WO2017162076A1 - Face identification method and system - Google Patents

Abstract

A face identification method and system. The identification method comprises: constructing a face feature template library (S301), wherein the face feature template library is stored with face feature templates and basic user information of N users, and each of the users corresponds to at least one face feature template; extracting face features from a face image of a user to be identified, so as to obtain a face feature template to be identified (S302); calculating similarity levels of the face feature template to be identified with respect to the face feature templates of the respective users in the face feature template library, and finding a maximum value from highest similarity levels of the face feature template to be identified with respect to the respective users; determining whether the user is the user corresponding to said maximum value; and if not, then finding a maximum value from average similarity levels of the face feature template to be identified with respect to the respective users, and determining whether the user is the user corresponding to said maximum value. Compared with existing face identification methods, the method and system in the present invention can effectively improve accuracy of face identification.

Description

Face recognition method and system Technical field

The invention belongs to the field of biometrics, and particularly relates to a face recognition method and system.

Background technique

With the rapid development of the mobile Internet, biometrics technology has also received more and more attention. As the most natural biometric feature of interactive mode, face recognition technology has received extensive attention and attention, and its application prospects are very broad.

Face recognition is a very challenging research topic, especially for face recognition under unconstrained conditions. Under different lighting, posture, expression, age, makeup, etc., shooting the same person's face image is very different. How to effectively overcome the effects of these unfavorable factors is crucial for face recognition. In general, the impact of adverse factors on face recognition can be overcome in two ways. On the one hand, the feature extraction process of face recognition is optimized: appropriate features are extracted from the face image, which should be intra-class changes of the same person while effectively depicting the inter-class differences between different people (intra-class Difference) has strong stability; on the other hand, it optimizes the feature template matching process of face recognition: the feature templates of two or more sets of face images that need to be compared are input into an appropriate classifier for comparison, A good classifier can further expand the distance between different people's face feature templates, reduce the distance between different face image feature templates of the same person, and better discriminate whether the two sets of face images are from the same person. In the case that the feature extraction process has been perfected, the optimization feature template comparison process can still greatly improve the recognition accuracy of the entire face recognition system. According to the number of feature templates registered by each person in the face feature template library, the face recognition system can be divided into a single template comparison system and a multiple template comparison system. In general, the use of multiple template alignment techniques in a face recognition system can significantly improve recognition accuracy compared to a single template alignment system.

At present, there are mainly two technical solutions when using the multi-template comparison technology: one solution is to use the average similarity as the decision basis for the feature template comparison. For example, user A registers k feature templates X _A1 , X _A2 , . . . , X _Ak in the face recognition system, and the similarity between the feature template Y of the face image to be recognized and the k feature templates is S _{A1 .} , S _A2 ,...,S _Ak , calculate the average similarity S _A =(S _A1 +S _A2 +...+S _Ak )/k, if S _{A is} greater than or equal to the preset feature template comparison similarity threshold S ₀ It is judged that the user in the face image corresponding to Y is the same person as A; if S _{A is} smaller than the threshold S ₀ , it is judged that the user in the face image corresponding to Y is not the same person as A. The scheme averages the similarity of the multi-template alignment, and the distribution of the similarity after the average is more concentrated. It is easy to cause the FRY of the face recognition to increase compared with the single template. Another solution is to use maximum similarity as the basis for decision making of feature template comparisons. For example, suppose that the maximum value of the similarity S _A1 , S _A2 , . . . , S _Ak of the feature template Y of the face image to be recognized and the k feature templates is set to S _A , if S _{A is} greater than or equal to a preset The feature template compares the similarity threshold S ₀ , and determines that the user in the face image corresponding to Y is the same person as A; if S _{A is} smaller than the threshold S ₀ , it determines the user in the face image corresponding to Y A is not the same person. The similarity of the multi-template alignment is maximized. The maximum similarity of multiple template comparisons between different people will be more similar than the single template comparison. It is easier to misjudge different people. For the same person, the false positive rate of face recognition, that is, the false acceptance rate FAR rises when compared with the single template.

Summary of the invention

In view of the deficiencies in the prior art, an object of the present invention is to provide a face recognition method and system, by which the accuracy of face recognition can be effectively improved.

In order to achieve the above object, the technical solution adopted by the present invention is as follows:

A face recognition method includes the following steps:

(1) constructing a face feature template library, wherein the face feature template library stores N user face feature templates and user basic information, each user corresponding to at least one face feature template; wherein, N≥1;

(2) extracting facial features in the face image of the user to be identified, and obtaining a facial feature template to be recognized;

(3) performing identification of the user to be identified according to the face feature template to be identified and the face feature template library; and the manner of identifying the user to be identified includes:

1 respectively calculating the similarity between the face feature template to be recognized and each face feature template of each user in the face feature template library, and obtaining the maximum of each user in the face feature template and the face feature template library to be recognized. Similarity and average similarity;

The maximum similarity between the face feature template to be identified and a certain user is the maximum similarity between the similarity between the face feature template to be identified and all the face feature templates of the user; the face feature template to be recognized and The average similarity of a user refers to the face feature template to be identified and the user's location. The average of the similarities of the face feature templates;

The maximum similarities between the N-users in the face feature template and the face feature template library are S _Max1 , S _Max2 ,..., S _MaxN ; the face feature template to be recognized and the face feature template library The average similarity of users is recorded as S _Avg1 , S _Avg2 ,...,S _AvgN ;

2 Obtain the maximum value MAX _{Max in} S _Max1 , S _Max2 ,..., S _MaxN , and _judge according to the user's face feature template and the face feature template to be recognized in the face feature template library corresponding to the maximum value MAX _Max Whether the user to be identified is the user in the face feature template library corresponding to the maximum value MAX _Max , if yes, the recognition ends, and if not, proceeds to step 3;

3 Obtaining the maximum value AVG _{Max in} S _Avg1 , S _Avg2 , ..., S _AvgN , _judging according to the user's face feature template and the face feature template to be recognized in the face feature template library corresponding to the maximum AVG _Max Whether the user to be identified is the user in the face feature template library corresponding to the maximum value AVG _Max , and if so, the recognition ends, and if not, the recognition fails.

