CN111783752A

CN111783752A - Face recognition method and device, electronic equipment and storage medium

Info

Publication number: CN111783752A
Application number: CN202010850796.5A
Authority: CN
Inventors: 于志鹏; 吴玉东; 梁鼎
Original assignee: Beijing Sensetime Technology Development Co Ltd
Current assignee: Beijing Sensetime Technology Development Co Ltd
Priority date: 2020-08-21
Filing date: 2020-08-21
Publication date: 2020-10-16

Abstract

The present disclosure relates to a face recognition method and apparatus, an electronic device, and a storage medium, wherein the method includes: determining first race information of a first human face and second race information of a second human face; modifying at least one parameter in face recognition parameters according to the first ethnic information and the second ethnic information to obtain a modification result, wherein the face recognition parameters comprise: a first similarity and a similarity threshold of the first face and the second face; and determining whether the first face and the second face belong to the same person or not according to the modification result. The embodiment of the disclosure can improve the accuracy of the face recognition process.

Description

Face recognition method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a face recognition method and apparatus, an electronic device, and a storage medium.

Background

With the rapid development of internet technology and machine learning, face recognition technology has also been developed. At present, the face recognition technology has been widely applied to daily life of people, for example, scenes of face brushing and money paying in supermarkets, face brushing and login in mobile phone applications, face brushing and station entering in stations, and the like.

With the wide application of the face recognition technology, it is important to improve the accuracy of the face recognition technology.

Disclosure of Invention

The present disclosure provides a face recognition technical scheme.

According to an aspect of the present disclosure, there is provided a face recognition method, including:

determining first race information of a first human face and second race information of a second human face;

modifying at least one parameter in face recognition parameters according to the first ethnic information and the second ethnic information to obtain a modification result, wherein the face recognition parameters comprise: a first similarity and a similarity threshold of the first face and the second face;

and determining whether the first face and the second face belong to the same person or not according to the modification result.

In a possible implementation manner, the modifying at least one of the face recognition parameters according to the first race information and the second race information to obtain a modification result includes:

under the condition that the first ethnic information and the second ethnic information are the same, modifying the first similarity according to the first ethnic information to obtain a second similarity;

the determining whether the first face and the second face belong to the same person according to the modification result includes:

and determining whether the first face and the second face belong to the same person or not according to the second similarity and the similarity threshold.

In a possible implementation manner, the determining whether the first face and the second face belong to the same person according to the second similarity and the similarity threshold includes:

obtaining a third similarity according to a first probability of a first face corresponding to the first ethnic information, a second probability of a second face corresponding to the second ethnic information, the first similarity and the second similarity;

and comparing the third similarity with a similarity threshold value to determine whether the first face and the second face belong to the same person.

In a possible implementation manner, the obtaining a third similarity according to a first probability that a first face corresponds to the first race information, a second probability that a second face corresponds to the second race information, the first similarity, and the second similarity includes:

determining a first probability that the first face corresponds to the first ethnic information and a second probability that the second face corresponds to the second ethnic information;

weighting the difference value between the second similarity and the first similarity according to the first probability and the second probability to obtain a weighted value;

and fusing the first similarity and the weighted value to obtain a third similarity.

In a possible implementation manner, the modifying the first similarity according to the first race information to obtain a second similarity includes:

modifying the first similarity according to the first ethnic information under the condition that the first similarity belongs to a preset range to obtain a second similarity, wherein the preset range comprises the similarity threshold;

and taking the first similarity as a second similarity when the first similarity does not belong to the preset range.

and modifying the first similarity by using a preset modification value corresponding to the first ethnic information to obtain a second similarity.

and mapping the first similarity to a second similarity by using a preset mapping function corresponding to the first ethnic group information.

In a possible implementation manner, in a case that the first similarity belongs to a preset range and the preset range includes two endpoints, the preset mapping function is a quadratic function, and a function value output by the quadratic function at the endpoint is equal to a value of the endpoint.

under the condition that the first ethnic information is the same as the second ethnic information, modifying the similarity threshold according to the first ethnic information to obtain a modified threshold;

and comparing the first similarity with the correction threshold, and determining a face recognition result according to a comparison result.

In a possible implementation manner, after determining the first race information of the first face and the second race information of the second face, the method further includes:

judging whether the first ethnic information and the second ethnic information are the same;

and under the condition that the ethnicity information is different, determining that the first face and the second face do not belong to the same person.

According to an aspect of the present disclosure, there is provided a face recognition apparatus including:

a race information determination unit for determining first race information of a first face and second race information of a second face;

a parameter modification unit, configured to modify at least one parameter of face recognition parameters according to the first race information and the second race information, so as to obtain a modification result, where the face recognition parameters include: a first similarity and a similarity threshold of the first face and the second face;

and the identification unit is used for determining whether the first face and the second face belong to the same person according to the modification result.

