CN115937921A - Image processing method, device and medium based on face recognition technology - Google Patents
Image processing method, device and medium based on face recognition technology Download PDFInfo
- Publication number
- CN115937921A CN115937921A CN202210575302.6A CN202210575302A CN115937921A CN 115937921 A CN115937921 A CN 115937921A CN 202210575302 A CN202210575302 A CN 202210575302A CN 115937921 A CN115937921 A CN 115937921A
- Authority
- CN
- China
- Prior art keywords
- face
- image
- similarity
- images
- recognized
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000005516 engineering process Methods 0.000 title claims abstract description 37
- 238000003672 processing method Methods 0.000 title claims abstract description 18
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 43
- 238000001514 detection method Methods 0.000 claims abstract description 36
- 238000000034 method Methods 0.000 claims abstract description 27
- 238000004364 calculation method Methods 0.000 claims abstract description 18
- 238000004590 computer program Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 230000003287 optical effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000001815 facial effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The application discloses an image processing method, an image processing device and an image processing medium based on a face recognition technology. The method comprises the following steps: acquiring an image to be identified; determining a face detection result aiming at an image to be recognized, wherein the face detection result comprises the number of faces and face coordinate related information, and when the number of the faces is more than 1, extracting each face area included in the image to be recognized according to the face coordinate related information to obtain a plurality of first face images; and respectively carrying out similarity calculation on the plurality of first face images and a preset second face image, and processing according to the similarity of the plurality of first face images and the second face image. The method and the device for extracting the human faces in the image achieve the purpose of comparing all the human faces in the extracted image according to the number of the human faces in the image, and solve the problem that the application range of a human face comparison algorithm is narrow due to the fact that only a large part of the human faces are compared in the existing human face recognition technology.
Description
Technical Field
The present application relates to the field of image recognition technologies, and in particular, to an image processing method, an image processing device, and an image processing medium based on a face recognition technology.
Background
With the application of artificial intelligence and deep learning methods, the recognition rate of the testimony comparison algorithm and the face comparison algorithm technology is improved qualitatively, and the accuracy rate of the face comparison algorithm reaches more than 99% at present. Compared with other biological feature recognition technologies, the face comparison algorithm technology has natural and unique advantages in practical application: the camera is used for directly obtaining the information, so that the identification process can be completed in a non-contact mode, and convenience and rapidness are realized. At present, the face comparison algorithm technology is applied to the fields of finance, education, scenic spots, travel, social security and the like. The application of face comparison can greatly reduce the tedious work of manual inspection and save a large amount of labor cost. The related face comparison algorithm has the problem of narrow application range caused by the fact that the comparison of multiple face images is not supported, and is mainly characterized in that the comparison of the multiple face images is not supported, the comparison can be only carried out on the larger face in the picture, and the comparison can not be carried out on the smaller face.
Disclosure of Invention
The application provides an image processing method and device based on a face recognition technology and a computer readable storage medium, which can solve the problems. The technical scheme is as follows:
in a first aspect, an image processing method based on a face recognition technology is provided, and the method includes:
acquiring an image to be identified;
determining a face detection result aiming at an image to be recognized, wherein the face detection result comprises face quantity and face coordinate related information;
if the number of the human faces is more than 1, extracting each human face area included in the image to be recognized according to the human face coordinate related information to obtain a plurality of first human face images;
similarity calculation is carried out on the plurality of first face images and a preset second face image respectively to obtain the similarity of the plurality of first face images and the second face image respectively;
and processing according to the similarity between the plurality of first face images and the second face images.
Further, the step of processing according to the similarity between the first face images and the second face images comprises:
judging whether the image to be recognized comprises a face pointed by the second face image or not based on the similarity between the first face images and the second face images;
and processing according to the judgment result and the preset application scene.
Further, based on the similarity between each of the plurality of first face images and the second face image, the step of judging whether the image to be recognized includes the face included in the second face image includes:
and if the similarity between any first face image and the second face image is greater than a preset similarity threshold, determining that the image to be recognized comprises the face pointed by the second face image.
