CN111967381A - Face image quality grading and labeling method and device - Google Patents
Face image quality grading and labeling method and device Download PDFInfo
- Publication number
- CN111967381A CN111967381A CN202010822252.8A CN202010822252A CN111967381A CN 111967381 A CN111967381 A CN 111967381A CN 202010822252 A CN202010822252 A CN 202010822252A CN 111967381 A CN111967381 A CN 111967381A
- Authority
- CN
- China
- Prior art keywords
- face
- face image
- quality
- ith
- person
- 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
Images
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
- G06V40/168—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
- G06V40/172—Classification, e.g. identification
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)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention provides a method and a device for marking face image quality scores, wherein the method comprises the following steps: the face image to be detected in the set and the face image with the external noise are subjected to face recognition network to obtain corresponding face characteristic vectors; wherein, each person at least comprises a reference picture; calculating an indicative function according to the reference map characteristics of the ith person and the reference map characteristics of other different persons; calculating a quality value for the kth map of the ith individual based on the indicative function; performing linear transformation on the quality value to obtain a final label value of the kth image to be tested of the ith person; and performing face quality evaluation model training by using the final label value. The method comprehensively considers the intra-class distance and the inter-class distance of the human face features and carries out the task of labeling the human face image training sample for the quality evaluation task. By applying the method, more accurate face image quality label values can be obtained, and a foundation is laid for better face quality evaluation networks for subsequent training.
Description
Technical Field
One or more embodiments of the invention relate to the technical field of image processing, in particular to a method and a device for marking face image quality scores.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein may include concepts that could be pursued, but are not necessarily ones that have been previously conceived or pursued. Thus, unless otherwise indicated herein, what is described in this section is not prior art to the description and claims in this application and is not admitted to be prior art by inclusion in this section.
With the rapid development of society and science and technology, face recognition technology is more and more widely applied and popularized, and for example, the face recognition technology is gradually applied to important security ports such as airports, railway stations and the like, and important places such as banks, communities and the like closely related to people's life, and the applications have higher requirements on the accuracy and the efficiency of a face recognition algorithm. In order to improve the accuracy of human face-based tasks such as human face recognition, quality evaluation is usually performed on human face images, and then the human face images with higher evaluation scores are applied to the tasks. The existing face image quality scoring technology mainly comprises the following steps:
1, scoring according to artificial subjective feelings;
2, no reference evaluation is carried out, according to objectively designed statistical values, such as illumination intensity, ambiguity, human face angle and the like are extracted first, and then comprehensive indexes are calculated to serve as label values;
and 3, full reference evaluation, and scoring according to the difference between the test image and the reference image: such as various statistical indicators, such as structural similarity, etc.; or directly using the similarity of the feature vectors extracted by the deep learning network.
However, the above techniques all have disadvantages:
1, the manual scoring cost is high, and the efficiency is low;
2, objective design indexes hardly take all possible influence factors into consideration on one hand, and comprehensive indexes are poor in robustness and inaccurate in quality evaluation on the other hand;
3, generally only considering the difference or the (intra-class) distance between the reference images of the same type, but not considering the difference or the (inter-class) distance between the reference images of different types, so that the evaluation label is not accurate enough, and further the training effect of the subsequent quality evaluation network or model is not good;
and 4, when the quality evaluation is carried out by using the depth characteristics, the accuracy of the depth network is not considered.
In view of the above, a more comprehensive scoring method with high quality evaluation is needed.
Disclosure of Invention
One or more embodiments of the present disclosure describe a method and an apparatus for labeling face image quality scores, which can solve the problems of low efficiency, high cost and incomplete and accurate evaluation in the prior art.
The technical scheme provided by one or more embodiments of the specification is as follows:
in a first aspect, the present invention provides a method for labeling face image quality scores, comprising:
the face image to be detected in the set and the face image with the external noise are subjected to face recognition network to obtain corresponding face characteristic vectors; wherein, each person at least comprises a reference picture;
calculating an indicative function according to the reference map characteristics of the ith person and the reference map characteristics of other different persons;
calculating a quality value for the kth map of the ith individual based on the indicative function;
performing linear transformation on the quality value to obtain a final label value of the kth image to be tested of the ith person;
and performing face quality evaluation model training by using the final label value.