In a possible implementation manner, the parameter modification unit is configured to modify the first similarity according to first race information to obtain a second similarity when the first race information and the second race information are the same;

and the identification unit is used for determining whether the first face and the second face belong to the same person according to the second similarity and the similarity threshold.

In a possible implementation manner, the identifying unit is configured to obtain a third similarity according to a first probability that a first face corresponds to the first ethnic information, a second probability that a second face corresponds to the second ethnic information, the first similarity, and the second similarity; and comparing the third similarity with a similarity threshold value to determine whether the first face and the second face belong to the same person.

In a possible implementation manner, the identifying unit is configured to determine a first probability that the first face corresponds to the first ethnic information, and a second probability that the second face corresponds to the second ethnic information; weighting the difference value between the second similarity and the first similarity according to the first probability and the second probability to obtain a weighted value; and fusing the first similarity and the weighted value to obtain a third similarity.

In a possible implementation manner, the parameter modifying unit is configured to modify the first similarity according to the first race information to obtain a second similarity when the first similarity belongs to a preset range, where the preset range includes the similarity threshold; and taking the first similarity as a second similarity when the first similarity does not belong to the preset range.

In a possible implementation manner, the parameter modification unit is configured to modify the first similarity by using a preset modification value corresponding to the first race information, so as to obtain a second similarity.

In a possible implementation manner, the parameter modification unit is configured to map the first similarity to a second similarity by using a preset mapping function corresponding to the first ethnic group information.

In a possible implementation manner, the parameter modification unit is configured to modify the similarity threshold according to the first race information under the condition that the first race information and the second race information are the same, so as to obtain a modified threshold;

and the identification unit is used for comparing the first similarity with the correction threshold and determining a face identification result according to a comparison result.

In one possible implementation, the apparatus further includes:

a judging unit configured to judge whether the first race information and the second race information are the same;

and the determining unit is used for determining that the first face and the second face do not belong to the same person under the condition that the race information is different.

According to an aspect of the present disclosure, there is provided an electronic device including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the memory-stored instructions to perform the above-described method.

According to an aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the above-described method.

In the embodiment of the disclosure, it is considered that the features of the faces are related to the ethnicity, the difference between some ethnicity faces is large, and the difference between some ethnicity faces is small, so that in the process of face recognition, the face recognition parameters are modified according to the ethnicity information of the two faces, and whether the two faces belong to the same person is determined according to the modification result, thereby improving the accuracy of the face recognition process.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure.

Fig. 1 shows a flow diagram of a face recognition method according to an embodiment of the present disclosure;

FIG. 2 shows a block diagram of a face recognition apparatus according to an embodiment of the present disclosure;

FIG. 3 shows a block diagram of an electronic device in accordance with an embodiment of the disclosure;

fig. 4 shows a block diagram of an electronic device in accordance with an embodiment of the disclosure.

Detailed Description

Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. In the drawings, like reference numbers can indicate functionally identical or similar elements. While the various aspects of the embodiments are presented in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.

The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, C, and may mean including any one or more elements selected from the group consisting of A, B and C.

Furthermore, in the following detailed description, numerous specific details are set forth in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements and circuits that are well known to those skilled in the art have not been described in detail so as not to obscure the present disclosure.

As the face recognition technology is becoming mature, more and more application scenes of the face recognition technology are available, and a typical application scene is to identify the user identity through face recognition, for example, in the process of performing face brushing login of an application program or performing face unlocking of an intelligent access control, the face of a current user requesting identity recognition is acquired through a camera, then the acquired face features are compared with the face features in a face feature library, and the face features belonging to the same person as the face features of the current user are searched in the face feature library. Because the identity information of the face features in the face feature library is known, the identity information of the user can be determined under the condition that the face features belonging to the same person as the face features of the current user are found in the face feature library, and then the identity information of the user is used for logging in software.

Because the face recognition technology is often applied to scenes such as identity recognition and the like which relate to user information, the improvement of the accuracy rate during face recognition is of great importance.

The utility model provides a technical scheme of face identification can confirm more accurately whether two faces of carrying out the comparison belong to the same person, improves the rate of accuracy of face identification process.

In the technical scheme of the face recognition provided by the disclosure, the application of the face recognition is considered to be very wide and is often used in various countries and regions, so that the face to be recognized relates to multiple races, the appearance of the face is related to the races, the difference between faces of some races is larger, and the difference between faces of some races is smaller, therefore, in the process of face recognition, parameters used in the process of face recognition are modified according to the race information of the face, whether two faces belong to the same person is determined according to the modification result, and the accuracy of the face recognition process can be improved.