Further, in the face recognition method, in step 2 and step 3, according to the face feature template of a user in the face feature template library and the face feature template to be recognized, it is determined whether the user to be identified is a The way to describe a user includes:

There are k face feature templates for the user in the face feature template library, and the similarity between the face feature template and the k face feature template for the recognition is S _A1 , S _A2 , ..., S _Ak ;

1) Take the k similarities _{S A1, S A2, ...,} S Ak maximum similarity S _MaxA, k is calculated a similarity S _A1, S _A2, ..., S _Ak average value, the average similarity _S AvgA ;

2) determining whether the maximum similarity S _MaxA is greater than or equal to the preset maximum similarity threshold S _max , and if so, determining that the user to be identified is the user, and if not, proceeding to step 3);

3) judging whether k≥K _S is satisfied, if yes, proceeding to step 4), if not, determining that the user to be identified is not the user; wherein K _S is a positive integer, K _S >1;

4) determining whether the average similarity S _AvgA is greater than or equal to a preset average similarity threshold S _avg , and if yes, determining that the user to be identified is the user, and if not, determining that the user to be identified is not the user .

Further, in the face recognition method, in step 4), if the average similarity S _AvgA <S _avg , before the prompt recognition fails, the method further includes:

Taking the minimum similarity S _MinA in the k similarities S _A1 , S _A2 , . . . , S _Ak , determining whether the minimum similarity S _MinA is greater than or equal to a preset minimum similarity threshold S _min , and if yes, determining The user is identified as the user, and if not, it is determined that the user to be identified is not the user.

Further, in the method for recognizing a face, the method further includes the steps of determining the maximum similarity threshold S _max , the average similarity threshold S _{avg ,} and the minimum similarity threshold S _min , and the determining manner is:

a. Construct a face image test library, where the face image of the H person is stored in the test library, and the number of face images of each person is one;

b, randomly selecting J images from each person's face images to form a sub-library P, and all remaining images constitute a sub-bank G;

c. Divide the face image of each person in the sub-library G into K groups, and obtain an H×K group image;

d. For each image P′ in the H×J images in the sub-library P, the maximum similarity and minimum similarity of the image P′ and each group of images other than the user of the image P′ in the sub-bank G are calculated. Degree and average similarity, obtain H × J × (H-1) × K maximum similarities, H × J × (H-1) × K minimum similarities and H × J × (H-1) × K Average similarity;

e. Align the H×J×(H-1)×K maximum similarities, the minimum similarity, and the average similarity in descending order, and take H×J×(H-1)×K The maximum similarity between the position number and the ratio of H×J×(H-1)×K equal to the preset first misrecognition rate threshold is the maximum similarity threshold S _max ; taking H×J× (H-1) × K average similarities, the ratio of the position number to H × J × (H-1) × K is equal to the preset second misunderstanding rate threshold, and the average similarity is the average similarity threshold S _avg ; Taking the ratio of the position number of H×J×(H-1)×K minimum similarities to the ratio of H×J×(H-1)×K equal to the minimum similarity of the preset third misrecognition rate threshold is the minimum similarity Degree threshold S _min .

Further, in the face recognition method, in step e, the first misrecognition rate threshold, the second misrecognition rate threshold, and the third misrecognition rate threshold when N=1 are greater than the first when N>1, respectively. The false positive rate threshold, the second false positive rate threshold, and the third false positive rate threshold.

Further, the face recognition method described is H=1000, I=100, J=10, and K=9.

Further, in the face recognition method, when N=1, the first false positive rate threshold is 0.01%, the second false positive rate threshold is 0.01%, and the third false positive rate threshold is 0.01%; When >1, the first false positive rate threshold is 0.001%, the second false positive rate threshold is 0.001%, and the third false positive rate threshold is 0.001%.

The embodiment of the invention further provides a face recognition system, comprising:

a template library building module, configured to construct a face feature template library, where the face feature template library stores N user face feature templates and user basic information, and each user corresponds to at least one face feature template; N≥1;

a feature extraction module to be used for extracting a face feature in a face image of the user to be identified, and obtaining a face feature template to be recognized;

a face recognition module, configured to perform identification of the user to be identified according to the face feature template to be identified and the face feature template library; the face recognition module includes:

a first similarity calculation unit, configured to respectively calculate a similarity between the face feature template to be recognized and each face feature template of each user in the face feature template library, to obtain a face feature template and a face feature to be recognized The maximum similarity and average similarity of each user in the template library;

The maximum similarity between the face feature template to be identified and a certain user is the maximum similarity between the similarity between the face feature template to be identified and all the face feature templates of the user; the face feature template to be recognized and The average similarity of a certain user refers to an average value of the similarity between the face feature template to be identified and all the face feature templates of the user;

The maximum similarities between the N-users in the face feature template and the face feature template library are S _Max1 , S _Max2 ,..., S _MaxN ; the face feature template to be recognized and the face feature template library The average similarity of users is recorded as S _Avg1 , S _Avg2 ,...,S _AvgN ;

The first face recognition unit is configured to obtain a maximum value MAX _{Max in} S _Max1 , S _Max2 , . . . , S _MaxN , and a facial feature template of the user in the face feature template library corresponding to the maximum value MAX _Max The recognized face feature template determines whether the user to be identified is the user in the face feature template library corresponding to the maximum value MAX _Max , and if so, the recognition ends; if not, the second face recognition unit is entered;

a second face recognition unit, configured to acquire a maximum value AVG _{Max in} S _Avg1 , S _Avg2 , . . . , S _AvgN , according to a face feature template of the user in the face feature template library corresponding to the maximum value AVG _Max The recognized face feature template determines whether the user to be identified is the user in the face feature template library corresponding to the maximum value AVG _Max , and if so, the recognition ends, and if not, the recognition fails.

Further, in a face recognition system as described above, there are k face feature templates of the user in the face feature template library, and the face feature template to be recognized is similar to the k face feature template. The degrees are S _A1 , S _A2 , ..., S _Ak ;

The first face recognition unit and the second face recognition unit each include:

The average similarity calculating sub-unit, for taking the k similarities _{S A1, S A2, ...,} S Ak maximum similarity S _MaxA, k is calculated a similarity S _A1, S _A2, ..., the average value of S _Ak , get the average similarity S _AvgA ;

a first identifying subunit, configured to determine whether the maximum similarity S _MaxA is greater than or equal to a preset maximum similarity threshold S _max , and if yes, determining that the user to be identified is the user, and if not, entering the second identifier unit;

a second identification subunit, configured to determine whether k≥K _S is satisfied, and if yes, proceeds to step third identification subunit, and if not, determines that the user to be identified is not the user; wherein K _S is a positive integer, K _S >1;

a third identifying subunit, configured to determine whether the average similarity S _AvgA is greater than or equal to a preset average similarity threshold S _avg , and if yes, determining that the user to be identified is the user, and if not, determining that the user is to be identified The user is not the user.