Further, the step of calculating the similarity between the plurality of first face images and a predetermined second face image to obtain the similarity between the plurality of first face images and the second face image includes:
and determining the similarity between the plurality of first face images and the second face images respectively based on a preset image similarity algorithm.
Further, before the step of calculating the similarity between each of the plurality of first face images and the predetermined second face image, the method further includes at least one of:
acquiring a second face image by using a preset identity document extraction algorithm;
and determining a second face image pointed by the selection operation based on the selection operation aiming at the preset image database.
Further, the step of determining a face detection result for the image to be recognized includes:
inputting an image to be recognized into a preset face recognition algorithm model;
and acquiring a face detection result returned by the face recognition algorithm model.
Further, the method also includes:
if the number of the human faces is 1, similarity calculation is carried out on the image to be recognized and a second human face image;
and processing according to the similarity calculation result of the image to be recognized and the second face image.
In a second aspect, an image processing apparatus based on face recognition technology is provided, the apparatus comprising:
the compared image acquisition module is used for acquiring an image to be identified;
the image face detection module is used for determining a face detection result aiming at the image to be recognized, and the face detection result comprises the face number and face coordinate related information;
the face matting processing module is used for extracting each face region included in the image to be recognized according to the face coordinate related information to obtain a plurality of first face images if the number of the faces is greater than 1;
the multi-face comparison module is used for respectively carrying out similarity calculation on the plurality of first face images and a preset second face image to obtain the similarity of the plurality of first face images and the second face image;
and the multi-face recognition processing module is used for processing according to the similarity between the first face images and the second face images.
Further, the multi-face recognition processing module comprises:
the face determining submodule is used for judging whether the image to be recognized comprises a face pointed by the second face image or not based on the similarity between the first face images and the second face images;
and the comparison processing sub-module is used for processing according to the judgment result and a preset application scene.
Further, the face determination sub-module includes:
and the face determining unit is used for determining that the image to be recognized comprises the face pointed by the second face image if the similarity between any first face image and the second face image is greater than a preset similarity threshold value.
Further, the multi-face comparison module comprises:
and the face comparison sub-module is used for determining the similarity between the first face images and the second face images based on a preset image similarity algorithm.
Further, before the step of calculating the similarity between a plurality of first face images and a predetermined second face image, the multi-face comparison module further includes at least one of the following sub-modules:
the first comparison source determination submodule is used for acquiring the second face image by using a preset identity document extraction algorithm;
and the second comparison source determining submodule is used for determining a second face image pointed by the selection operation based on the selection operation aiming at the preset image database.
Further, the image face detection module comprises:
the compared image sending submodule is used for inputting the image to be recognized into a preset face recognition algorithm model;
and the detection result acquisition submodule is used for acquiring a face detection result returned by the face recognition algorithm model.
Further, the apparatus further comprises:
the single face image comparison module is used for calculating the similarity between the image to be recognized and the second face image if the number of the faces is 1;
and the single face recognition processing module is used for processing according to the similarity calculation result of the image to be recognized and the second face image.
In a third aspect, an image processing apparatus based on a face recognition technology is provided, including:
one or more processors;
a memory;
one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to: the image processing method based on the face recognition technology is executed.
In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, which when executed by a processor, implements the above-described image processing method based on face recognition technology.
According to the embodiment of the application, the image to be recognized is obtained, the face detection result aiming at the image to be recognized is determined, the face detection result comprises the face number and face coordinate related information, under the condition that the face number is larger than 1, each face area included by the image to be recognized is extracted according to the face coordinate related information, a plurality of first face images are obtained, the similarity calculation is carried out on the plurality of first face images and a preset second face image respectively, the similarity between the plurality of first face images and the second face image is obtained, the processing is carried out according to the similarity between the plurality of first face images and the second face image respectively, the method for extracting a plurality of faces in the image according to the face number in the image achieves the purpose of comparing all the faces included in the extracted image, the problem that only a large part of the faces are compared in the existing face recognition technology, the application range of a face comparison algorithm is narrow is solved, and the effect of improving the face comparison efficiency by expanding the application scene of face comparison is achieved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings used in the description of the embodiments of the present application will be briefly described below.