The technical scheme of face recognition provided by the present disclosure will be described in detail below with reference to specific implementation manners.

Fig. 1 shows a flowchart of a face recognition method according to an embodiment of the present disclosure, as shown in fig. 1, the face recognition method includes:

in step S11, first race information of the first face and second race information of the second face are determined.

The race information of the human face can be obtained by analyzing the extracted human face features, the human face features are features capable of representing the human face, and the human face features are often represented in a feature vector form in a computer.

The acquisition mode of the face features may be various, and may be specifically determined according to the application scenario of the present disclosure. For example, in the identification, the feature of the first face may be extracted from a face image of a user requesting identification, and the feature of the second face may be obtained from a feature library in which the face features are stored; alternatively, when the target person tracking is performed, the features of the first face and the features of the second face may be extracted from the image.

The first face and the second face are used to refer to two faces to be compared, and the first face and the second face are used to distinguish the two faces, and should not be understood as other limitations of the faces.

The ethnicity is a group with certain common characteristics on constitutional features or genetic features, and the classification can be carried out according to the standards of external features (such as skin color, hair color, facial skeleton structure and the like), genes, regions and the like. For example, according to skin color, the skin color can be divided into black race, white race, yellow race (including red race), brown race; according to the regional division, the species can be divided into east Asian, Indian, Mexico, middle east, southeast Asian, Western Europe, east Europe, etc. The present disclosure is not limited to specific division criteria.

The race information of the face is the race to which the person corresponding to the face belongs, and can be specifically determined through a trained neural network, and the specific mode for determining the race information is not limited in the disclosure.

In step S12, modifying at least one of the face recognition parameters according to the first race information and the second race information to obtain a modified result;

the face recognition parameters include: a first similarity and a similarity threshold of the first face and the second face.

In the embodiment of the disclosure, whether the first face and the second face belong to the same person may be measured through the face recognition parameters, however, the difference between the face appearances of some ethnic groups is large, and the difference between the faces of some ethnic groups is small, so that the requirement of the recognition accuracy rate may be met only when the similarity threshold value is 72% for the ethnic group a with a large difference between the faces, and the requirement of the recognition accuracy rate may be met only when the similarity threshold value is 80% for the ethnic group B with a small difference between the faces.

Therefore, in order to improve the accuracy of face recognition of various families, in the process of face recognition based on the first similarity and the similarity threshold, the first similarity may be modified based on the determined race information, and the similarity threshold may also be modified based on the determined race information, so as to reduce the occurrence of false recognition. Hereinafter, the process of adjusting the first similarity or adjusting the similarity threshold according to the race information will be described in detail through several possible implementation manners, which will not be described herein again.

In the process of modifying the face recognition parameters, only one of the face recognition parameters may be modified, for example, only the first similarity, or only the similarity threshold. This will be described later in conjunction with possible implementations of the present disclosure, and will not be described in detail here. Of course, in practical application, both the first similarity and the similarity threshold may be modified, and the specific modification manner is not limited in the present application.

The first similarity may be determined in various ways, for example, by using a euclidean distance, or may also be calculated by using a cosine distance, and the determination way of the first similarity is not specifically limited in the present disclosure.

In step S13, it is determined whether the first face and the second face belong to the same person according to the modification result.

When determining whether two faces belong to the same person, the similarity of the faces is often compared with a similarity threshold value to determine, and the higher the similarity is, the higher the probability representing that the two faces belong to the same person is, so that under the condition that the similarity is higher than the similarity threshold value, the two faces can be determined to belong to the same person.

In the embodiment of the present disclosure, under the condition that the first similarity is modified, the modified first similarity is compared with a similarity threshold value to determine whether two faces belong to the same face; in the case of modifying the similarity threshold, the modified similarity threshold is compared with the first similarity to determine whether the two faces belong to the same person. This will be described later in conjunction with possible implementations of the present disclosure, and will not be described in detail here.

In one possible implementation, the processing of steps S12 and S13 may be performed in a case where the first race information and the second race information are the same.

In a possible implementation manner, in a case where the first race information and the second race information are different, it may be determined that the first face and the second face do not belong to the same person, and in a case where the first race information and the second race information are the same, the first face and the second face are further identified according to the first similarity and the similarity threshold, and several possible implementation manners in a case where the first race information and the second race information are the same are described in detail below.

In a possible implementation manner, the modifying at least one of the face recognition parameters according to the first race information and the second race information to obtain a modification result includes: under the condition that the first ethnic information and the second ethnic information are the same, modifying the first similarity according to the first ethnic information to obtain a second similarity; the determining whether the first face and the second face belong to the same person according to the modification result includes: and determining whether the first face and the second face belong to the same person or not according to the second similarity and the similarity threshold.