Further, in a face recognition system as described above, the third identification subunit further includes:

Recognizing the sub-unit again, when the average similarity S _AvgA <S _avg is used, the identification of the user to be identified is performed again before the prompt recognition fails; the recognition manner is:

Taking the minimum similarity S _MinA in the k similarities S _A1 , S _A2 , . . . , S _Ak , determining whether the minimum similarity S _MinA is greater than or equal to a preset minimum similarity threshold S _min , and if yes, determining The user is identified as the user, and if not, it is determined that the user to be identified is not the user.

Further, a face recognition system as described above, the system further comprising:

a similarity threshold determining module, configured to determine the maximum similarity threshold S _max , an average similarity threshold S _{avg ,} and a minimum similarity threshold S _min ; the similarity confirmation module includes:

The test library building unit is configured to construct a face image test library, wherein the face image of the H person is stored in the test library, and the number of face images of each person is one;

a sub-library building unit for randomly selecting J images from each person's I face images to form a sub-library P, and all remaining images constitute a sub-library G;

a sub-library grouping unit, which divides a face image of each person in the sub-library G into K groups, and obtains an H×K group image;

a second similarity calculation unit, configured to calculate, for each image P′ in the H×J images in the sub-library P, each image of the image P′ and the sub-library G other than the user to which the image P′ belongs The maximum similarity, the minimum similarity and the average similarity are obtained as H × J × (H-1) × K maximum similarities, H × J × (H-1) × K minimum similarities and H × J × (H-1) × K average similarities;

a similarity threshold determining unit, configured to arrange the H×J×(H−1××K maximum similarities, the minimum similarity, and the average similarity in descending order, respectively, in an order of H×J×( H-1) × K maximum similarities, the ratio of the position number to H × J × (H-1) × K is equal to the preset first misrecognition rate threshold, the maximum similarity is the maximum similarity threshold S _max Taking the ratio of the position number of H×J×(H-1)×K average similarities to H×J×(H-1)×K equal to the average similarity of the preset second misrecognition rate threshold is average Similarity threshold S _avg ; taking H × J × (H-1) × K minimum similarities, the ratio of the position number to H × J × (H-1) × K is equal to the preset third misrecognition rate threshold The minimum similarity is the minimum similarity threshold S _min .

The invention has the beneficial effects that the face recognition method provided by the present invention comprehensively utilizes the maximum similarity and average similarity between the face feature template to be recognized and the face feature template of the user in the template library, or the maximum similarity. Degree, average similarity and minimum similarity multiple reference factors can effectively improve the accuracy of face recognition compared with existing face recognition methods.

DRAWINGS

1 is a flowchart of a face recognition method according to Embodiment 1 of the present invention;

2 is a flowchart of determining whether a user to be identified is a user in a feature template library according to Embodiment 2 of the present invention;

3 is a flowchart of a face recognition method according to Embodiment 3 of the present invention;

4 is a structural block diagram of a face recognition system according to Embodiment 6 of the present invention.

detailed description

The present invention will be further described in detail below in conjunction with the drawings and specific embodiments.

Embodiment 1

FIG. 1 is a flowchart of a face recognition method provided in this embodiment. As can be seen from the figure, the method may include the following steps:

Step S101: construct a face feature template library;

Firstly, a face feature template library for face recognition is constructed, and the feature library is used for storing basic information of the user and face feature information.

In this embodiment, the existing facial feature extraction algorithm is used to extract the facial features of the user's face image, for example, the deep neural network algorithm is used to extract the facial features, and the extracted user facial features are used as follow-up purposes. The face feature template identifying the user is stored in the template library.

In this embodiment, the face feature template library stores N user face feature templates and user basic information (user name and other information), and each user corresponds to at least one face feature template; wherein, N≥ 1. The number of face feature templates for different users can be different.

Step S102: Extract a face feature in a face image of the user to be identified, and obtain a face feature template to be identified;

When performing face recognition, for the user to be identified, the face image of the user to be recognized is first acquired, and the image is generally collected in real time, or may be an existing face image (for characters in the existing face image) The recognition is performed), and then the facial features in the image of the user's face to be recognized are extracted, and the facial feature template to be recognized is obtained. The manner of extracting the face features of the user to be recognized is the same as the manner of extracting the face features when constructing the template library in step S101.

Step S103: Perform identification of the user to be identified according to the face feature template to be identified and the face feature template library.

After obtaining the face feature template to be identified, according to the face feature template and step to be recognized The face feature template library constructed in step S101 performs identification of the user to be identified. In this embodiment, the identification manner of the user to be identified is as shown in FIG. 1 , and includes the following steps:

1 respectively calculating the similarity between the face feature template to be recognized and each face feature template of each user in the face feature template library, and obtaining the maximum of each user in the face feature template and the face feature template library to be recognized. Similarity and average similarity;

The maximum similarity between the face feature template to be identified and a certain user refers to the maximum similarity between the similarity between the face feature template to be identified and all the face feature templates of the user; the face feature to be recognized The average similarity between the template and a certain user refers to the average of the similarity between the face feature template to be identified and all the face feature templates of the user.

For example, the face feature template library includes two users, user A and user B. The template library user A corresponds to two face feature templates, and user B corresponds to three face feature templates, and the face feature templates to be recognized are respectively calculated. The similarity between the two face feature templates of user A. The larger of the two similarities is the maximum similarity between the face feature template to be identified and the user A. The average of the two similarities is the person to be identified. The average similarity between the face feature template and user A. Similarly, the maximum value of the similarity between the face feature template to be identified and the three face feature templates of the user B is the maximum similarity between the face feature template to be recognized and the user B, and the average of the three similarities is The average similarity between the face feature template to be identified and the user B.

The similarity of the two face template features is calculated by using the existing calculation method. For example, the similarity between the two face feature templates can be calculated by using the cosine similarity.

In this embodiment, the maximum similarities of the N face users in the face feature template and the face feature template library are S _Max1 , S _Max2 , . . . , S _{MaxN respectively} ; the face feature template and the face to be recognized are respectively The average similarity of N users in the feature template library is recorded as S _Avg1 , S _Avg2 , ..., S _AvgN , _respectively .

2 Obtain the maximum value MAX _{Max in} S _Max1 , S _Max2 ,..., S _MaxN , and _judge according to the user's face feature template and the face feature template to be recognized in the face feature template library corresponding to the maximum value MAX _Max Whether the user to be identified is the user in the face feature template library corresponding to the maximum value MAX _Max , if yes, the recognition ends, and if not, proceeds to step 3;

3 Obtaining the maximum value AVG _{Max in} S _Avg1 , S _Avg2 , ..., S _AvgN , _judging according to the user's face feature template and the face feature template to be recognized in the face feature template library corresponding to the maximum AVG _Max Whether the user to be identified is the user in the face feature template library corresponding to the maximum value AVG _Max , and if so, the recognition ends, and if not, the recognition fails.

