S1), the method may also include that
S0: many groups that obtain the known personage of multiple identity preset sample image, and extract the characteristics of image of the described default sample image of many groups.
Further, the face sample image that the known personage of the multiple identity of above-mentioned acquisition is respectively under different default illumination condition can preferably include:
Obtain each personage in the known personage of multiple identity respectively and be in different several face sample images preset under illumination condition, and on this basis, several face sample images belonging to same personage can be preset sample image as one group.
Specifically, in the sample collection stage, gather the facial image under different lighting angle as database template, to set up face database.When starting to identify, first image to be identified is carried out feature extraction (such as extracting the gray feature of image), be then the linear combination of different illumination conditions human face characteristics of image in data base by the character representation of this image to be identified.Owing to having stronger dependency between the facial image of same person, and dependency between different people is less, therefore data base is that the facial image of same people has bigger expression coefficient (i.e. likeness coefficient) with image to be identified, and the expression coefficient of the facial image of different people is almost 0；Thus can pass through to analyze image to be identified expression coefficient on the database, it is possible to complete recognition of face.
Fig. 3 illustrates the top view of the sample image harvester of one embodiment of the invention；Fig. 4 illustrates the horizontal direction schematic diagram of the sample image harvester of one embodiment of the invention.As it is shown on figure 3, image collecting device can be made up of (below in order to describe principle, it is assumed that number of light sources is 7, the angle between each light source is 20 °) a photographing unit and multiple lighting source.Multiple lighting sources can independent switch, and be arranged on same horizontal plane, for instance multiple lighting sources are respectively positioned on the same circumference that face location is the center of circle.This photographing unit is just to face, it is in same level with face, the height of lighting source can regulate and (preferably be respectively arranged at higher than face by lighting source, slightly above face with lower than the position of face), and in adjustment process, all light sources are in same level all the time, as shown in Figure 4.
Specifically, as shown in Figure 3, Figure 4, be numbered 1,2,3 ..., 7 light source position be relatively fixed, angle between each light source is 20 °, namely being irradiated from the direction of-60 ° of face ,-40 ° ,-20 °, 0 °, 20 °, 40 °, 60 ° respectively (being wherein positioned at the light source of 0 ° just to face), position for video camera is in just position to face.When image acquisition, according to numbering, 7 light sources are lighted successively, and simultaneous camera shoots the facial image under different light source irradiation successively, and records light source numbering corresponding to image and height and position.Then regulate the height and position of light source, again according to the mode putting bright light source successively, gather 7 facial images；The like, obtain each 7 images under 3 kinds of light source differing heights altogether, namely everyone correspondence 21 in face database has numbered images.
Image under everyone 21 different illumination in data base is carried out feature extraction respectively, the feature extracted is designated as:
fi=[fi1fi2fi3fi4fi5…fi21],
fij=[fij1fij2…fijr-1fijr]T, j=1,2 ... 21,
Wherein i is the numbering of i-th people in data base, and r is the intrinsic dimensionality of every face extraction；If there being n people in data base, then the information of whole data base can use matrix F=[f1f2…fn] represent.
For a facial image x to be identified, extract and it is characterized by fx；By fxRepresent then have with the linearity in data base:
fx=W × F=W × [f1f2…fn]
=W × [f11f12…fn21],
Solved by optimization algorithm (such as L1 norm optimization algorithm), can obtain
W=[w1w2…wn21]。
Due to facial image x to be identified only with data base is that the facial image of same person (assuming this artificial i) has higher similarity, therefore in W the overwhelming majority elements all close to 0, only at the coefficient place that the characteristic vector of i is corresponding, there is bigger value, coefficient is represented, it is possible to complete the process of recognition of face by analyzing.
Concrete comparison procedure is as follows:
Calculate in facial image x to be identified and data base each group of image expression error under the coefficient W solved, as with the i-th person-to-person expression error in data base being:
Wherein wijIn corresponding expression coefficient W, i-th people's jth opens the expression coefficient of sample characteristics, fijThe feature of sample image is opened for i-th people's jth.
Would indicate that the identity recognition result the most that the minimum one group of image of error is corresponding.
The face identification method of the present embodiment can reduce the different illumination conditions impact on recognition of face, thus improving accuracy rate and the robustness of recognition of face.
Fig. 5 illustrates the structured flowchart of the face identification device of one embodiment of the invention；As it is shown in figure 5, this device includes feature extraction unit 11, similarity analysis unit 12 and face identification unit 13；
Described feature extraction unit 11, the first testing image feature corresponding for extracting the first facial image of target to be measured；
Described similarity analysis unit 12, for the characteristics of image that described first testing image feature and many groups preset sample image is carried out similarity analysis, described many groups preset the face sample image that sample image is the multiple personages obtained under multiple default illumination condition；
Described face identification unit 13, for result according to similarity analysis, using the identity corresponding for first group of the highest for similarity face sample image the first recognition result as recognition of face.
Face identification method and device described in the present embodiment may be used for performing said method embodiment, and its principle is similar with technique effect, repeats no more herein.
