CN114299568A

CN114299568A - Human face recognition method, system, electronic device and medium based on artificial intelligence

Info

Publication number: CN114299568A
Application number: CN202111468281.XA
Authority: CN
Inventors: 余佳涛; 余思彤
Original assignee: Shanghai Qingzhi Information Technology Co ltd
Current assignee: Shanghai Qingzhi Information Technology Co ltd
Priority date: 2021-12-03
Filing date: 2021-12-03
Publication date: 2022-04-08

Abstract

The invention provides a face recognition method, a face recognition system, electronic equipment and a medium based on artificial intelligence, and relates to the technical field of face recognition. Acquiring an image by using a depth camera and an infrared thermal imager; extracting a face image shot by a depth camera; deep learning is carried out on the face image by using a support vector machine to obtain a common reference sample; if the image does not accord with the common reference sample, judging that the image is not the user; if the image accords with the common reference sample, identifying the outline of the face in the face image, generating a boundary base line, and taking the area enclosed by the boundary base line as a main identification area; extracting an infrared face image of an infrared thermal imager, generating an infrared baseline according to the outer contour of the infrared face image, wherein the area defined by the infrared baseline is an infrared identification area; comparing the two identification areas, and if the two identification areas are overlapped, determining that the user is the user; and if the main identification area contains a protruding area relative to the infrared identification area, judging the non-user. The method can prevent the silica gel simulation mask from being cracked when the face is recognized, and improves safety.

Description

Human face recognition method, system, electronic device and medium based on artificial intelligence

Technical Field

The invention relates to the technical field of face recognition, in particular to a face recognition method, a face recognition system, electronic equipment and a medium based on artificial intelligence.

Background

Face recognition is a biometric technology for identity recognition based on facial feature information of a person. Face recognition generally includes face image acquisition and detection, face image preprocessing, face image feature extraction, and matching and recognition. The process of face image matching and recognition is that the extracted feature data of the face image is searched and matched with a feature template stored in a bottom library, and a threshold value is set, and when the similarity exceeds the threshold value, the result obtained by matching is output.

However, most of the prior art methods for recognizing human faces basically adopt feature points for capturing, and such methods still have great vulnerability, such as a silica gel simulation mask and the like, so that a safer human face recognition method based on artificial intelligence is needed.

Disclosure of Invention

The invention aims to provide a human face recognition method based on artificial intelligence, which can prevent a silica gel simulation mask from recognizing human faces and improving safety.

The embodiment of the invention is realized by the following steps:

in a first aspect, an embodiment of the present application provides a face recognition method based on artificial intelligence, which includes: respectively acquiring images to be recognized at the same time and the same angle by using a depth camera and an infrared thermal imager; extracting a common face image in any image to be identified shot by a depth camera; carrying out deep learning on image information of a plurality of common face images by using a support vector machine to obtain common reference samples; when the face recognition is carried out, if the image to be detected does not conform to the common reference sample, judging that the user is not the user; if the image to be detected accords with the common reference sample, identifying the outer contour of the face in the face image, generating a boundary base line overlapped with the outer contour, and defining an area defined by the boundary base line as a main identification area; extracting any infrared face image to be recognized, which is shot by an infrared thermal imager, generating an infrared baseline overlapped with the outer contour according to the outer contour of the infrared face image, and defining an area surrounded by the infrared baseline as an infrared recognition area; comparing the infrared identification area with the main identification area, and if the main identification area is overlapped with the infrared identification area, determining that the user is the user; and if the main identification area contains a protruding area relative to the infrared identification area, judging the non-user.

In some embodiments of the present invention, the step of performing deep learning on image information of a plurality of common face images by using a support vector machine to obtain a common reference sample includes: and selecting eye images, mouth images and nose images of a plurality of common face images by using a support vector machine, and performing deep learning according to respective image information of the eye images, the mouth images and the nose images and the distance between the eye images, the mouth images and the nose images to obtain a common reference sample.

In some embodiments of the present invention, the step of respectively acquiring images to be recognized at the same time and the same angle by using a depth camera and an infrared thermal imager includes: and respectively acquiring a main view of the face to be recognized, a left view of the face to be recognized and a right view of the face to be recognized of the person to be detected at the same time and at the same angle by using a depth camera and an infrared thermal imager.