The face recognition method in this embodiment first calculates the similarity between the face feature template of the user to be identified and each face feature template of each user in the template library, and obtains the face feature template to be identified and each The maximum similarity of the user is determined by selecting a maximum of the plurality of maximum similarities, and identifying the user to be identified based on the facial feature template in the template library of the user corresponding to the maximum value of the maximum similarity. If the user cannot be identified by the facial feature template in the template library of the user corresponding to the maximum value, and according to the average similarity of each facial feature template to each user, the maximum value among the multiple average similarities is obtained. The face feature template in the corresponding user's template library is recognized again.

In step 2 and step 3, after the maximum value MAX _Max and the maximum value AVG _{Max are obtained} , the face feature template of the user and the face feature to be recognized in the face feature template library corresponding to the maximum value MAX _Max are obtained. The manner in which the template is to be recognized by the user to be identified, or the method of identifying the user to be recognized according to the face feature template of the user in the face feature template library corresponding to the maximum AVG _Max and the face feature template to be recognized may be used. Some face recognition methods are implemented.

Embodiment 2

The difference between this embodiment and the first embodiment is that after the maximum value MAX _Max is obtained in step 2 or after the AVG _Max is acquired in step 3, the embodiment further provides a maximum value MAX _Max . The face feature template of the user and the face feature template to be recognized in the corresponding face feature template library are used to identify the user to be recognized or the face feature template of the user in the face feature template library corresponding to the maximum AVG _Max And the manner of identifying the user to be recognized by the face feature template to be identified.

In this embodiment, according to the face feature template of a user in the face feature template library and the face feature template to be identified, the manner of determining whether the user to be identified is the user is as shown in FIG. 2, and includes the following Steps:

There are k face feature templates for the user in the face feature template library, and the similarity between the face feature template and the k face feature template for the recognition is S _A1 , S _A2 , ..., S _Ak ;

1) Take the k similarities _{S A1, S A2, ...,} S Ak maximum similarity S _MaxA, k is calculated a similarity S _A1, S _A2, ..., S _Ak average value, the average similarity _S AvgA ;

2) determining whether the maximum similarity S _MaxA is greater than or equal to the preset maximum similarity threshold S _max , and if so, determining that the user to be identified is the user, and if not, proceeding to step 3);

3) judging whether k≥K _S is satisfied, if yes, proceeding to step 4), if not, determining that the user to be identified is not the user; wherein K _S is a positive integer, K _S >1, for example, K _S =3 ;

4) determining whether the average similarity S _AvgA is greater than or equal to a preset average similarity threshold S _avg , and if yes, determining that the user to be identified is the user, and if not, determining that the user to be identified is not the user .

For step 2, the user is the user in the face feature template library corresponding to the maximum value MAX _Max . For step 3, the user is the user in the face feature template library corresponding to the maximum value AVG _Max .

Embodiment 3

FIG. 3 is a flowchart of a method for recognizing a face provided in this embodiment. The method in this embodiment of China may include the following steps:

Step S301: construct a face feature template library;

Step S302: Extract a face feature in a face image of the user to be identified, and obtain a face feature template to be identified;

The specific manner of constructing the face feature template library in step S301 in the embodiment and the face feature in the face image of the user to be recognized in step S302, and obtaining the face feature template to be recognized, and the first embodiment The manner of constructing the face feature template library in step S101 described in the same manner as the step S102 of obtaining the face feature template to be recognized is the same.

Step S303: Perform identification of the user to be identified according to the face feature template to be identified and the face feature template library.

In this embodiment, the specific manner of performing the identification of the user to be identified according to the face feature template to be identified and the constructed face feature template library includes the following steps:

1 respectively calculating the similarity between the face feature template to be recognized and each face feature template of each user in the face feature template library, and obtaining the maximum of each user in the face feature template and the face feature template library to be recognized. Similarity and average similarity;

Similarly, the maximum similarity between the face feature template to be identified and a certain user refers to the maximum similarity between the similarity between the face feature template to be identified and all the face feature templates of the user; the face feature to be recognized The average similarity between the template and a certain user refers to the average of the similarity between the face feature template to be identified and all the face feature templates of the user.

In this embodiment, the maximum similarity between the face feature template and the face feature template library in the face feature template library are respectively S _Max1 , S _Max2 , . . . , S _MaxN ; the face feature template to be recognized and the person The average similarity of N users in the face feature template library is recorded as S _Avg1 , S _Avg2 , ..., S _AvgN , _respectively .

② acquisition S _Max1, S _Max2, ..., MAX _Max S _MaxN maximum value of the maximum value MAX _Max and corresponding facial feature template library users, and the person to be identified with the face feature pattern of the maximum value MAX _Max Corresponding the similarity of the user's face feature template in the face feature template library, determining whether the user to be identified is the user in the face feature template library corresponding to the maximum value MAX _Max , and if so, the recognition ends, if not, Then proceed to step 3;

In this embodiment, the face feature template of the user in the face feature template library corresponding to the maximum value MAX _Max has k ₁ , and the face feature template to be recognized and k ₁ person The similarity of the face feature templates are S _A1 , S _A2 , . . . , S _Ak1 ; respectively, and the specific manner of determining whether the user to be identified is the user in the face feature template library corresponding to the maximum value MAX _Max is as shown in FIG. 3 . Includes the following steps:

i, k ₁ th take similarities _{S A1, S A2, ...,} S Ak1 maximum similarity S _MaxA, calculate k ₁ th similarity S _A1, S _A2, ..., S _Ak1 average, the average similarity S _AvgA ;

Ii. Determine whether the maximum similarity S _MaxA is greater than or equal to a preset maximum similarity threshold S _max , and if yes, determine that the user to be identified is a user in the face feature template library corresponding to MAX _Max , and if not, proceed to the step Iii;

Iii, determining whether k ₁ ≥ K _S is satisfied, if yes, proceeding to step iv, if not, determining that the user to be identified is not a user in the face feature template library corresponding to MAX _Max , and proceeding to step 3; wherein, K _S Is a positive integer, K _S >1;

Iv, determining whether the average similarity S _AvgA is greater than or equal to a preset average similarity threshold S _avg , and if yes, determining that the user to be identified is a user in the face feature template library corresponding to MAX _Max , and if not, Go to step v;

v, k ₁ th take similarities S _A1, S _A2, ..., S _Ak1 whether the minimum degree of similarity S _MinA, S _MinA determining the minimum degree of similarity equal to or greater than a preset minimum similarity threshold S _min, and if yes, Then, the user to be identified is the user in the face feature template library corresponding to the MAX _Max . If not, the user to be identified is not the user in the face feature template library corresponding to the MAX _Max , and the process proceeds to step 3.