In one possible implementation, the out-of-set faces and the in-set face identities do not overlap.
In one possible implementation, the feature vectors are normalized before the indicative function is calculated.
In one possible implementation, the indicative function is calculated according to the following formula:
wherein the content of the first and second substances,a reference map feature for the ith person;reference map features for other different persons; j ═ 1,2,. N + M-1; n is the number of people to be tested in the set, and M is the number of noise people outside the set; the vector inner product of the reference image feature of the ith person and the reference images of other different persons is recorded ast is a threshold constant.
In one possible implementation, the quality value q of the kth test image of the ith individual is calculated according to the following formula:
therein, ζi,jIs an indicative function; the vector inner product of the ith individual's reference image feature and its kth chart feature to be measured is recorded asp is a relaxation constant; and s is a scale constant.
In one possible implementation, the quality value q is linearly transformed according to the following formula: q (i, j) ═ w · Q + b, where w, b are constants.
In a second aspect, the present invention provides a face image quality scoring and labeling device, including:
the processing unit is configured to enable the face image to be detected in the set and the face image with the external noise to pass through a face recognition network to obtain corresponding face characteristic vectors; wherein, each person at least comprises a reference picture;
a first calculation unit configured to calculate an indicative function based on the reference map feature of the ith person and the reference map features of the different persons;
a second calculation unit configured to calculate a quality value of the kth chart to be tested of the ith individual based on the indicative function;
the linear transformation unit is configured to perform linear transformation on the quality value to obtain a final label value of the kth image to be tested of the ith person;
and the model training unit is configured to perform face quality evaluation model training by using the final label value.
In a third aspect, the invention provides a face image quality scoring and labeling system, which comprises at least one processor and a memory;
the memory to store one or more program instructions;
the processor is configured to execute one or more program instructions to perform the method according to one or more of the first aspects.
In a fourth aspect, the present invention provides a chip, which is coupled to a memory in a system, so that the chip calls program instructions stored in the memory when running to implement the method according to one or more of the first aspects.
In a fifth aspect, the invention provides a computer readable storage medium comprising one or more program instructions executable by a system according to the third aspect to implement a method according to one or more of the first aspects.
The method provided by the embodiment of the invention comprehensively considers the intra-class distance and the inter-class distance of the human face characteristics and carries out the task of labeling the human face image training sample for the quality evaluation task. By applying the method, more accurate face image quality label values can be obtained, and a foundation is laid for better face quality evaluation networks for subsequent training.
Drawings
Fig. 1 is a schematic flow chart of a method for marking a face image quality score according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a face image quality scoring and labeling device according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a face image quality scoring and labeling system according to an embodiment of the present invention.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be further noted that, for the convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Fig. 1 shows a flowchart of a face image quality score labeling method according to an embodiment, and an execution subject of the method may be any device, equipment, platform, or equipment cluster with computing and processing capabilities.
As shown in fig. 1, the method comprises the steps of:
Firstly, establishing an in-set human face image sample set to be detected and an out-set noise human face image sample set, specifically, the following process is carried out:
the image is processed by a face detection network to obtain a reference image sample set containing N different personsAnd a sample book to be testedEach person comprises at least one reference picture;
the images are subjected to a face detection network to obtain a reference image sample set containing M different personsCommon out-of-collection and in-collection face identities do not overlap
And step 20, calculating the representative function according to the reference picture characteristics of the ith person and the reference picture characteristics of other different persons.
Before calculating the indicative function, normalizing the feature vector, specifically: all pictures are subjected to a face recognition network to obtain corresponding face feature vectors v, and the face feature vectors v are subjected to feature normalizationThe reference picture of the ith person is characterized in thatThe kth image to be measured of the ith person is characterized in that
Specifically, the illustrative function is calculated by the following formula:
wherein the content of the first and second substances,a reference map feature for the ith person;reference map features for other different persons; j ═ 1,2,. N + M-1; n is the number of people to be tested in the set, and M is the number of noise people outside the set; the vector inner product of the reference image feature of the ith person and the reference images of other different persons is recorded ast is a threshold constant, which may be 0.5.
And step 30, calculating the quality value of the k-th image to be tested of the ith individual based on the indicative function.