Preferred as the present embodiment, described similarity analysis unit 12 is further used for determining the first testing image characteristic vector according to described first testing image feature, described first testing image characteristic vector is expressed as sample image eigenmatrix and first and represents the form of coefficient matrix product, by optimization algorithm (such as L1 norm optimization algorithm) solve as described in the first optimal solution representing coefficient matrix, described sample image eigenmatrix is preset, according to described many groups, the matrix that the characteristics of image of sample image are determined；Represent that the optimal solution of coefficient matrix determines respectively that with the characteristics of image of the described default sample image of many groups described many groups preset the characteristics of image of the often width synthesis facial image that the default sample image of group is corresponding in sample image according to described first；Calculate between the characteristics of image of described first testing image feature and every width synthesis facial image first respectively and represent error, and represent that using described first minimum width synthesis lineup's face image corresponding to facial image of error is as the highest first group of face sample image of similarity.
On this basis, this device also includes image acquisition unit 14, and described image acquisition unit 14 presets sample image for many groups that obtain the known personage of multiple identity；
Correspondingly, described feature extraction unit 11 is additionally operable to extract described many groups and presets the characteristics of image of sample image.
Alternatively, described image acquisition unit 14 is further used for obtaining each personage in the known personage of multiple identity respectively and is in different several face sample images preset under illumination condition, and as one group, several face sample images belonging to same personage can be preset sample image.
Face identification method and device described in the present embodiment may be used for performing said method embodiment, and its principle is similar with technique effect, repeats no more herein.For device embodiment, due to itself and embodiment of the method basic simlarity, so what describe is fairly simple, relevant part illustrates referring to the part of embodiment of the method.
The method of the present invention and device can reduce the different illumination conditions impact on recognition of face, thus improving accuracy rate and the robustness of recognition of face.
Above example is merely to illustrate technical scheme, is not intended to limit；Although the present invention being described in detail with reference to previous embodiment, it will be understood by those within the art that: the technical scheme described in foregoing embodiments still can be modified by it, or wherein portion of techniques feature is carried out equivalent replacement；And these amendments or replacement, do not make the essence of appropriate technical solution depart from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (10)
1. a face identification method, it is characterised in that including:
Extract the first testing image feature that the first facial image of target to be measured is corresponding；
The characteristics of image that described first testing image feature and many groups preset sample image carries out similarity analysis, and described many groups preset the face sample image that sample image is the multiple personages obtained under multiple default illumination condition；
Result according to similarity analysis, using the identity corresponding for first group of the highest for similarity face sample image the first recognition result as recognition of face.
2. face identification method as claimed in claim 1, it is characterised in that the described characteristics of image by described first testing image feature with the default sample image of many groups carries out similarity analysis, including:
The first testing image characteristic vector is determined according to described first testing image feature, described first testing image characteristic vector is expressed as sample image eigenmatrix and first and represents the form of coefficient matrix product, solving the described first optimal solution representing coefficient matrix by optimization algorithm, described sample image eigenmatrix is preset, according to described many groups, the matrix that the characteristics of image of sample image is determined；
Represent that the optimal solution of coefficient matrix determines respectively that with the characteristics of image of the described default sample image of many groups described many groups preset the characteristics of image of the often width synthesis facial image that the default sample image of group is corresponding in sample image according to described first；
Calculate between the characteristics of image of described first testing image feature and every width synthesis facial image first respectively and represent error, and represent that using described first minimum width synthesis lineup's face image corresponding to facial image of error is as the highest first group of face sample image of similarity.
3. face identification method as claimed in claim 1 or 2, it is characterised in that the described characteristics of image by described first testing image feature with the default sample image of many groups also includes before carrying out similarity analysis:
Preset sample image, and extract the characteristics of image of the described default sample image of many groups for many groups that obtain the known personage of multiple identity.
4. face identification method as claimed in claim 3, it is characterised in that many groups of the known personage of the multiple identity of described acquisition preset sample image, including:
Obtain each personage in the known personage of multiple identity respectively and be in different several face sample images preset under illumination condition.
5. face identification method as claimed in claim 4, it is characterised in that obtain each personage in the known personage of multiple identity respectively and be in different several face sample images preset under illumination condition, including:
Several face sample images belonging to same personage are preset sample image as one group.
6. a face identification device, it is characterised in that including:
Feature extraction unit, the first testing image feature corresponding for extracting the first facial image of target to be measured；
Similarity analysis unit, for the characteristics of image that described first testing image feature and many groups preset sample image is carried out similarity analysis, described many groups preset the face sample image that sample image is the multiple personages obtained under multiple default illumination condition；
Face identification unit, for result according to similarity analysis, using the identity corresponding for first group of the highest for similarity face sample image the first recognition result as recognition of face.
7. face identification device as claimed in claim 6, it is characterized in that, described similarity analysis unit is further used for determining the first testing image characteristic vector according to described first testing image feature, described first testing image characteristic vector is expressed as sample image eigenmatrix and first and represents the form of coefficient matrix product, solving the described first optimal solution representing coefficient matrix by optimization algorithm, described sample image eigenmatrix is preset, according to described many groups, the matrix that the characteristics of image of sample image is determined；Represent that the optimal solution of coefficient matrix determines respectively that with the characteristics of image of the described default sample image of many groups described many groups preset the characteristics of image of the often width synthesis facial image that the default sample image of group is corresponding in sample image according to described first；Calculate between the characteristics of image of described first testing image feature and every width synthesis facial image first respectively and represent error, and represent that using described first minimum width synthesis lineup's face image corresponding to facial image of error is as the highest first group of face sample image of similarity.