③ Get _S Avg1, S Avg2, ..., _{AVG Max} S AvgN maximum value and the maximum value of AVG _Max corresponding facial feature template library users, and the person to be recognized face feature pattern and the maximum value of the AVG _Max Corresponding the similarity degree of the user's face feature template in the face feature template library, determining whether the user to be identified is the user in the face feature template library corresponding to the maximum value AVG _Max , and if so, the recognition ends, if not, Then the prompt identification fails;

In this embodiment, the manner of determining whether the user to be identified is the user in the face feature template library corresponding to the maximum value AVG _Max and the face feature template corresponding to determining whether the user to be identified is the maximum value MAX _{Max in} the above step 2 The users in the library are in the same way, as follows:

Let the user in the face feature template library corresponding to the maximum AVG _Max have k ₂ face feature templates in the face feature template library, and the face feature template to be recognized is similar to the k ₂ face feature template. The degrees are S _A1 , S _A2 ,..., S _Ak2 ;

I, taken k ₂ th similarity _{S A1, S A2, ...,} S Ak2 maximum similarity _S MaxB, calculate k ₁ th similarity S _A1, S _A2, ..., S _Ak2 average, the average similarity S _AvgB ;

II. Determine whether the maximum similarity S _MaxB is greater than or equal to a preset maximum similarity threshold S _max , and if yes, determine that the user to be identified is a user in the facial feature template library corresponding to AVG _Max , and if not, proceed to the step III;

III. Determine whether k ₂ ≥ K _S is satisfied. If yes, proceed to step IV. If not, determine that the user to be identified is not a user in the face feature template library corresponding to AVG _Max , and prompt recognition failure; wherein, K _S Is a positive integer, K _S >1;

IV. Determine whether the average similarity S _AvgB is greater than or equal to a preset average similarity threshold S _avg , and if yes, determine that the user to be identified is a user in the face feature template library corresponding to AVG _Max , and if not, Go to step V;

V, k ₂ th take similarities _{S A1, S A2, ...,} S Ak2 _S MinB the minimum degree of similarity, determining the minimum degree of similarity is greater than or equal to _S MinB preset minimum similarity threshold S _min, and if yes, Then, the user to be identified is the user in the face feature template library corresponding to the AVG _Max . If not, the user to be identified is not the user in the face feature template library corresponding to the AVG _Max , and the recognition fails.

Embodiment 4

The face recognition method provided in this embodiment is a flowchart for using the method described in Embodiment 3 for a 1:1 face verification system, wherein 1:1 refers to only storing in the face feature template library. A user's face feature template, ie N=1.

In this embodiment, the R facial feature template of the user A is stored in the face feature template library, and the R personal face feature templates are respectively recorded as feature templates X _A1 , X _A2 , . . . , X _AR , to be identified by the user to be identified. The face feature template is recorded as the feature template Y. K _S is 3.

The face recognition method in this embodiment can be simplified into the following steps:

Step 1: Calculate the similarity between the feature template Y and the R feature templates X _A1 , X _A2 , . . . , X _AR respectively. The R similarities are respectively recorded as S _A1 , S _A2 , . . . , S _AR , and the maximum similarity is taken. The degree is recorded as SMax _A =max(S _A1 , S _A2 ,...,S _AR ), and the minimum similarity is recorded as SMin _A =min(S _A1 ,S _A2 ,...,S _AR ), and the average similarity SAvg is calculated. _A = (S _A1 + S _A2 +... + S _AR ) / R;

Step 2: determining whether SMax _A is greater than or equal to the preset maximum similarity threshold S _max , and if so, determining that the user to be identified corresponding to the feature template Y is the same person as the user A, and if not, proceeding to step 3;

Step 3: Determine whether R≥3 is satisfied. If yes, proceed to step 4. If the user to be identified corresponding to the judgment feature template Y is not the same person as the user A, the prompt recognition fails.

Step 4: Determine whether SAvg _A is greater than or equal to the preset average similarity threshold S _avg , and if so, determine that the user to be identified corresponding to the feature template Y is the same person as the user A, and if not, proceed to step 5;

Step 5: Determine whether the SMin _A is greater than or equal to the preset minimum similarity threshold. If yes, determine that the user to be identified corresponding to the feature template Y is the same person as the user A. If not, determine the user to be identified corresponding to the feature template Y. The user is not the same person as User A, and the prompt recognition fails.

Embodiment 5

The maximum similarity threshold S _max , the average similarity threshold S _avg , and the minimum similarity threshold S _min in the first embodiment, the second embodiment, the third embodiment, and the fourth embodiment may be directly applied according to the application scenario. Set directly to the experience value by the user.

In this embodiment, a method for determining the maximum similarity threshold S _max , the average similarity threshold S _{avg ,} and the minimum similarity threshold S _min is provided, and the manner includes the following steps:

a. Construct a face image test library, where the face image of the H person is stored in the test library, and the number of face images of each person is one;

b, randomly selecting J images from each person's face images to form a sub-library P, and all remaining images constitute a sub-bank G;

c. Divide the face image of each person in the sub-library G into K groups, and obtain an H×K group image;

d. For each image P′ in the H×J images in the sub-library P, the maximum similarity and minimum similarity of the image P′ and each group of images other than the user of the image P′ in the sub-bank G are calculated. Degree and average similarity, obtain H × J × (H-1) × K maximum similarities, H × J × (H-1) × K minimum similarities and H × J × (H-1) × K Average similarity;

e. Align the H×J×(H-1)×K maximum similarities, the minimum similarity, and the average similarity in descending order, and take H×J×(H-1)×K The maximum similarity between the position number and the ratio of H×J×(H-1)×K equal to the preset first misrecognition rate threshold is the maximum similarity threshold S _max ; taking H×J× (H-1) × K average similarities, the ratio of the position number to H × J × (H-1) × K is equal to the preset second misunderstanding rate threshold, and the average similarity is the average similarity threshold S _avg ; Taking the ratio of the position number of H×J×(H-1)×K minimum similarities to the ratio of H×J×(H-1)×K equal to the minimum similarity of the preset third misrecognition rate threshold is the minimum similarity Degree threshold S _min .

In order to further improve the recognition accuracy, in step e, the first false positive rate threshold, the second false positive rate threshold, and the third false positive rate threshold when N=1 are respectively greater than the first false positive rate threshold when N>1, The second false positive rate threshold and the third false positive rate threshold. The first erroneous rate threshold, the second erroneous rate threshold, and the third erroneous rate threshold may be set to the same value or may be set to different values.