In some embodiments of the present invention, the infrared identification area is compared with the main identification area, and if the main identification area and the infrared identification area are overlapped, the user is determined to be himself; if the main identification area contains a protruding area relative to the infrared identification area, the step of judging the non-user himself comprises the following steps: comparing the main face view to be recognized of the person to be detected, and if the main recognition area of the main face view to be recognized contains a protruding area relative to the infrared recognition area, judging that the person is not the user; if the main identification area of the main view of the face to be identified is overlapped with the infrared identification area; comparing the left view of the face to be recognized of the person to be detected, and if the left recognition area of the left view of the face to be recognized contains a protruding area relative to the infrared recognition area, judging that the person is not the user; if the left to-be-identified area of the left view of the face to be identified is overlapped with the infrared identification area; comparing the right view of the face to be recognized of the person to be recognized, and if the right recognition area of the right view of the face to be recognized contains a protruding area relative to the infrared recognition area, judging that the person is not the user; if the right recognition area of the right view of the face to be recognized is overlapped with the infrared recognition area; the user is determined to be himself.

In some embodiments of the present invention, the step of generating an infrared baseline overlapping with the outer contour according to the outer contour of the infrared face image includes: and selecting outermost pixel points in the infrared face image, and connecting adjacent pixels to form an infrared baseline.

In some embodiments of the present invention, the infrared thermal imager is a non-refrigerated infrared thermal imager.

In some embodiments of the present invention, the depth camera employs a structured light type depth camera.

In a second aspect, an embodiment of the present application provides a face recognition system based on artificial intelligence, which includes a shooting module, configured to respectively obtain images to be recognized at the same time and at the same angle by using a depth camera and an infrared thermal imager; the first processing module is used for extracting a common face image in any image to be identified, which is shot by the depth camera; carrying out deep learning on image information of a plurality of common face images by using a support vector machine to obtain common reference samples; the first judgment module is used for judging that the user is not the user if the image to be detected does not conform to the common reference sample when the face recognition is carried out; the second processing module is used for identifying the outline of the face in the face image if the image to be detected accords with the common reference sample, generating a boundary baseline overlapped with the outline, and defining an area defined by the boundary baseline as a main identification area; extracting any infrared face image to be recognized, which is shot by an infrared thermal imager, generating an infrared baseline overlapped with the outer contour according to the outer contour of the infrared face image, and defining an area surrounded by the infrared baseline as an infrared recognition area; the second judgment module is used for comparing the infrared identification area with the main identification area, and judging the user if the main identification area is overlapped with the infrared identification area; and if the main identification area contains a protruding area relative to the infrared identification area, judging the non-user.

In a third aspect, an embodiment of the present application provides an electronic device, which includes at least one processor, at least one memory, and a data bus; wherein: the processor and the memory complete mutual communication through a data bus; the memory stores program instructions executable by the processor, which invokes the program instructions to perform an artificial intelligence based face recognition method.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements an artificial intelligence based face recognition method.

Compared with the prior art, the embodiment of the invention has at least the following advantages or beneficial effects:

to the crack of the silica gel simulation mask to the face recognition in the recognition of the face, the design utilizes infrared rays to further approve the face outline of the person, thereby utilizing the infrared rays to detect whether the user wears the mask.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.

FIG. 1 is a flow chart of a human face recognition method based on artificial intelligence in the invention;

FIG. 2 is a schematic structural diagram of a face recognition method based on artificial intelligence in the present invention;

fig. 3 is a schematic structural diagram of an electronic device according to the present invention.

Icon: 1. a shooting module; 2. a first processing module; 3. a first judgment module; 4. a second processing module; 5. a second judgment module; 6. a processor; 7. a memory; 8. a data bus.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations.

Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.

It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

In the description of the present application, it should be noted that the terms "upper", "lower", "inner", "outer", and the like indicate orientations or positional relationships based on orientations or positional relationships shown in the drawings or orientations or positional relationships conventionally found in use of products of the application, and are used only for convenience in describing the present application and for simplification of description, but do not indicate or imply that the referred devices or elements must have a specific orientation, be constructed in a specific orientation, and be operated, and thus should not be construed as limiting the present application.