Fig. 1 is a schematic flowchart of an image processing method based on a face recognition technology according to an embodiment of the present application;
fig. 2 is a schematic diagram of a compared source according to an embodiment of an image processing method based on a face recognition technology provided in the present application;
fig. 3 is a schematic diagram of a comparison source according to an embodiment of an image processing method based on a face recognition technology provided in the embodiment of the present application;
fig. 4 is a schematic flowchart of an embodiment of an image processing method based on a face recognition technology according to the embodiment of the present application; and
fig. 5 is a schematic structural diagram of an image processing apparatus based on a face recognition technology according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary only for the purpose of explaining the present application and are not to be construed as limiting the present application.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. As used herein, the term "and/or" includes all or any element and all combinations of one or more of the associated listed items.
The following describes the technical solutions of the present application and how to solve the above technical problems with specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
The embodiment of the application provides an image processing method based on a face recognition technology, and as shown in fig. 1, the method comprises the following steps: step S101 to step S105.
And step S101, acquiring an image to be identified.
Specifically, the image to be recognized may be from a predetermined storage space, or may be obtained by real-time shooting with a camera. For example, a storage space for an album is selected through a preset interface, and the storage space is previewed and displayed, so that after a selected operation of a user is detected, an image to be recognized to which the selected operation points is acquired.
Step S102, determining a face detection result aiming at the image to be recognized, wherein the face detection result comprises face quantity and face coordinate related information.
Specifically, a pre-configured face recognition algorithm can be used for processing an image to be recognized, so that a face detection result is obtained; and the image to be recognized can be processed by utilizing a face recognition algorithm of a third party.
In the embodiment of the application, the number of the human faces represents the type of the image to be recognized. For example, in the case that the number of faces is 0, the image to be recognized refers to a non-face image, such as a scene image, a moving image, and the like; under the condition that the number of the human faces is more than 1, the image to be recognized refers to the situation that the same image comprises a plurality of users, and at the moment, one human face corresponds to one group of human face coordinates.
Specifically, the face coordinate related information may include coordinates of a face region and coordinates of an image to be recognized. For example, a coordinate system is established with the image to be recognized, and the coordinates of the face region are determined according to the coordinate system.
And S103, if the number of the human faces is more than 1, extracting each human face area included in the image to be recognized according to the human face coordinate related information to obtain a plurality of first human face images.
Specifically, the face coordinate related information may be determined according to a preset tool. For example, the preset tool is a rectangular frame, the coordinates of each face include four vertices of the rectangular frame, the face region is extracted on the image to be recognized through the coordinates of the four vertices, and the obtained rectangular region is a face image.
And step S104, respectively carrying out similarity calculation on the plurality of first face images and a preset second face image to obtain the similarity of the plurality of first face images and the second face image.
Specifically, the second facial image may be a certificate image uploaded in advance, or a facial image selected from images included in the image database.
Specifically, image features of the face image are extracted first, and the similarity is calculated according to the image features. For example, assuming that the first face image includes P1 and P2, the image feature of P1 is T11, the image feature of P2 is P12, and the image feature of the second face image is T2, the similarity between T11 and T2, and the similarity between T12 and T2 are calculated, respectively.
And S105, processing according to the similarity between the first face images and the second face images.
Specifically, whether the first face image and the second face image belong to the same user may be determined according to a preset similarity threshold. More specifically, if the similarity between the first face image and the second face image is greater than a preset similarity threshold, it is determined that the two face images belong to the same user.
According to the method, the purpose of comparing all the faces in the extracted images is achieved, the problem that the application range of a face comparison algorithm is narrow due to the fact that only a large part of the faces are compared in the existing face recognition technology is solved, and the effect of improving the face comparison efficiency through expanding the application scene of face comparison is achieved.