The size of the test library is also as large as possible. In this embodiment, H=1000, I=100, J=10, and K=9 can be used. When N=1, the first false alarm rate threshold can be set to 0.01%, the second false positive rate threshold can be set to 0.01%, the third false positive rate threshold can be set to 0.01%; when N>1, the first false positive rate threshold can be set to 0.001%, the second false positive rate The threshold can be set to 0.001%, the first The three false alarm rate threshold can be set to 0.001%.

Using the above data provided in this embodiment, a test library of 100 face images of 100 faces per person for a total of 100,000 face images can be constructed. 10 sub-databases P constituting a total of 10,000 face images are randomly selected from each of the 100 face images, and the remaining 90,000 face images constitute a sub-library G, and 90 of each of the sub-libraries G The face images are evenly divided into 9 groups, which are divided into 9×1000 groups. First, the maximum similarity, the minimum similarity, and the average similarity between each face image in the sub-database P and each group of face images in the sub-bank G are calculated separately (the maximum similarity between an image and a group of images) Degree refers to the maximum value of the similarity between the image and each image in a group of images), which gives 10,000 × 9 × 1000 = 90 million maximum similarities, 90 million minimum similarities and 90 million averages Similarity, wherein the similarity among the 90 million similarities belongs to the same user (when the similarity is calculated, the image in the sub-database P and the image group in the sub-database G belong to the same user) 1000×10×9=9 10,000, therefore, 90.000 million of the 90 million similarities do not belong to the same user, respectively, the maximum similarity of 89.91 million, the minimum similarity of 89.91 million, and the average similarity of 89.91 million are in descending order Arranged, for the 1:1 (N=1) face verification system, the maximum similarity between the ranked position number and the 89.91 million ratio equal to 0.01% is determined as the maximum similarity threshold S _max , and the position number will be ranked The minimum similarity with a ratio of 89.91 million equal to 0.01% is determined to be the minimum similarity After the threshold value S _min, will line up with the position number 89910000 ratio is equal to 0.01% average similarity is determined as the average similarity threshold S _avg, the second row is about 8991 after the maximum similarity in good order, the minimum similarity 8991 The average similarity with the 8991th is determined as the maximum similarity threshold, the minimum similarity threshold, and the average similarity threshold respectively; similarly, for the 1:N (N>1) face search system, the 899th order will be ranked. The maximum similarity is set to the maximum similarity threshold, the 899th minimum similarity is set as the minimum similarity threshold, and the 889th average similarity is set as the average similarity threshold.

Embodiment 6

FIG. 4 is a structural block diagram of a face recognition system provided in this embodiment. As can be seen from the figure, the system includes a template library establishment module 100, a similarity threshold determination module 200, and a feature extraction module 300 to be verified. And a face recognition module 400. among them,

The template library building module 100 is configured to construct a face feature template library, where the face feature template library stores N user face feature templates and user basic information, and each user corresponds to at least one face feature template; , N≥1;

The to-be-verified feature extraction module 300 is configured to extract a facial feature in a face image of the user to be identified, and obtain a facial feature template to be identified;

The face recognition module 400 is configured to perform identification of the user to be identified according to the face feature template to be recognized and the face feature template library; the face recognition module 400 includes a first similarity calculation unit 401 The first face recognition unit 402 and the second face recognition unit 403. among them:

The first similarity calculation unit 401 is configured to separately calculate the similarity between the face feature template to be recognized and each face feature template of each user in the face feature template library, and obtain the face feature template and the face to be recognized. The maximum similarity and average similarity of each user in the feature template library;

The maximum similarity between the face feature template to be identified and a certain user is the maximum similarity between the similarity between the face feature template to be identified and all the face feature templates of the user; the face feature template to be recognized and The average similarity of a certain user refers to an average value of the similarity between the face feature template to be identified and all the face feature templates of the user;

The maximum similarities between the N-users in the face feature template and the face feature template library are S _Max1 , S _Max2 ,..., S _MaxN ; the face feature template to be recognized and the face feature template library The average similarity of users is recorded as S _Avg1 , S _Avg2 ,...,S _AvgN ;

The first face recognition unit 402 is configured to obtain a maximum value MAX _{Max in} S _Max1 , S _Max2 , . . . , S _MaxN , according to a face feature template of the user in the face feature template library corresponding to the maximum value MAX _Max a face feature template to be identified, determining whether the user to be identified is a user in the face feature template library corresponding to the maximum value MAX _Max , and if so, the recognition ends; if not, entering the second face recognition unit;

a second face recognition unit 403, configured to acquire a maximum value AVG _{Max in} S _Avg1 , S _Avg2 , . . . , S _AvgN , according to a face feature template of the user in the face feature template library corresponding to the maximum value AVG _Max The face feature template to be identified determines whether the user to be identified is the user in the face feature template library corresponding to the maximum value AVG _Max , and if so, the recognition ends, and if not, the recognition fails.

In this embodiment, the first face recognition unit 402 and the second face recognition unit 403 each include an average similarity calculation subunit, a first identification subunit, a second identification subunit, and a third identification subunit. There are k face feature templates for the user in the face feature template library, and the similarity between the face feature template and the k face feature template for the recognition is S _A1 , S _A2 , ..., S _Ak . among them,

The average similarity calculating sub-unit, for taking the k similarities _{S A1, S A2, ...,} S Ak maximum similarity S _MaxA, k is calculated a similarity S _A1, S _A2, ..., the average value of S _Ak , get the average similarity S _AvgA ;

a first identifying subunit, configured to determine whether the maximum similarity S _MaxA is greater than or equal to a preset maximum similarity threshold S _max , and if yes, determining that the user to be identified is the user, and if not, entering the second identifier unit;

a second identification subunit, configured to determine whether k≥K _S is satisfied; if yes, proceed to step third identification subunit, if not, determine that the user to be identified is not the user, and prompt identification failure; wherein, K _S Is a positive integer, K _S >1;

a third identifying subunit, configured to determine whether the average similarity S _AvgA is greater than or equal to a preset average similarity threshold S _avg , and if yes, determining that the user to be identified is the user, and if not, prompting the identification to fail .

In this embodiment, the third identifier subunit may further include:

Recognizing the sub-unit again, when the average similarity S _AvgA <S _avg is used, the identification of the user to be identified is performed again before the prompt recognition fails; the recognition manner is:

Taking the minimum similarity S _MinA in the k similarities S _A1 , S _A2 , . . . , S _Ak , determining whether the minimum similarity S _MinA is greater than or equal to a preset minimum similarity threshold S _min , and if yes, determining The user is identified as the user, and if not, the recognition fails.

In this embodiment, the face recognition system may further include:

The similarity threshold determining module 200 is configured to determine the maximum similarity threshold S _max , the average similarity threshold S _{avg ,} and the minimum similarity threshold S _min .