8. face identification device as claimed in claims 6 or 7, it is characterised in that this device also includes image acquisition unit, described image acquisition unit presets sample image for many groups that obtain the known personage of multiple identity；
Described feature extraction unit is additionally operable to extract described many groups and presets the characteristics of image of sample image.
9. face identification device as claimed in claim 8, it is characterised in that described image acquisition unit is further used for:
Obtain each personage in the known personage of multiple identity respectively and be in different several face sample images preset under illumination condition.
10. face identification device as claimed in claim 9, it is characterised in that described image acquisition unit is further used for:
Several face sample images belonging to same personage are preset sample image as one group.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610306277.6A CN105809154A (en) | 2016-05-10 | 2016-05-10 | Face identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610306277.6A CN105809154A (en) | 2016-05-10 | 2016-05-10 | Face identification method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105809154A true CN105809154A (en) | 2016-07-27 |
Family
ID=56455758
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610306277.6A Pending CN105809154A (en) | 2016-05-10 | 2016-05-10 | Face identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105809154A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106548161A (en) * | 2016-11-23 | 2017-03-29 | 上海成业智能科技股份有限公司 | The collection of face recognition features' code and knowledge method for distinguishing under the conditions of disturbing for outdoor or light |
| CN107609508A (en) * | 2017-09-08 | 2018-01-19 | 深圳市金立通信设备有限公司 | A kind of face identification method, terminal and computer-readable recording medium |
| CN111291627A (en) * | 2020-01-16 | 2020-06-16 | 广州酷狗计算机科技有限公司 | Face recognition method and device and computer equipment |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105488486A (en) * | 2015-12-07 | 2016-04-13 | 清华大学 | Face recognition method and device for preventing photo attack |
-
2016
- 2016-05-10 CN CN201610306277.6A patent/CN105809154A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105488486A (en) * | 2015-12-07 | 2016-04-13 | 清华大学 | Face recognition method and device for preventing photo attack |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106548161A (en) * | 2016-11-23 | 2017-03-29 | 上海成业智能科技股份有限公司 | The collection of face recognition features' code and knowledge method for distinguishing under the conditions of disturbing for outdoor or light |
| CN107609508A (en) * | 2017-09-08 | 2018-01-19 | 深圳市金立通信设备有限公司 | A kind of face identification method, terminal and computer-readable recording medium |
| CN111291627A (en) * | 2020-01-16 | 2020-06-16 | 广州酷狗计算机科技有限公司 | Face recognition method and device and computer equipment |
| CN111291627B (en) * | 2020-01-16 | 2024-04-19 | 广州酷狗计算机科技有限公司 | Face recognition method and device and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR100974293B1 (en) | METHOD AND SYSTEM FOR AUTOMATED FACE DETECTION and Recognition | |
| Sun et al. | Improving iris recognition accuracy via cascaded classifiers | |
| US6944318B1 (en) | Fast matching systems and methods for personal identification | |
| CN104091176B (en) | Portrait comparison application technology in video | |
| CN100403981C (en) | Positive patient identification | |
| CN109558810B (en) | Target person identification method based on part segmentation and fusion | |
| CN104820819B (en) | Verifying uses true finger as the verification method of the carrier of fingerprint and verifying device | |
| US20210034840A1 (en) | Method for Recognzing Face from Monitoring Video Data | |
| CN110728252B (en) | Face detection method applied to regional personnel motion trail monitoring | |
| KR100944247B1 (en) | System and method for face recognition | |
| CN105718866B (en) | A kind of detection of sensation target and recognition methods | |
| CN103034838A (en) | Special vehicle instrument type identification and calibration method based on image characteristics | |
| CN105488486B (en) | The face identification method and device for preventing photo from attacking | |
| KR20050025927A (en) | The pupil detection method and shape descriptor extraction method for a iris recognition, iris feature extraction apparatus and method, and iris recognition system and method using its | |
| CN101027678A (en) | Single image based multi-biometric system and method | |
| CN106650623A (en) | Face detection-based method for verifying personnel and identity document for exit and entry | |
| CN106022241A (en) | Face recognition method based on wavelet transformation and sparse representation | |
| CN105809154A (en) | Face identification method and device | |
| Lijun et al. | Multi-branch face quality assessment for face recognition | |
| CN110222660B (en) | Signature authentication method and system based on dynamic and static feature fusion | |
| CN108345847B (en) | System and method for generating label data of face image | |
| CN113947796A (en) | Human body temperature trend detection method and device based on identity recognition | |
| EP1020811A2 (en) | Fast matching systems and methods for personal identification | |
| CN107657201A (en) | NEXT series of products characteristics of image identifying systems and its recognition methods | |
| CN106548112A (en) | A kind of personal identification method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160727 |