In some embodiments, step S105 further comprises:
step S1051 (not shown in the figure), based on the similarity between the first face images and the second face images, determining whether the image to be recognized includes a face pointed by the second face image;
step S1052 (not shown in the figure), processing is performed according to the determination result and the application scene of the face recognition.
Specifically, based on a plurality of application scenarios of face recognition configured in advance, such as an application scenario of face verification, an application scenario of video image frame retouching, an application scenario of tracking a criminal suspect, and the like, when a selected operation for the plurality of application scenarios of face recognition configured in advance is detected, the determination result of step S1051 is processed in combination with the selected operation pointing to the application scenario.
Specifically, the corresponding processing mode may be determined according to an application scenario of face recognition. For example, if the application scene is a bank counter business transaction, the second face image is an image of an identity document of a user, the image to be recognized is an image including the user and captured by a bank camera, the first face image is a face area part extracted from the image including the user, when the judgment result shows that the image to be recognized includes a face pointed by the second face image, the processing mode is an operation of jumping to a next user interface, otherwise, prompt information that the face not including the face pointed by the second face image in the image to be recognized needs to be captured again or uploaded to the image to be recognized is generated.
In some embodiments, step S1051 further comprises:
and if the similarity between any first face image and the second face image is greater than a preset similarity threshold, determining that the image to be recognized comprises the face pointed by the second face image.
Specifically, the similarity threshold may be set according to an application scenario. When the method is applied, the similarity threshold value can be adjusted in real time according to the service precision.
In some embodiments, step S104 further comprises:
and determining the similarity between the plurality of first face images and the second face images respectively based on a preset image similarity algorithm.
Specifically, the image similarity algorithm may be stored locally, and the image similarity algorithm may be called by using a preset interface to calculate the plurality of first face images and the plurality of second face images respectively; or the first face images and the second face images are respectively sent to an image similarity algorithm provided by a third party, so that the similarity between the first face images and the second face images is determined according to a result returned by the image similarity algorithm provided by the third party.
Specifically, the image similarity algorithm may be an image Hash value algorithm, an image template matching algorithm, an image ssim value, or the like.
In some embodiments, step S104 is preceded by a step of calculating similarity between each of the plurality of first face images and a predetermined second face image, and the method further comprises at least one of:
acquiring a second face image by using a preset identity document extraction algorithm;
and determining a second face image pointed by the selection operation based on the selection operation aiming at the preset image database.
In particular, the image database may be set up according to business needs. For example, assuming that the image database is set as a crime suspect database, the face image of the tracked crime suspect is determined according to the user's selection of the database.
Specifically, in the shooting process, the shooting range of the identity card photo can be limited according to a preset identity card photo shooting frame, so that after the image of the identity card is obtained, the image part is extracted and used as a second face image.
In some embodiments, step S102 further comprises:
inputting an image to be recognized into a preset face recognition algorithm model;
and obtaining a face detection result returned by the face recognition algorithm model.
Specifically, the face recognition algorithm model can be stored locally or in a server; and when the face recognition algorithm model is stored in the server, sending the image to be recognized to the server so as to enable the server to perform face detection on the image to be recognized.
In some embodiments, the method further comprises:
if the number of the faces is 1, performing similarity calculation on the image to be recognized and a second face image;
and processing according to the similarity calculation result of the image to be recognized and the second face image.
Specifically, the similarity calculation between the image to be recognized and the second face image may be performed by using a preset image similarity calculation method with reference to step S104.
To further illustrate the methods provided by the examples of the present application, a detailed description is provided below in conjunction with FIGS. 2-4.