In this embodiment, the similarity confirmation module 200 may include a test library construction unit 201, a sub-library construction unit 202, a sub-library grouping unit 203, a second similarity calculation unit 204, and a similarity threshold determination unit 205. among them:

The test library construction unit 201 is configured to construct a face image test library, where the face image of the H person is stored in the test library, and the number of face images of each person is one;

The sub-library building unit 202 is configured to randomly select J images from each of the I face images to form a sub-library P, and all the remaining images constitute a sub-library G;

The sub-library grouping unit 203 divides the face image of each person in the sub-library G into K groups, and obtains H. ×K group image;

The second similarity calculation unit 204 is configured to calculate, for each image P′ in the H×J images in the sub-library P, each set of images other than the user of the image P′ in the sub-library G The maximum similarity, minimum similarity and average similarity of the image are obtained as H×J×(H-1)×K maximum similarities, H×J×(H-1)×K minimum similarities and H×J ×(H-1)×K average similarities;

The similarity threshold determining unit 205 is configured to arrange the H×J×(H−1××K maximum similarities, the minimum similarity, and the average similarity in descending order, respectively, in an order of H×J× (H-1)×K maximum similarities, the ratio of the position number to H×J×(H-1)×K is equal to the maximum similarity of the preset first misrecognition rate threshold is the maximum similarity threshold S _Max ; taking H×J×(H-1)×K average similarities, the ratio of the position number to H×J×(H-1)×K is equal to the preset second misunderstanding rate threshold, the average similarity is The average similarity threshold S _avg ; taking H × J × (H-1) × K minimum similarities, the ratio of the position number to H × J × (H-1) × K is equal to the preset third misrecognition rate threshold The minimum similarity is the minimum similarity threshold S _min .

It is apparent that those skilled in the art can make various modifications and variations to the invention without departing from the spirit and scope of the invention. Thus, it is intended that the present invention cover the modifications and the modifications

Claims (11)

1. A face recognition method includes the following steps:

   (1) constructing a face feature template library, wherein the face feature template library stores N user face feature templates and user basic information, each user corresponding to at least one face feature template; wherein, N≥1;

   (2) extracting facial features in the face image of the user to be identified, and obtaining a facial feature template to be recognized;

   (3) performing identification of the user to be identified according to the face feature template to be identified and the face feature template library; and the manner of identifying the user to be identified includes:

   1 respectively calculating the similarity between the face feature template to be recognized and each face feature template of each user in the face feature template library, and obtaining the maximum of each user in the face feature template and the face feature template library to be recognized. Similarity and average similarity;

   The maximum similarity between the face feature template to be identified and a certain user is the maximum similarity between the similarity between the face feature template to be identified and all the face feature templates of the user; the face feature template to be recognized and The average similarity of a certain user refers to an average value of the similarity between the face feature template to be identified and all the face feature templates of the user;

   The maximum similarities between the N-users in the face feature template and the face feature template library are S _Max1 , S _Max2 ,..., S _MaxN ; the face feature template to be recognized and the face feature template library The average similarity of users is recorded as S _Avg1 , S _Avg2 ,...,S _AvgN ;

   2 Obtain the maximum value MAX _{Max in} S _Max1 , S _Max2 ,..., S _MaxN , and _judge according to the user's face feature template and the face feature template to be recognized in the face feature template library corresponding to the maximum value MAX _Max Whether the user to be identified is the user in the face feature template library corresponding to the maximum value MAX _Max , if yes, the recognition ends, and if not, proceeds to step 3;

   3 Obtaining the maximum value AVG _{Max in} S _Avg1 , S _Avg2 , ..., S _AvgN , _judging according to the user's face feature template and the face feature template to be recognized in the face feature template library corresponding to the maximum AVG _Max Whether the user to be identified is the user in the face feature template library corresponding to the maximum value AVG _Max , and if so, the recognition ends, and if not, the recognition fails.
2. The method for recognizing a face according to claim 1, wherein in step 2 and step 3, judging according to a face feature template of a user in the face feature template library and a face feature template to be recognized Whether the user to be identified is the user or not includes:

   There are k face feature templates for the user in the face feature template library, and the similarity between the face feature template and the k face feature template for the recognition is S _A1 , S _A2 , ..., S _Ak ;

   1) Take the k similarities _{S A1, S A2, ...,} S Ak maximum similarity S _MaxA, k is calculated a similarity S _A1, S _A2, ..., S _Ak average value, the average similarity _S AvgA ;

   2) determining whether the maximum similarity S _MaxA is greater than or equal to the preset maximum similarity threshold S _max , and if so, determining that the user to be identified is the user, and if not, proceeding to step 3);

   3) judging whether k ≥ K _S is satisfied, if yes, proceeding to step 4), if not, determining that the user to be identified is not the user; wherein K _S is a positive integer, K _S >1;

   4) determining whether the average similarity S _AvgA is greater than or equal to a preset average similarity threshold S _avg , and if yes, determining that the user to be identified is the user, and if not, determining that the user to be identified is not the user .
3. The face recognition method according to claim 2, wherein in step 4), if the average similarity S _AvgA <S _avg , before determining that the user to be identified is not the user, the method further comprises:

   Taking the minimum similarity S _MinA in the k similarities S _A1 , S _A2 , . . . , S _Ak , determining whether the minimum similarity S _MinA is greater than or equal to a preset minimum similarity threshold S _min , and if yes, determining The user is identified as the user, and if not, it is determined that the user to be identified is not the user.
4. A face recognition method according to claim 3, characterized in that the method further comprises the steps of determining the maximum similarity threshold S _max , the average similarity threshold S _avg and the minimum similarity threshold S _min , determining the manner for:

   a. Construct a face image test library, where the face image of the H person is stored in the test library, and the number of face images of each person is one;

   b, randomly selecting J images from each person's face images to form a sub-library P, and all remaining images constitute a sub-bank G;

   c. Divide the face image of each person in the sub-library G into K groups, and obtain an H×K group image;

   d. For each image P′ in the H×J images in the sub-library P, the maximum similarity and minimum similarity of the image P′ and each group of images other than the user of the image P′ in the sub-bank G are calculated. Degree and average similarity, obtain H × J × (H-1) × K maximum similarities, H × J × (H-1) × K minimum similarities and H × J × (H-1) × K Average similarity;