In the description of the present application, it is also to be noted that, unless otherwise explicitly specified or limited, the terms "disposed" and "connected" are to be interpreted broadly, e.g., as being either fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present application can be understood in a specific case by those of ordinary skill in the art.

Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the individual features of the embodiments can be combined with one another without conflict.

Example 1

Referring to fig. 1, in the human face recognition method based on artificial intelligence provided in the embodiment of the present application, for the crack of the silica gel simulation mask on the human face recognition in the human face recognition, the present embodiment further approves the facial contour of the human by using infrared rays, so as to detect whether the user wears the mask by using infrared rays.

S101: respectively acquiring images to be recognized at the same time and the same angle by using a depth camera and an infrared thermal imager;

in order to further reduce errors, the depth camera and the infrared thermal imager are used for shooting at the same angle at the same time, so that the images shot by the two cameras are the same as far as possible.

S102: extracting a common face image in any image to be identified shot by a depth camera; carrying out deep learning on image information of a plurality of common face images by using a support vector machine to obtain common reference samples;

firstly, in order to identify similarity, a depth camera is adopted for identification, and the depth camera is utilized to avoid a user from deceiving face identification by using photos or other images; meanwhile, deep learning is carried out by adopting a support vector machine, so that a reference sample for judging the user is obtained;

s103: when the face recognition is carried out, if the image to be detected does not conform to the common reference sample, judging that the user is not the user; if the image to be detected accords with the common reference sample, identifying the outer contour of the face in the face image, generating a boundary base line overlapped with the outer contour, and defining an area defined by the boundary base line as a main identification area;

after the similarity between the human body and the user is judged by using the depth camera, the human power area is selected, and whether the wearing area is judged in the next step is convenient;

s104: extracting any infrared face image to be recognized, which is shot by an infrared thermal imager, generating an infrared baseline overlapped with the outer contour according to the outer contour of the infrared face image, and defining an area surrounded by the infrared baseline as an infrared recognition area;

extracting an infrared image of the face, and conveniently comparing the infrared image with the face image selected by the depth camera;

s105: comparing the infrared identification area with the main identification area, and if the main identification area is overlapped with the infrared identification area, determining that the user is the user; and if the main identification area contains a protruding area relative to the infrared identification area, judging the non-user.

Because the images are shot at the same angle at the same time, if the user does not wear the mask, the infrared thermal imaging image of the face of the user is overlapped with the face image of the depth camera, and if the face area in the depth camera, namely the area of the main identification area, is larger than the area of the infrared identification area, the user can be judged to wear the mask, so that the user is judged not to be the user.

In some embodiments of the present invention, the similarity is determined by the depth camera mainly by using the characteristics of the eyes, mouth and nose of the user and the distance therebetween.

In some embodiments of the present invention, in order to avoid that some users wear a partial mask, the partial mask is difficult to be found at the front view angle of the user, so when collecting facial data, the main view of the face to be identified, the left view of the face to be identified, and the right view of the face to be identified of the person to be detected need to be collected, so that the person to be detected can still detect the thickness of the mask from different angles even if the person to be detected adopts a silica gel mask with a fully wrapped head, thereby improving the detection accuracy.

In some embodiments of the present invention, for each viewing angle comparison, the sequence may be adjusted as needed, but for the convenience of the user to detect, the sequence of the front view, the left view and the right view is adopted for comparison, so as to improve the comfort.

Example 2

Referring to fig. 2, a face recognition system based on artificial intelligence provided by the present invention includes: the system comprises a shooting module 1, a recognition module and a control module, wherein the shooting module 1 is used for respectively acquiring images to be recognized at the same time and the same angle by using a depth camera and an infrared thermal imager; the first processing module 2 is used for extracting a common face image in any image to be identified, which is shot by the depth camera; carrying out deep learning on image information of a plurality of common face images by using a support vector machine to obtain common reference samples; the first judging module 3 is used for judging that the user is not the user if the image to be detected does not conform to the common reference sample when the face recognition is carried out; the second processing module 4 is used for identifying the outline of the face in the face image if the image to be detected conforms to the common reference sample, generating a boundary baseline overlapping with the outline, and defining an area surrounded by the boundary baseline as a main identification area; extracting any infrared face image to be recognized, which is shot by an infrared thermal imager, generating an infrared baseline overlapped with the outer contour according to the outer contour of the infrared face image, and defining an area surrounded by the infrared baseline as an infrared recognition area; the second judging module 5 is used for comparing the infrared identification area with the main identification area, and judging the user if the main identification area is overlapped with the infrared identification area; and if the main identification area contains a protruding area relative to the infrared identification area, judging the non-user.