The picture shown in fig. 2 includes two faces, one face is large, and the other face Zhang Jiaoxiao, and in the prior art, the face comparison is generally performed only on the large part of the face, that is, the face in the rectangular frame in fig. 2, with the face in the rectangular frame in fig. 3, so that there is a problem that the comparison between fig. 2 and fig. 3 fails when the large part of the face in fig. 2 is not consistent with the face in fig. 3. In order to solve the problem, referring to fig. 4, two pictures, picture a and picture B, are input, where picture a is used as an image to be identified of a compared source, and picture B is used as a second face image of the compared source (i.e., a base image); then, calling a face detection algorithm to judge whether a face exists in the picture A, if so, judging whether the number of the faces in the picture A is larger than two faces, assuming that the picture A is a picture 2 and the picture B is a picture 3, wherein the picture 2 comprises two faces, namely the number of the faces is larger than 1, and performing image matting on each face in the picture 2, namely extracting the two faces existing in the picture 2; finally, calling a face comparison algorithm to carry out comparison, namely, comparing two faces existing in the image 2 obtained by image matting with the faces in the image 3 respectively, wherein the comparison result is that the faces marked by the rectangular frames in the image 2 and the faces in the image 3 are the same user, and the comparison is successful; if only one face exists in fig. 2, the faces of fig. 2 and fig. 3 are directly compared, and if the comparison is successful, the same user is determined. During application, if no human face exists in the picture A, the picture A can be stopped to be processed, and the next compared source is called to be processed by referring to fig. 4.
In another embodiment of the present application, an image processing apparatus based on a face recognition technology is provided, as shown in fig. 5, the apparatus 20 includes: compared image acquisition module 501, image face detection module 502, face matting processing module 503, multi-face comparison module 504, and shelf layering processing module 204.
A compared image obtaining module 501, configured to obtain an image to be identified;
an image face detection module 502, configured to determine a face detection result for an image to be recognized, where the face detection result includes face number and face coordinate related information;
a face matting processing module 503, configured to extract, according to the face coordinate related information, each face region included in the image to be recognized, if the number of faces is greater than 1, to obtain a plurality of first face images;
a multi-face comparison module 504, configured to perform similarity calculation on the plurality of first face images and a predetermined second face image respectively, so as to obtain similarities between the plurality of first face images and the second face image respectively;
and the multi-face recognition processing module is used for processing according to the similarity between the first face images and the second face images.
According to the embodiment of the application, the image to be recognized is obtained, the face detection result aiming at the image to be recognized is determined, the face detection result comprises the face number and face coordinate related information, under the condition that the face number is larger than 1, each face area included by the image to be recognized is extracted according to the face coordinate related information, a plurality of first face images are obtained, the similarity calculation is carried out on the plurality of first face images and a preset second face image respectively, the similarity between the plurality of first face images and the second face image is obtained, the processing is carried out according to the similarity between the plurality of first face images and the second face image respectively, the method for extracting a plurality of faces in the image according to the face number in the image achieves the purpose of comparing all the faces included in the extracted image, the problem that only a large part of the faces are compared in the existing face recognition technology, the application range of a face comparison algorithm is narrow is solved, and the effect of improving the face comparison efficiency by expanding the application scene of face comparison is achieved.
Further, the multi-face recognition processing module comprises:
the face determining submodule is used for judging whether the image to be recognized comprises a face pointed by the second face image or not based on the similarity between the first face images and the second face images;
and the comparison processing submodule is used for processing according to the judgment result and the preset application scene.
Further, the face determination sub-module includes:
and the face determining unit is used for determining that the image to be recognized comprises a face pointed by the second face image if the similarity between any first face image and the second face image is greater than a preset similarity threshold value.
Further, the multi-face comparison module comprises:
and the face comparison sub-module is used for determining the similarity between the first face images and the second face images based on a preset image similarity algorithm.
Further, before the step of calculating the similarity between a plurality of first face images and a predetermined second face image, the multi-face comparison module further includes at least one of the following sub-modules:
the first comparison source determination submodule is used for acquiring the second face image by using a preset identity document extraction algorithm;
and the second comparison source determining submodule is used for determining a second face image pointed by the selection operation based on the selection operation aiming at the preset image database.