   e. Align the H×J×(H-1)×K maximum similarities, the minimum similarity, and the average similarity in descending order, and take H×J×(H-1)×K The maximum similarity between the position number and the ratio of H×J×(H-1)×K equal to the preset first misrecognition rate threshold is the maximum similarity threshold S _max ; taking H×J× (H-1) × K average similarities, the ratio of the position number to H × J × (H-1) × K is equal to the preset second misunderstanding rate threshold, and the average similarity is the average similarity threshold S _avg ; Taking the ratio of the position number of H×J×(H-1)×K minimum similarities to the ratio of H×J×(H-1)×K equal to the minimum similarity of the preset third misrecognition rate threshold is the minimum similarity Degree threshold S _min .
5. The face recognition method according to claim 4, wherein in step e, the first false positive rate threshold, the second false positive rate threshold, and the third false positive rate threshold are respectively greater than N when N=1; The first false positive rate threshold, the second false positive rate threshold, and the third false positive rate threshold of >1.
6. A face recognition method according to claim 4 or 5, characterized in that H = 1000, I = 100, J = 10, and K = 9.
7. A face recognition method according to claim 6, wherein when N=1, the first false positive rate threshold is 0.01%, the second false positive rate threshold is 0.01%, and the third false positive rate threshold is It is 0.01%; when N>1, the first false positive rate threshold is 0.001%, the second false positive rate threshold is 0.001%, and the third false positive rate threshold is 0.001%.
8. A face recognition system comprising:

   a template library building module, configured to construct a face feature template library, where the face feature template library stores N user face feature templates and user basic information, and each user corresponds to at least one face feature template; N≥1;

   a feature extraction module to be used for extracting a face feature in a face image of the user to be identified, and obtaining a face feature template to be recognized;

   a face recognition module, configured to perform identification of the user to be identified according to the face feature template to be identified and the face feature template library; the face recognition module includes:

   a first similarity calculation unit, configured to respectively calculate a similarity between the face feature template to be recognized and each face feature template of each user in the face feature template library, to obtain a face feature template and a face feature to be recognized The maximum similarity and average similarity of each user in the template library;

   The maximum similarity between the face feature template to be identified and a certain user is the maximum similarity between the similarity between the face feature template to be identified and all the face feature templates of the user; the face feature template to be recognized and The average similarity of a certain user refers to an average value of the similarity between the face feature template to be identified and all the face feature templates of the user;

   The maximum similarities between the N-users in the face feature template and the face feature template library are S _Max1 , S _Max2 ,..., S _MaxN ; the face feature template to be recognized and the face feature template library The average similarity of users is recorded as S _Avg1 , S _Avg2 ,...,S _AvgN ;

   The first face recognition unit is configured to obtain a maximum value MAX _{Max in} S _Max1 , S _Max2 , . . . , S _MaxN , and a facial feature template of the user in the face feature template library corresponding to the maximum value MAX _Max The recognized face feature template determines whether the user to be identified is the user in the face feature template library corresponding to the maximum value MAX _Max , and if so, the recognition ends; if not, the second face recognition unit is entered;

   a second face recognition unit, configured to acquire a maximum value AVG _{Max in} S _Avg1 , S _Avg2 , . . . , S _AvgN , according to a face feature template of the user in the face feature template library corresponding to the maximum value AVG _Max The recognized face feature template determines whether the user to be identified is the user in the face feature template library corresponding to the maximum value AVG _Max , and if so, the recognition ends, and if not, the recognition fails.
9. A face recognition system according to claim 8, wherein there are k face feature templates of the user in the face feature template library, and the face feature templates and k individuals to be identified are identified. The similarity of face feature templates are S _A1 , S _A2 ,..., S _Ak ;

   The first face recognition unit and the second face recognition unit each include:

   The average similarity calculating sub-unit, for taking the k similarities _{S A1, S A2, ...,} S Ak maximum similarity S _MaxA, k is calculated a similarity S _A1, S _A2, ..., the average value of S _Ak , get the average similarity S _AvgA ;

   a first identifying subunit, configured to determine whether the maximum similarity S _MaxA is greater than or equal to a preset maximum similarity threshold S _max , and if yes, determining that the user to be identified is the user, and if not, entering the second identifier unit;

   a second identification subunit, configured to determine whether k≥K _S is satisfied, and if yes, proceeds to step third identification subunit, and if not, determines that the user to be identified is not the user; wherein K _S is a positive integer, K _S >1;

   a third identifying subunit, configured to determine whether the average similarity S _AvgA is greater than or equal to a preset average similarity threshold S _avg , and if yes, determining that the user to be identified is the user, and if not, determining to be identified The user is not the user.
10. A face recognition system according to claim 9, wherein the third identification subunit further comprises:

    Recognizing the sub-unit again, when the average similarity S _AvgA <S _avg is used, the identification of the user to be identified is performed again before the prompt recognition fails; the recognition manner is:

    Taking the minimum similarity S _MinA in the k similarities S _A1 , S _A2 , . . . , S _Ak , determining whether the minimum similarity S _MinA is greater than or equal to a preset minimum similarity threshold S _min , and if yes, determining The user is identified as the user, and if not, it is determined that the user to be identified is not the user.
11. A face recognition system according to claim 10, wherein the system further comprises:

    a similarity threshold determining module, configured to determine the maximum similarity threshold S _max , an average similarity threshold S _{avg ,} and a minimum similarity threshold S _min ; the similarity confirmation module includes:

    The test library building unit is configured to construct a face image test library, wherein the face image of the H person is stored in the test library, and the number of face images of each person is one;

    a sub-library building unit for randomly selecting J images from each person's I face images to form a sub-library P, and all remaining images constitute a sub-library G;

    a sub-library grouping unit, which divides a face image of each person in the sub-library G into K groups, and obtains an H×K group image;

    a second similarity calculation unit, configured to calculate, for each image P′ in the H×J images in the sub-library P, each image of the image P′ and the sub-library G other than the user to which the image P′ belongs Maximum similarity, most Small similarity and average similarity, get H×J×(H-1)×K maximum similarities, H×J×(H-1)×K minimum similarities and H×J×(H-1) ×K average similarities;

    a similarity threshold determining unit, configured to arrange the H×J×(H−1××K maximum similarities, the minimum similarity, and the average similarity in descending order, respectively, in an order of H×J×( H-1) × K maximum similarities, the ratio of the position number to H × J × (H-1) × K is equal to the preset first misrecognition rate threshold, the maximum similarity is the maximum similarity threshold S _max Taking the ratio of the position number of H×J×(H-1)×K average similarities to H×J×(H-1)×K equal to the average similarity of the preset second misrecognition rate threshold is average Similarity threshold S _avg ; taking H × J × (H-1) × K minimum similarities, the ratio of the position number to H × J × (H-1) × K is equal to the preset third misrecognition rate threshold The minimum similarity is the minimum similarity threshold S _min .

Images