In case the first similarity is modified based on the determined first race information, the similarity threshold may be kept unchanged, i.e. the similarity threshold used by the various races may be the same. Then, the first similarity threshold is modified based on the race information, and for races with large differences between the faces, the similarity between the faces is usually small, so that the first similarity can be properly increased, and the accuracy rate of face recognition is improved under the condition that various races use the same similarity threshold; for the ethnicity with small difference between the human faces, the similarity between the human faces is usually larger, so that the first similarity can be properly reduced, and the accuracy rate of the human face recognition is improved under the condition that various ethnicities use the same similarity threshold.

For the specific implementation manner of modifying the first similarity, description will be made in possible implementation manners disclosed in the following text, and details are not repeated here.

In a possible implementation manner, the determining whether the first face and the second face belong to the same person according to the second similarity and the similarity threshold includes: obtaining a third similarity according to a first probability of a first face corresponding to the first ethnic information, a second probability of a second face corresponding to the second ethnic information, the first similarity and the second similarity; and comparing the third similarity with a similarity threshold value to determine whether the first face and the second face belong to the same person.

In the embodiment of the present disclosure, the first similarity may be modified according to the first race information, however, in the process of determining the race information, the determined first race information and the second race information have a certain probability, so that after the first similarity is modified by using the first race information and the second race information to obtain the second similarity, the first similarity and the second similarity may be further adjusted by using the first probability and the second probability to obtain the third similarity.

Because the first similarity is modified through the first race information and the second race information, and the determined first race information and the determined second race information have certain probability, the probability that the human face corresponds to the race information is considered in the process of modifying the first similarity through the first race information and the second race information, and therefore the accuracy rate in human face recognition can be further improved.

In a possible implementation manner, obtaining a third similarity according to a first probability that a first face corresponds to the first race information, a second probability that a second face corresponds to the second race information, the first similarity, and the second similarity includes: determining a first probability that the first face corresponds to the first ethnic information and a second probability that the second face corresponds to the second ethnic information; weighting the difference value between the second similarity and the first similarity according to the first probability and the second probability to obtain a weighted value; and fusing the first similarity and the weighted value to obtain a third similarity.

In the process of determining the race information of the face, the probabilities of the face corresponding to different race information are obtained, and generally, the race information with the highest probability is often selected as finally determined race information. Obviously, by this process, it is possible to determine both a first probability that a first face corresponds to the first ethnic information and a second probability that a second face corresponds to the second ethnic information. Of course, the probability of the race information corresponding to the face may also be determined by other means, which is not limited in the present application.

The difference value between the second similarity and the first similarity is a value which is increased or decreased when the first similarity is adjusted through the first race information and the second race information, and the difference value is determined by the determined race information which corresponds to a certain probability, so that the weighted value obtained by weighting the difference value through the probability can more accurately reflect the adjustment amplitude of the first similarity through the race information.

And then, the weighted value is fused with the first similarity, and the obtained third similarity can accurately reflect the amplitude of the adjustment of the first similarity through ethnicity information, so that the accuracy rate of face recognition is further improved.

The method of fusing the first similarity with the weighted value may be, for example, adding the first similarity with the weighted value, or may be, during the adding, respectively giving a weight corresponding to the first similarity and the weighted value, and the specific fusing method is not limited in the present disclosure.

For convenience of understanding of the process of obtaining the third similarity, the process of obtaining the third similarity is exemplarily described below by the following formula (1).

S₃＝S₁+p¹*p²*(S₂-S₁) (1)

Wherein S is₁Characterizing a first degree of similarity, S₂Characterizing the second degree of similarity, S₃Characterizing the third degree of similarity, p¹Characterizing a first probability, p²The second probability is characterized.

In a possible implementation manner, the modifying the first similarity according to the first race information to obtain a second similarity includes: modifying the first similarity according to the first ethnic information under the condition that the first similarity belongs to a preset range to obtain a second similarity, wherein the preset range comprises the similarity threshold; and taking the first similarity as a second similarity when the first similarity does not belong to the preset range.

Since the difference value between the determined first similarity and the similarity threshold may be much larger than the difference value between the first similarity and the second similarity, in this case, even if the first similarity is adjusted to the second similarity, the result of the face recognition will not be changed.

Therefore, when the first similarity belongs to the preset range, the first similarity is modified according to the first ethnic information to obtain a second similarity; under the condition that the first similarity does not belong to the preset range, the first similarity can be directly used as the second similarity, and the second similarity does not need to be determined through calculation, so that the processing resource is saved.