Specifically, the quality value q of the kth image to be tested of the ith individual is calculated according to the following formula:
therein, ζi,jIs an indicative function; the vector inner product of the ith individual's reference image feature and its kth chart feature to be measured is recorded asp is a relaxation constant, which can be set to 0.2 in general; s is a scale constant, which can be set to 32 in general.
And step 40, performing linear transformation on the quality value to obtain a final label value of the kth image to be tested of the ith individual.
Specifically, the quality value q is linearly transformed according to the following formula: q (i, j) ═ w · Q + b, where w, b are constants.
And step 50, training a face quality evaluation model by using the final label value.
And (4) performing face quality evaluation model training by using the final label value obtained in the step (40).
The label value is obtained by the features extracted by the deep learning network, so the face image quality scoring and labeling method provided by the embodiment of the invention has high efficiency and low cost. Meanwhile, the method has the following advantages:
(1) the introduction of a relaxation variable is controlled by constructing an indicative function, so that the problem of low intra-class similarity caused by insufficient classification capability of the face recognition model can be solved, and the condition of low score caused by non-picture quality problem is corrected.
(2) By retraining the network model, the face recognition model features are used directly.
(3) Meanwhile, inter-class and intra-class distance influences of the face image are considered, so that evaluation is more comprehensive.
Corresponding to the method of the above embodiment, the present invention further provides a method and an apparatus for labeling face image quality scores, as shown in fig. 2, the method and the apparatus for labeling face image quality scores include: a processing unit 210, a first calculation unit 220, a second calculation unit 230, a linear transformation unit 240, and a model training unit 250. In particular, the method comprises the following steps of,
the processing unit 210 is configured to pass the face image to be detected in the set and the face image with the noise outside the set through a face recognition network to obtain corresponding face feature vectors; wherein, each person at least comprises a reference picture;
a first calculating unit 220 configured to calculate an indicative function according to the reference map feature of the ith person and the reference map features of the different persons;
a second calculation unit 230 configured to calculate a quality value of the kth chart of interest of the ith individual based on the indicative function;
a linear transformation unit 240 configured to perform linear transformation on the quality value to obtain a final label value of the kth image to be tested of the ith individual;
a model training unit 250 configured to perform face quality assessment model training using the final label value
The functions executed by each component in the face image quality scoring and labeling device provided by the embodiment of the invention are described in detail in the method, so that redundant description is not repeated here.
Corresponding to the above embodiments, the embodiment of the present invention further provides a facial image quality scoring and labeling system, specifically as shown in fig. 3, the system includes at least one processor 310 and a memory 220;
a memory 310 for storing one or more program instructions;
the processor 320 is configured to execute one or more program instructions to perform any method step in the method for labeling face image quality scores as described in the above embodiments.
Corresponding to the above embodiment, an embodiment of the present invention further provides a chip, where the chip is coupled with the memory in the system, so that the chip calls the program instruction stored in the memory when running, thereby implementing the method for scoring and labeling the face image quality introduced in the above embodiment.
In accordance with the foregoing embodiments, the present invention further provides a computer storage medium, which includes one or more programs, where the one or more program instructions are used to execute the above-described face image quality scoring and labeling method by a speech recognition system.
The method for marking the face image quality score comprehensively considers the intra-class distance and the inter-class distance of the face features and carries out a task of labeling face image training samples for a quality evaluation task. By applying the method, more accurate face image quality label values can be obtained, and a foundation is laid for better face quality evaluation networks for subsequent training. The label value is obtained by the features extracted by the deep learning network, so the method has high efficiency and low cost, and simultaneously considers the inter-class and intra-class distance influence of the face image, thereby ensuring more comprehensive evaluation.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied in hardware, a software module executed by a processor, or a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The above embodiments are provided to further explain the objects, technical solutions and advantages of the present invention in detail, it should be understood that the above embodiments are merely exemplary embodiments of the present invention and are not intended to limit the scope of the present invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A face image quality scoring and labeling method is characterized by comprising the following steps:
the face image to be detected in the set and the face image with the external noise are subjected to face recognition network to obtain corresponding face characteristic vectors; wherein, each person at least comprises a reference picture;
calculating an indicative function according to the reference map characteristics of the ith person and the reference map characteristics of other different persons;
calculating a quality value for the kth map of the ith individual based on the indicative function;
performing linear transformation on the quality value to obtain a final label value of the kth image to be tested of the ith person;
and performing face quality evaluation model training by using the final label value.