Further, the image face detection module comprises:
the compared image sending submodule is used for inputting the image to be recognized into a preset face recognition algorithm model;
and the detection result acquisition submodule is used for acquiring a face detection result returned by the face recognition algorithm model.
Further, the apparatus further comprises:
the single face image comparison module is used for calculating the similarity between the image to be recognized and the second face image if the number of the faces is 1;
and the single face recognition processing module is used for processing according to the similarity calculation result of the image to be recognized and the second face image.
The image processing apparatus based on the face recognition technology of this embodiment can execute the image processing method based on the face recognition technology in the first embodiment of this application, and the implementation principles thereof are similar, and are not described herein again.
Another embodiment of the present application provides a terminal, including: the image processing method based on the face recognition technology comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to realize the image processing method based on the face recognition technology.
In particular, the processor may be a CPU, general purpose processor, DSP, ASIC, FPGA or other programmable logic device, transistor logic device, hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the disclosure. A processor may also be a combination of computing functions, e.g., comprising one or more microprocessors, a DSP and a microprocessor, or the like.
In particular, the processor is coupled to the memory via a bus, which may include a path for communicating information. The bus may be a PCI bus or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc.
The memory may be, but is not limited to, ROM or other type of static storage device that can store static information and instructions, RAM or other type of dynamic storage device that can store information and instructions, EEPROM, CD-ROM or other optical disk storage, optical disk storage (including compact disk, laser disk, optical disk, digital versatile disk, blu-ray disk, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
Optionally, the memory is used for storing codes of computer programs for executing the scheme of the application, and the processor is used for controlling the execution. The processor is used for executing the application program codes stored in the memory so as to realize the actions of the image processing device based on the face recognition technology provided by the embodiment.
Yet another embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the above-mentioned image processing method based on face recognition technology.
The above-described embodiments of the apparatus are merely illustrative, and the units illustrated as separate components may or may not be physically separate, may be located in one place, or may be distributed over a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
One of ordinary skill in the art will appreciate that all or some of the steps, systems, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.
While the present invention has been described with reference to the preferred embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. An image processing method based on a face recognition technology is characterized by comprising the following steps:
acquiring an image to be identified;
determining a face detection result aiming at the image to be recognized, wherein the face detection result comprises face quantity and face coordinate related information;
if the number of the human faces is more than 1, extracting each human face area included in the image to be recognized according to the human face coordinate related information to obtain a plurality of first human face images;
similarity calculation is carried out on the plurality of first face images and a preset second face image respectively, and the similarity of the plurality of first face images and the second face image is obtained;
and processing according to the similarity between the plurality of first face images and the second face images.
2. The method according to claim 1, wherein the step of processing according to the similarity between the first face images and the second face images comprises:
judging whether the image to be recognized comprises a face pointed by the second face image or not based on the similarity between the first face images and the second face images;
and processing according to the judgment result and the preset application scene.
3. The method according to claim 2, wherein the step of determining whether the image to be recognized includes the face included in the second face image based on the similarity between the first face images and the second face images comprises:
and if the similarity between any one first face image and the second face image is larger than a preset similarity threshold value, determining that the image to be recognized comprises the face pointed by the second face image.
4. The method according to claim 1, wherein the step of calculating the similarity between each of the plurality of first face images and a predetermined second face image to obtain the similarity between each of the plurality of first face images and the predetermined second face image comprises:
and determining the similarity between the first face images and the second face images respectively based on a preset image similarity algorithm.
5. The method according to claim 1, wherein the step of calculating the similarity between each of the plurality of first face images and a predetermined second face image is preceded by at least one of:
acquiring the second face image by using a preset identity document extraction algorithm;
and determining a second face image pointed by the selection operation based on the selection operation aiming at a preset image database.
6. The method according to claim 1, wherein the step of determining the face detection result for the image to be recognized comprises:
inputting the image to be recognized into a preset face recognition algorithm model;
and acquiring a face detection result returned by the face recognition algorithm model.