The middle value of the preset range may be a similarity threshold, and the specific value of the preset range may be determined according to the maximum adjustment range of the first race information to the first similarity, and specifically may be obtained by adding the similarity threshold on the basis of the maximum adjustment range. For example, the maximum adjustment amplitude is [ -0.15, +0.15], the similarity threshold is 0.55, and the preset range may be [0.4,0.7 ]. If the first similarity exceeds the preset range, the first similarity can be directly used as the second similarity, namely the second similarity is not calculated, so that the processing resource is saved.

In a possible implementation manner, the modifying the first similarity according to the first race information to obtain a second similarity includes: and modifying the first similarity by using a preset modification value corresponding to the first ethnic information to obtain a second similarity.

The first race information may have a one-to-one correspondence with the preset modification value, for example, the preset modification value corresponding to the east asian race is + 0.0; the preset modified value for the Indian race is-0.2; the corresponding preset modification value for Mexico race is 0.12; the preset modification value for the middle east race is 0.18, the preset modification value for the southeast asian race is-0.1, the preset modification value for the western european race is-0.1, and the preset modification value for the eastern european race is-0.1.

In the process of face recognition, certain requirements can be made on the recognition accuracy rate, namely certain requirements on the false recognition rate, and generally, the false recognition rate can be required to be less than one thousandth. The false recognition rate is adjusted by controlling the similarity threshold, so that when the false recognition rate requirement is satisfied, each family respectively corresponds to a respective similarity threshold, which is referred to as an original similarity threshold for convenience of description.

Then, when the same standard similarity threshold is used by the various families for face recognition, the preset modification value corresponding to the various families is the difference between the original similarity threshold of the various families and the standard similarity threshold. In addition, the value of the preset modification value may also be an empirical value, which is not specifically limited by the present disclosure.

In the process of modifying the first similarity by using the preset modified value, the preset modified value may be added to the first similarity to obtain a second similarity. In addition, in the process of addition, corresponding weights can be given to the preset modification value and the first similarity, and the specific modification process is not limited by the disclosure.

In a possible implementation manner, the modifying the first similarity according to the first race information to obtain a second similarity includes: and mapping the first similarity to a second similarity by using a preset mapping function corresponding to the first ethnic group information.

The preset mapping function establishes a mapping relationship between the first similarity and the second similarity, and the preset mapping function may be a linear function or a quadratic function, which is not limited in the present disclosure.

In a case where the preset mapping function is a quadratic function, and the function value output by the quadratic function at the end point is equal to the value of the end point, the magnitude of the modification of the first similarity is larger closer to the middle value of the preset range. Then, under the condition that the middle value of the preset range is the similarity threshold, the closer the first similarity is to the middle value of the preset range, the larger the adjustment amplitude is, and the farther the first similarity is from the middle value of the preset range, the smaller the adjustment amplitude is, thereby realizing smooth adjustment of the first similarity near the preset range.

To facilitate understanding of the process of mapping the second similarity by the quadratic function, the quadratic function provided by the present disclosure is exemplarily described below by the following formula (2).

S₂＝aS₁ ²+bS₁+c (2)

Wherein a, b and c are coefficients of a quadratic function.

Assuming that the similarity threshold is 0.55, map the first similarity 0.6 to the second similarity 0.55, with the preset range [0.4,0.7], that is: the first similarity 0.4 is mapped to a second similarity 0.4; the first similarity 0.7 is mapped to a second similarity 0.7.

From the above three mappings, it can be calculated that a is 2.5, b is-1.75, and c is 0.7, and then the quadratic mapping function can be expressed as:

S₂＝2.5S₁ ²-1.75S₁+0.7 (2)

thus forming an S₁∈[0.4,0.7]Thereby smoothly reducing the first similarity in the interval.

While various implementations of modifying the first similarity are discussed above, in one possible implementation, the similarity threshold may also be modified based on race information. In this implementation manner, the modifying at least one of the face recognition parameters according to the first race information and the second race information to obtain a modification result includes: under the condition that the first ethnic information is the same as the second ethnic information, modifying the similarity threshold according to the first ethnic information to obtain a modified threshold, and determining whether the first face and the second face belong to the same person according to the modified result, wherein the method comprises the following steps of: and comparing the first similarity with the correction threshold, and determining a face recognition result according to a comparison result.

The specific modification method for the similarity threshold is similar to the modification method for the first similarity, for example, the similarity threshold may be modified by a preset modification value corresponding to the first family information, or the similarity threshold may be mapped as a modification threshold by a function, which is not described herein again.

In the embodiment of the disclosure, the similarity threshold is modified through the first race information, so that the similarity of each race face corresponds to the respective modification threshold, and then the first similarity is compared with the modification threshold, so that the accuracy in face recognition can be improved.

In a possible implementation manner, after determining the first race information of the first face and the second race information of the second face, the method further includes: judging whether the first ethnic information and the second ethnic information are the same; and under the condition that the ethnicity information is different, determining that the first face and the second face do not belong to the same person.