2. The method of claim 1, wherein the out-of-collection face and the in-collection face identities do not overlap.
3. The method of claim 1, wherein the feature vectors are normalized prior to computing the indicative function.
4. The method of claim 1, wherein the indicative function is calculated according to the formula:
wherein the content of the first and second substances,a reference map feature for the ith person;reference map features for other different persons; j ═ 1,2,. N + M-1; n is the number of people to be tested in the set, and M is the number of noise people outside the set; the vector inner product of the reference image feature of the ith person and the reference images of other different persons is recorded ast is a threshold constant.
5. The method of claim 1, wherein the quality value q of the kth map of the ith individual is calculated according to the following formula:
6. The method of claim 1, wherein the quality value q is linearly transformed according to the following equation: q (i, j) ═ w · Q + b, where w, b are constants.
7. A face image quality scoring and labeling device is characterized by comprising:
the processing unit is configured to enable the face image to be detected in the set and the face image with the external noise to pass through a face recognition network to obtain corresponding face characteristic vectors; wherein, each person at least comprises a reference picture;
a first calculation unit configured to calculate an indicative function based on the reference map feature of the ith person and the reference map features of the different persons;
a second calculation unit configured to calculate a quality value of the kth chart to be tested of the ith individual based on the indicative function;
the linear transformation unit is configured to perform linear transformation on the quality value to obtain a final label value of the kth image to be tested of the ith person;
and the model training unit is configured to perform face quality evaluation model training by using the final label value.
8. A face image quality scoring and labeling system is characterized by comprising at least one processor and a memory;
the memory to store one or more program instructions;
the processor, configured to execute one or more program instructions to perform the method according to one or more of claims 1 to 5.
9. A chip, characterized in that it is coupled to a memory in a system such that it, when run, invokes program instructions stored in said memory implementing the method according to one or more of claims 1 to 5.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium comprises one or more program instructions that are executable by the system of claim 8 to implement the method of one or more of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010822252.8A CN111967381B (en) | 2020-08-16 | 2020-08-16 | Face image quality grading and labeling method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010822252.8A CN111967381B (en) | 2020-08-16 | 2020-08-16 | Face image quality grading and labeling method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111967381A true CN111967381A (en) | 2020-11-20 |
CN111967381B CN111967381B (en) | 2022-11-11 |
Family
ID=73388178
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010822252.8A Active CN111967381B (en) | 2020-08-16 | 2020-08-16 | Face image quality grading and labeling method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111967381B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113139462A (en) * | 2021-04-23 | 2021-07-20 | 杭州魔点科技有限公司 | Unsupervised face image quality evaluation method, electronic device and storage medium |
CN113192028A (en) * | 2021-04-29 | 2021-07-30 | 北京的卢深视科技有限公司 | Quality evaluation method and device for face image, electronic equipment and storage medium |
CN117372405A (en) * | 2023-10-31 | 2024-01-09 | 神州通立电梯有限公司 | Face image quality evaluation method, device, storage medium and equipment |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107330397A (en) * | 2017-06-28 | 2017-11-07 | 苏州经贸职业技术学院 | A kind of pedestrian's recognition methods again based on large-spacing relative distance metric learning |
CN108235770A (en) * | 2017-12-29 | 2018-06-29 | 深圳前海达闼云端智能科技有限公司 | image identification method and cloud system |
CN109003266A (en) * | 2018-07-13 | 2018-12-14 | 中国科学院长春光学精密机械与物理研究所 | A method of based on fuzzy clustering statistical picture quality subjective evaluation result |
CN109241880A (en) * | 2018-08-22 | 2019-01-18 | 北京旷视科技有限公司 | Image processing method, image processing apparatus, computer readable storage medium |