7. The method of claim 1, further comprising:
if the number of the human faces is 1, similarity calculation is carried out on the image to be recognized and the second human face image;
and processing according to the similarity calculation result of the image to be recognized and the second face image.
8. An image processing apparatus based on a face recognition technology, comprising:
the compared image acquisition module is used for acquiring an image to be identified;
the image face detection module is used for determining a face detection result aiming at the image to be recognized, and the face detection result comprises face quantity and face coordinate related information;
the face matting processing module is used for extracting each face region included in the image to be recognized according to the face coordinate related information to obtain a plurality of first face images if the number of the faces is larger than 1;
the multi-face comparison module is used for calculating the similarity between the plurality of first face images and a preset second face image respectively to obtain the similarity between the plurality of first face images and the second face image respectively;
and the multi-face recognition processing module is used for processing according to the similarity between the first face images and the second face images.
9. An image processing apparatus based on a face recognition technology, comprising:
one or more processors;
a memory;
one or more applications, wherein the one or more applications are stored in the memory and configured for execution by the one or more processors, the one or more programs configured to: performing the method according to any one of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210575302.6A CN115937921A (en) | 2022-05-24 | 2022-05-24 | Image processing method, device and medium based on face recognition technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210575302.6A CN115937921A (en) | 2022-05-24 | 2022-05-24 | Image processing method, device and medium based on face recognition technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115937921A true CN115937921A (en) | 2023-04-07 |
Family
ID=86647867
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210575302.6A Pending CN115937921A (en) | 2022-05-24 | 2022-05-24 | Image processing method, device and medium based on face recognition technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115937921A (en) |
-
2022
- 2022-05-24 CN CN202210575302.6A patent/CN115937921A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110569721B (en) | Recognition model training method, image recognition method, device, equipment and medium | |
| CN109325933B (en) | Method and device for recognizing copied image | |
| KR102087882B1 (en) | Device and method for media stream recognition based on visual image matching | |
| CN110866466B (en) | Face recognition method, device, storage medium and server | |
| CN111788572A (en) | Method and system for face recognition | |
| CN108509231B (en) | VR-based application program opening method, electronic device, equipment and storage medium | |
| CN107491674B (en) | Method and device for user authentication based on characteristic information | |
| CN110675433A (en) | Video processing method and device, electronic equipment and storage medium | |
| US11087137B2 (en) | Methods and systems for identification and augmentation of video content | |
| CN112906483B (en) | Target re-identification method, device and computer readable storage medium | |
| CN110751071A (en) | Face recognition method and device, storage medium and computing equipment | |
| US9286707B1 (en) | Removing transient objects to synthesize an unobstructed image | |
| CN112115910A (en) | Face library updating method and device | |
| CN110223320B (en) | Object detection tracking method and detection tracking device | |
| CN115937921A (en) | Image processing method, device and medium based on face recognition technology | |
| CN111274965A (en) | Face recognition method and device, computer equipment and storage medium | |
| CN110968719A (en) | Face clustering method and device | |
| CN112257666B (en) | Target image content aggregation method, device, equipment and readable storage medium | |
| JP2017512398A (en) | Method and apparatus for presenting video | |
| CN114743254B (en) | Face authentication method and device, terminal equipment and storage medium | |
| CN111242020A (en) | Face recognition method and device | |
| CN113343870B (en) | Identification enabling method based on Android system mobile equipment | |
| CN112634460B (en) | Outdoor panorama generation method and device based on Haar-like features | |
| CN112633233B (en) | Engineering sample anti-counterfeiting detection method and device, computer equipment and storage medium | |
| CN114359607A (en) | Face clustering method, device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 100083 129, Floor 1, Building 5, Yard 1, Shangdi Fourth Street, Haidian District, Beijing Applicant after: Beijing Zhongkejin Finite Element Technology Co.,Ltd. Address before: 100083 129, Floor 1, Building 5, Yard 1, Shangdi Fourth Street, Haidian District, Beijing Applicant before: Beijing finite element technology Co.,Ltd. |