Accordingly, in the case that the first race information and the second race information are determined to be the same, the face recognition method described above in the embodiments of the present disclosure may be continuously performed.

In the embodiment of the present disclosure, under the condition that the race information of the first face and the race information of the second face are different, the first face and the second face do not necessarily belong to the same person, and then the similarity between the first face and the second face does not need to be calculated, so as to save processing resources.

As described above, the face recognition technical solution provided by the present disclosure can be applied to various application scenarios, and the specific acquisition modes of the first face and the second face depend on different application scenarios.

In one possible implementation, the method further includes: acquiring a first image and a second image which are acquired; and extracting first face features of the face in the first image and extracting second face features of the face in the second image.

The implementation method can be applied to various application scenarios, for example, when tracking a target person, a first image containing the target person is acquired in advance, and then a first face feature of a face in the first image is extracted; then, a second image is collected through a camera arranged at the target position, and second face features of the face in the second image are extracted; when the first face feature and the second face feature are determined to belong to the same person, the target person is considered to be tracked.

In one possible implementation, the method further includes: acquiring a first acquired image;

extracting first face features of a first face in a first image; the determining the first race information of the first face and the second race information of the second face includes: determining ethnicity information of a first facial feature; determining a set of second facial features corresponding to ethnicity information of the first facial features; the method further comprises the following steps: first similarities of the first facial features and second facial features in the set are determined, respectively.

The implementation mode can be applied to various application scenes, for example, the implementation mode can be applied to the scenes of identity recognition such as face-brushing payment and application face-brushing login.

The first image can contain the face of a user requesting identity recognition, and the first image can be acquired through a terminal camera.

After the first image is collected, the first face features of the first face in the first image can be extracted, then the race information of the first face features is determined, and because the two face features possibly belong to the same face under the condition that the race information is the same, a set of second face features corresponding to the race information of the first face features can be determined. The identity information of the second face features is known, the second face features are features of the second face and can be stored in a database in advance, the second face features with the same ethnicity information can form a set of the second face features, and each set can respectively correspond to different ethnicity information.

And then searching for a second face feature belonging to the same person as the first face feature in the set according to the determined first similarity and the ethnic information.

Under the condition of being found, the identity information of the found second face features can be used as the identity information of the user of the first face.

In the embodiment of the present disclosure, it is considered that two face features may belong to the same face only when the race information is the same, and therefore, a set of second face features corresponding to the race information of the first face feature may be determined, and then in the process of determining the first similarity, the first similarity between the first face feature and the second face feature in the set may be determined, and for other face features outside the set, similarity calculation may not be performed, so as to save processing resources.

In various application scenarios, the above embodiments may be used in combination, for example, after extracting a first face feature of a first face in a first image and a second face feature of a second face in a second image, it may be determined whether race information of the first face feature and the second face feature is the same, and if the race information is different, it may be determined that the first face feature and the second face feature do not belong to the same person. Under the condition that the ethnicity information is the same, determining a first similarity of the first face feature and the second face feature; and judging whether the first similarity belongs to a preset range or not, if not, directly taking the first similarity as a second similarity, and judging whether the first similarity and the second similarity belong to the same person or not according to the second similarity and a similarity threshold value. In the case that the first similarity belongs to the preset range, the first similarity may be adjusted to the second similarity according to the foregoing embodiment, and further, according to the foregoing embodiment, a third similarity may be obtained according to the second similarity, and the second similarity or the third similarity is compared with a similarity threshold to determine whether the first face and the second face belong to the same person.

For another example, after extracting a first face feature of a first face in a first image, a set of second face features having the same ethnic information as the first face feature may be determined, and a first similarity between the first face feature and each second face feature in the set may be determined; and judging whether the first similarity belongs to a preset range or not according to each first similarity, if not, directly taking the first similarity as a second similarity, and judging whether the first similarity and the second similarity belong to the same person or not according to the second similarity and a similarity threshold value. In the case that the first similarity belongs to the preset range, the first similarity may be adjusted to the second similarity according to the foregoing embodiment, and further, according to the foregoing embodiment, a third similarity may be obtained according to the second similarity, and the second similarity or the third similarity is compared with a similarity threshold to determine whether the first face and the second face belong to the same person.

In a possible implementation manner, the face recognition method may be performed by an electronic device such as a terminal device or a server, the terminal device may be a User Equipment (UE), a mobile device, a User terminal, a cellular phone, a cordless phone, a Personal Digital Assistant (PDA), a handheld device, a computing device, an in-vehicle device, a wearable device, or the like, and the method may be implemented by a processor calling a computer readable instruction stored in a memory. Alternatively, the method may be performed by a server.