Example 3

Referring to fig. 3, an electronic device provided by the present invention includes at least one processor 6, at least one memory 7, and a data bus 8; wherein: the processor 6 and the memory 7 complete mutual communication through a data bus 8; the memory 7 stores program instructions executable by the processor 6, and the processor 6 calls the program instructions to perform an artificial intelligence based face recognition method. For example, the following steps are realized:

respectively acquiring images to be recognized at the same time and the same angle by using a depth camera and an infrared thermal imager; extracting a common face image in any image to be identified shot by a depth camera; carrying out deep learning on image information of a plurality of common face images by using a support vector machine to obtain common reference samples; when the face recognition is carried out, if the image to be detected does not conform to the common reference sample, judging that the user is not the user; if the image to be detected accords with the common reference sample, identifying the outer contour of the face in the face image, generating a boundary base line overlapped with the outer contour, and defining an area defined by the boundary base line as a main identification area; extracting any infrared face image to be recognized, which is shot by an infrared thermal imager, generating an infrared baseline overlapped with the outer contour according to the outer contour of the infrared face image, and defining an area surrounded by the infrared baseline as an infrared recognition area; comparing the infrared identification area with the main identification area, and if the main identification area is overlapped with the infrared identification area, determining that the user is the user; and if the main identification area contains a protruding area relative to the infrared identification area, judging the non-user.

Example 4

A computer-readable storage medium is provided for the present invention, on which a computer program is stored which, when being executed by a processor 6, carries out a method for artificial intelligence based face recognition. For example, the following steps are realized:

The MEMORY 7 may be, but is not limited to, RANDOM ACCESS MEMORY (RAM), READ ONLY MEMORY (READ ONLY MEMORY, ROM), PROGRAMMABLE READ ONLY MEMORY (PROM), ERASABLE READ ONLY MEMORY (EPROM), electrically ERASABLE READ ONLY MEMORY (EEPROM), and the like.

The processor 6 may be an integrated circuit chip having signal processing capabilities. The PROCESSOR 6 may be a general-purpose PROCESSOR, including a CENTRAL PROCESSING UNIT (CPU), a NETWORK PROCESSOR (NP), etc.; it may also be a digital signal processor (DIGITAL SIGNAL PROCESSING, DSP), an APPLICATION Specific Integrated CIRCUIT (ASIC), a FIELD PROGRAMMABLE gate array (FIELD-PROGRAMMABLE GATE ARRAY, FPGA) or other PROGRAMMABLE logic device, discrete gate or transistor logic device, discrete hardware component.

In the embodiments provided in the present application, it should be understood that the disclosed method can be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate methods according to various embodiments of the application and, in this regard, each block in the flowchart or block diagrams may represent a portion of a module that contains one or more executable instructions for implementing the specified logical function(s). It should also be noted that, 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.

In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U disk, a removable hard disk, a READ-ONLY MEMORY (ROM), a RANDOM ACCESS MEMORY (RAM), a magnetic disk or an optical disk, and various media capable of storing program codes.

The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.

It will be evident to those skilled in the art that the present application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.

Claims

1. A face recognition method based on artificial intelligence is characterized by comprising the following steps:

respectively acquiring images to be recognized at the same time and the same angle by using a depth camera and an infrared thermal imager;

extracting a common face image in any image to be recognized shot by a depth camera; carrying out deep learning on the image information of the plurality of common face images by using a support vector machine to obtain a common reference sample;

when the face recognition is carried out, if the image to be detected does not conform to the common reference sample, judging that the user is not the user;

if the image to be detected accords with a common reference sample, identifying the outer contour of the face in the face image, generating a boundary baseline overlapped with the outer contour, and defining an area surrounded by the boundary baseline as a main identification area;

extracting any infrared face image to be recognized, which is shot by the infrared thermal imager, generating an infrared baseline overlapped with the outer contour according to the outer contour of the infrared face image, and defining an area defined by the infrared baseline as an infrared recognition area;

comparing the infrared identification area with the main identification area, and if the main identification area is overlapped with the infrared identification area, determining that the user is the user; and if the main identification area contains a protruding area relative to the infrared identification area, judging the non-user.