CN111241925A (en) * | 2019-12-30 | 2020-06-05 | 新大陆数字技术股份有限公司 | Face quality evaluation method, system, electronic equipment and readable storage medium |
-
2020
- 2020-08-16 CN CN202010822252.8A patent/CN111967381B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107330397A (en) * | 2017-06-28 | 2017-11-07 | 苏州经贸职业技术学院 | A kind of pedestrian's recognition methods again based on large-spacing relative distance metric learning |
CN108235770A (en) * | 2017-12-29 | 2018-06-29 | 深圳前海达闼云端智能科技有限公司 | image identification method and cloud system |
CN109003266A (en) * | 2018-07-13 | 2018-12-14 | 中国科学院长春光学精密机械与物理研究所 | A method of based on fuzzy clustering statistical picture quality subjective evaluation result |
CN109241880A (en) * | 2018-08-22 | 2019-01-18 | 北京旷视科技有限公司 | Image processing method, image processing apparatus, computer readable storage medium |
CN111241925A (en) * | 2019-12-30 | 2020-06-05 | 新大陆数字技术股份有限公司 | Face quality evaluation method, system, electronic equipment and readable storage medium |
Non-Patent Citations (2)
Title |
---|
PHILIPP TERHORST等: "Face Quality Estimation and Its Correlation to Demographic and Non-Demographic Bias in Face Recognition", 《ARXIV:2004.01019V3[CS.CV]》 * |
PHILIPP TERHÖRST等: "SER-FIQ: Unsupervised Estimation of Face Image Quality Based on Stochastic Embedding Robustness", 《2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113139462A (en) * | 2021-04-23 | 2021-07-20 | 杭州魔点科技有限公司 | Unsupervised face image quality evaluation method, electronic device and storage medium |
CN113192028A (en) * | 2021-04-29 | 2021-07-30 | 北京的卢深视科技有限公司 | Quality evaluation method and device for face image, electronic equipment and storage medium |
CN113192028B (en) * | 2021-04-29 | 2022-05-31 | 合肥的卢深视科技有限公司 | Quality evaluation method and device for face image, electronic equipment and storage medium |
CN117372405A (en) * | 2023-10-31 | 2024-01-09 | 神州通立电梯有限公司 | Face image quality evaluation method, device, storage medium and equipment |
Also Published As
Publication number | Publication date |
---|---|
CN111967381B (en) | 2022-11-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111967381B (en) | Face image quality grading and labeling method and device | |
WO2020211339A1 (en) | Finger vein recognition method and apparatus, and computer device and storage medium | |
CN109255289B (en) | Cross-aging face recognition method based on unified generation model | |
CN108304820A (en) | A kind of method for detecting human face, device and terminal device | |
CN108154133B (en) | Face portrait-photo recognition method based on asymmetric joint learning | |
CN102737633A (en) | Method and device for recognizing speaker based on tensor subspace analysis | |
CN105005772A (en) | Video scene detection method | |
CN114359283A (en) | Defect detection method based on Transformer and electronic equipment | |
US10423817B2 (en) | Latent fingerprint ridge flow map improvement | |
CN111178252A (en) | Multi-feature fusion identity recognition method | |
CN114241505B (en) | Method and device for extracting chemical structure image, storage medium and electronic equipment | |
CN111401105B (en) | Video expression recognition method, device and equipment | |
CN116152870A (en) | Face recognition method, device, electronic equipment and computer readable storage medium | |
CN114722812A (en) | Method and system for analyzing vulnerability of multi-mode deep learning model | |
CN110874576B (en) | Pedestrian re-identification method based on typical correlation analysis fusion characteristics | |
CN108010015A (en) | One kind refers to vein video quality evaluation method and its system | |
CN114398611A (en) | Bimodal identity authentication method, device and storage medium | |
CN116153337B (en) | Synthetic voice tracing evidence obtaining method and device, electronic equipment and storage medium | |
Kumar et al. | Footprint recognition using modified sequential haar energy transform (MSHET) | |
CN116542912A (en) | Flexible body bridge vibration detection model with multi-target visual tracking function and application | |
CN110909678A (en) | Face recognition method and system based on width learning network feature extraction | |
RU2148274C1 (en) | Method for identification of person using properties of signature | |
CN107424141A (en) | A kind of face-image method for evaluating quality based on probability block | |
Bousquet et al. | Reliability criterion based on learning-phase entropy for speaker recognition with neural network. | |
Ahlawat et al. | Online invigilation: A holistic approach |
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 |