It is understood that the above-mentioned method embodiments of the present disclosure can be combined with each other to form a combined embodiment without departing from the logic of the principle, which is limited by the space, and the detailed description of the present disclosure is omitted. Those skilled in the art will appreciate that in the above methods of the specific embodiments, the specific order of execution of the steps should be determined by their function and possibly their inherent logic.

In addition, the present disclosure also provides a face recognition apparatus, an electronic device, a computer-readable storage medium, and a program, which can be used to implement any one of the face recognition methods provided by the present disclosure, and the corresponding technical solutions and descriptions and corresponding descriptions in the methods section are not repeated.

Fig. 2 shows a block diagram of a face recognition apparatus according to an embodiment of the present disclosure, and as shown in fig. 2, the apparatus 20 includes:

a race information determination unit 21 for determining first race information of a first face and second race information of a second face;

a parameter modifying unit 22, configured to modify at least one parameter of face recognition parameters according to the first race information and the second race information, so as to obtain a modification result, where the face recognition parameters include: a first similarity and a similarity threshold of the first face and the second face;

and the identifying unit 23 is configured to determine whether the first face and the second face belong to the same person according to the modification result.

In a possible implementation manner, the parameter modifying unit 22 is configured to modify the first similarity according to the first race information to obtain a second similarity when the first race information and the second race information are the same;

the identifying unit 23 is configured to determine whether the first face and the second face belong to the same person according to the second similarity and the similarity threshold.

In a possible implementation manner, the identifying unit 23 is configured to obtain a third similarity according to a first probability that a first face corresponds to the first ethnic information, a second probability that a second face corresponds to the second ethnic information, the first similarity, and the second similarity; and comparing the third similarity with a similarity threshold value to determine whether the first face and the second face belong to the same person.

In a possible implementation manner, the identifying unit 23 is configured to determine a first probability that the first face corresponds to the first ethnic information, and a second probability that the second face corresponds to the second ethnic information; weighting the difference value between the second similarity and the first similarity according to the first probability and the second probability to obtain a weighted value; and fusing the first similarity and the weighted value to obtain a third similarity.

In a possible implementation manner, the parameter modifying unit 22 is configured to modify the first similarity according to the first race information to obtain a second similarity when the first similarity belongs to a preset range, where the preset range includes the similarity threshold; and taking the first similarity as a second similarity when the first similarity does not belong to the preset range.

In a possible implementation manner, the parameter modifying unit 22 is configured to modify the first similarity by using a preset modification value corresponding to the first race information, so as to obtain a second similarity.

In a possible implementation manner, the parameter modifying unit 22 is configured to map the first similarity to a second similarity by using a preset mapping function corresponding to the first race information.

In a possible implementation manner, the parameter modifying unit 22 is configured to modify the similarity threshold according to the first race information to obtain a modified threshold when the first race information and the second race information are the same;

the recognition unit 23 is configured to compare the first similarity with the correction threshold, and determine a face recognition result according to a comparison result.

In one possible implementation, the apparatus further includes:

In some embodiments, functions of or modules included in the apparatus provided in the embodiments of the present disclosure may be used to execute the method described in the above method embodiments, and specific implementation thereof may refer to the description of the above method embodiments, and for brevity, will not be described again here.

Embodiments of the present disclosure also provide a computer-readable storage medium having stored thereon computer program instructions, which when executed by a processor, implement the above-mentioned method. The computer readable storage medium may be a non-volatile computer readable storage medium.

An embodiment of the present disclosure further provides an electronic device, including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the memory-stored instructions to perform the above-described method.

The disclosed embodiments also provide a computer program product comprising computer readable code, when the computer readable code runs on a device, a processor in the device executes instructions for implementing the face recognition method provided in any of the above embodiments.

The embodiments of the present disclosure also provide another computer program product for storing computer readable instructions, which when executed cause a computer to perform the operations of the face recognition method provided in any of the above embodiments.

The electronic device may be provided as a terminal, server, or other form of device.

Fig. 3 illustrates a block diagram of an electronic device 800 in accordance with an embodiment of the disclosure. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, or the like terminal.

Referring to fig. 3, electronic device 800 may include one or more of the following components: processing component 802, memory 804, power component 806, multimedia component 808, audio component 810, input/output (I/O) interface 812, sensor component 814, and communication component 816.

The processing component 802 generally controls overall operation of the electronic device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing components 802 may include one or more processors 820 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interaction between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

The memory 804 is configured to store various types of data to support operations at the electronic device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 804 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

The power supply component 806 provides power to the various components of the electronic device 800. The power components 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 800.