2. The artificial intelligence based face recognition method of claim 1, wherein the step of performing deep learning on the image information of the plurality of normal face images by using a support vector machine to obtain a normal reference sample comprises:

selecting eye images, mouth images and nose images of the common face images by using a support vector machine, and performing deep learning according to respective image information and mutual distance of the eye images, the mouth images and the nose images to obtain a common reference sample.

3. The artificial intelligence based face recognition method of claim 1, wherein the step of respectively obtaining the images to be recognized at the same time and the same angle by using the depth camera and the infrared thermal imager comprises:

and respectively acquiring a main view of the face to be recognized, a left view of the face to be recognized and a right view of the face to be recognized of the person to be detected at the same time and at the same angle by using a depth camera and an infrared thermal imager.

4. The artificial intelligence based face recognition method of claim 3, wherein the infrared recognition area and the main recognition area are compared, and if the main recognition area and the infrared recognition area are overlapped, the user is determined to be himself; if the main identification area contains a protruding area relative to the infrared identification area, the step of judging the non-user himself comprises the following steps:

comparing the main face view to be recognized of the person to be detected, and if the main recognition area of the main face view to be recognized contains a protruding area relative to the infrared recognition area, judging that the person is not the user; if the main identification area of the main view of the face to be identified is overlapped with the infrared identification area;

comparing the left view of the face to be recognized of the person to be detected, and if the left recognition area of the left view of the face to be recognized contains a protruding area relative to the infrared recognition area, judging that the person is not the user; if the left to-be-identified area of the left view of the face to be identified is overlapped with the infrared identification area;

comparing the right view of the face to be recognized of the person to be detected, and if the right recognition area of the right view of the face to be recognized contains a protruding area relative to the infrared recognition area, judging that the person is not the user; if the right identification area of the right view of the face to be identified is overlapped with the infrared identification area; the user is determined to be himself.

5. The artificial intelligence based face recognition method of claim 1, wherein the step of generating an infrared baseline overlapping with the outer contour according to the outer contour of the infrared face image comprises:

and selecting outmost pixel points in the infrared face image, and connecting adjacent pixel points to form an infrared baseline.

6. The artificial intelligence based face recognition method of claim 1, wherein the infrared thermal imager is a non-refrigeration type infrared thermal imager.

7. The artificial intelligence based face recognition method of claim 1, wherein the depth camera is a structured light type depth camera.

8. A face recognition system based on artificial intelligence, comprising:

the shooting module is used for respectively acquiring images to be recognized at the same time and the same angle by utilizing the depth camera and the infrared thermal imager;

the first processing module is used for extracting a common face image in any image to be recognized, which is shot by the depth camera; carrying out deep learning on the image information of the plurality of common face images by using a support vector machine to obtain a common reference sample;

the first judgment module is used for judging that the user is not the user if the image to be detected does not conform to the common reference sample when the face recognition is carried out;

the second processing module is used for identifying the outline of the face in the face image and generating a boundary baseline overlapped with the outline if the image to be detected conforms to a common reference sample, and an area defined by the boundary baseline is defined as a main identification area; extracting any infrared face image to be recognized, which is shot by the infrared thermal imager, generating an infrared baseline overlapped with the outer contour according to the outer contour of the infrared face image, and defining an area defined by the infrared baseline as an infrared recognition area;

the second judgment module is used for comparing the infrared identification area with the main identification area, and judging the user if the main identification area is overlapped with the infrared identification area; and if the main identification area contains a protruding area relative to the infrared identification area, judging the non-user.

9. An electronic device comprising at least one processor, at least one memory, and a data bus; wherein: the processor and the memory complete mutual communication through the data bus; the memory stores program instructions executable by the processor, the processor calling the program instructions to perform the method of any of claims 1-7.

10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-7.