The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and a user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front facing camera and/or a rear facing camera. The front camera and/or the rear camera may receive external multimedia data when the electronic device 800 is in an operation mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the electronic device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

The sensor assembly 814 includes one or more sensors for providing various aspects of state assessment for the electronic device 800. For example, the sensor assembly 814 may detect an open/closed state of the electronic device 800, the relative positioning of components, such as a display and keypad of the electronic device 800, the sensor assembly 814 may also detect a change in the position of the electronic device 800 or a component of the electronic device 800, the presence or absence of user contact with the electronic device 800, orientation or acceleration/deceleration of the electronic device 800, and a change in the temperature of the electronic device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 814 may also include a light sensor, such as a Complementary Metal Oxide Semiconductor (CMOS) or Charge Coupled Device (CCD) image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 may access a wireless network based on a communication standard, such as a wireless network (WiFi), a second generation mobile communication technology (2G) or a third generation mobile communication technology (3G), or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the electronic device 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.

In an exemplary embodiment, a non-transitory computer-readable storage medium, such as the memory 804, is also provided that includes computer program instructions executable by the processor 820 of the electronic device 800 to perform the above-described methods.

Fig. 4 shows a block diagram of an electronic device 1900 according to an embodiment of the disclosure. For example, the electronic device 1900 may be provided as a server. Referring to fig. 4, electronic device 1900 includes a processing component 1922 further including one or more processors and memory resources, represented by memory 1932, for storing instructions, e.g., applications, executable by processing component 1922. The application programs stored in memory 1932 may include one or more modules that each correspond to a set of instructions. Further, the processing component 1922 is configured to execute instructions to perform the above-described method.

The electronic device 1900 may also include a power component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input/output (I/O) interface 1958. The electronic device 1900 may operate based on an operating system, such as the Microsoft Server operating system (Windows Server), stored in the memory 1932^TM) Apple Corp LtdA pushed graphical user interface based operating system (Mac OSX)^TM) Multi-user, multi-process computer operating system (Unix)^TM) Free and open native code Unix-like operating System (Linux)^TM) Open native code Unix-like operating System (FreeBSD)^TM) Or the like.

In an exemplary embodiment, a non-transitory computer readable storage medium, such as the memory 1932, is also provided that includes computer program instructions executable by the processing component 1922 of the electronic device 1900 to perform the above-described methods.

The present disclosure may be systems, methods, and/or computer program products. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied thereon for causing a processor to implement various aspects of the present disclosure.

The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.

The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.

The computer program instructions for carrying out operations of the present disclosure may be assembler instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, the electronic circuitry that can execute the computer-readable program instructions implements aspects of the present disclosure by utilizing the state information of the computer-readable program instructions to personalize the electronic circuitry, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA).

Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.

These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The computer program product may be embodied in hardware, software or a combination thereof. In an alternative embodiment, the computer program product is embodied in a computer storage medium, and in another alternative embodiment, the computer program product is embodied in a Software product, such as a Software Development Kit (SDK), or the like.

Having described embodiments of the present disclosure, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A face recognition method, comprising:

2. The method according to claim 1, wherein the modifying at least one of the face recognition parameters according to the first ethnic information and the second ethnic information to obtain a modification result comprises:

3. The method of claim 2, wherein determining whether the first face and the second face belong to the same person according to the second similarity and the similarity threshold comprises:

4. The method according to claim 3, wherein the obtaining a third similarity according to a first probability that a first face corresponds to the first ethnic information, a second probability that a second face corresponds to the second ethnic information, the first similarity, and the second similarity comprises:

5. The method according to any one of claims 2 to 4, wherein the modifying the first similarity according to the first ethnic group information to obtain a second similarity comprises:

6. The method according to any one of claims 2 to 5, wherein the modifying the first similarity according to the first ethnic group information to obtain a second similarity comprises:

7. The method according to any one of claims 2 to 5, wherein the modifying the first similarity according to the first ethnic group information to obtain a second similarity comprises:

8. The method according to claim 7, wherein in a case where the first similarity belongs to a preset range and the preset range includes two endpoints, the preset mapping function is a quadratic function, and a function value output by the quadratic function at the endpoint is equal to a value of the endpoint.

9. The method according to claim 1, wherein the modifying at least one of the face recognition parameters according to the first ethnic information and the second ethnic information to obtain a modification result comprises:

10. The method of claim 1, wherein after determining the first ethnic information of the first face and the second ethnic information of the second face, the method further comprises:

11. A face recognition apparatus, comprising:

12. An electronic device, comprising:

a processor;

a memory for storing processor-executable instructions;

wherein the processor is configured to invoke the memory-stored instructions to perform the method of any one of claims 1 to 10.

13. A computer readable storage medium having computer program instructions stored thereon, which when executed by a processor implement the method of any one of claims 1 to 10.