Image processing method, apparatus, device, and storage medium

Abstract

The present disclosure provides an image processing method, device and equipment and storage medium, relates to the field of image processing, in particular to the field of computer vision, face recognition and other artificial intelligence. The image processing method comprises: acquiring an image, the image comprising a plurality of targets; extracting feature data of the plurality of targets to obtain mixed feature data, the mixed feature data comprising: the feature data of the plurality of targets; and obtaining a matching result of the plurality of targets based on the mixed feature data. The present disclosure can improve the image processing efficiency.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of image processing, in particular to the field of artificial intelligence such as computer vision and face recognition, and more particularly to an image processing method and device, an image processing apparatus, and a storage medium. BACKGROUND

[0002] The intelligent helmet can collect a face image and learn whether the face image is a target image.

[0003] In the related art, each time a face image of a person is collected, it is sent to the cloud, and the cloud performs feature point extraction and matching, and feeds back the matching result to the intelligent helmet. SUMMARY

[0004] The present disclosure provides an image processing method and device, an image processing apparatus, and a storage medium.

[0005] According to an aspect of the present disclosure, an image processing method is provided, including: acquiring an image, the image including a plurality of targets; extracting feature data of the plurality of targets to obtain mixed feature data, the mixed feature data including the feature data of the plurality of targets; and acquiring a matching result of the plurality of targets based on the mixed feature data.

[0006] According to another aspect of the present disclosure, an image processing apparatus is provided, including: an acquisition module configured to acquire an image, the image including a plurality of targets; an extraction module configured to extract feature data of the plurality of targets to obtain mixed feature data, the mixed feature data including the feature data of the plurality of targets; and a first matching module configured to acquire a matching result of the plurality of targets based on the mixed feature data.

[0007] According to another aspect of the present disclosure, an electronic device is provided, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of the preceding aspects.

[0008] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to perform the method according to any one of the preceding aspects.

[0009] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, the computer program being executed by a processor to implement the method according to any one of the preceding aspects.

[0010] According to the technical solution of the present disclosure, the image processing efficiency can be improved.

[0011] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0012] The accompanying drawings are used to better understand the present solution and do not constitute a limitation on the present disclosure. Among them:

[0013] Figure 1 is a schematic diagram according to the first embodiment of the present disclosure;

[0014] Figure 2 is a schematic diagram according to the second embodiment of the present disclosure;

[0015] Figure 3 is a schematic diagram according to the third embodiment of the present disclosure;

[0016] Figure 4 is a schematic diagram according to the fourth embodiment of the present disclosure;

[0017] Figure 5 is a schematic diagram according to the fifth embodiment of the present disclosure;

[0018] Figure 6 is a schematic diagram of an electronic device for implementing any of the image processing methods according to the embodiments of the present disclosure. DETAILED DESCRIPTION

[0019] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to help understanding, and should be considered as merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Also, in order to be clear and concise, the description below omits the description of well-known functions and structures.

[0020] In related art, each time a person's face image is collected, it is sent to the cloud, and the cloud performs feature point extraction and recognition, and the matching result is fed back to the intelligent helmet.

[0021] However, this way needs a long processing time, and in a large flow of people or weak network situation, the application is limited.

[0022] In order to improve the image processing efficiency, the present disclosure provides the following embodiments.

[0023] Figure 1 is a schematic diagram according to the first embodiment of the present disclosure, which provides an image processing method, the method comprising:

[0024] 101. Obtain an image comprising a plurality of targets.

[0025] 102. Extract feature data of the plurality of targets to obtain mixed feature data, the mixed feature data comprising the feature data of the plurality of targets.

[0026] 103. Obtain a matching result of the plurality of targets based on the mixed feature data.

[0027] The execution subject of the embodiment can be referred to as an image processing apparatus, which can be software, hardware or a combination of software and hardware. The apparatus can be located in an electronic device. The electronic device can be located in a user terminal or a server. The server can include a local server or a cloud server. The user terminal can include a mobile device (such as a mobile phone or a tablet computer), a vehicle-mounted terminal (such as a car machine), a wearable device (such as a smart watch or a smart bracelet), a smart home device (such as a smart television or a smart speaker), a special smart device (such as a smart helmet), and the like.

[0028] The target in the image refers to an object to be detected. For example, if the image is a face image, the target is a face.

[0029] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information comply with relevant laws and regulations and do not violate public order and good customs.

[0030] After obtaining the image comprising a plurality of targets, feature extraction can be performed on each target to obtain feature data of each target. After obtaining the feature data of each target, the mixed feature data can be composed of the feature data of each target. The feature data of each target in the mixed feature data can be randomly arranged.

[0031] For example, taking a face image as an example, the feature data of N (N is 48, for example) feature points can be extracted from each face image. It is assumed that the feature data of a face image includes feature point 1 1, feature point 1 2,..., feature point 1 N, and the feature data of another face image includes feature point 2 1, feature point 2 2,..., feature point 2 N. The mixed feature data composed of the feature data of the two face images is, for example, feature point 1 1, feature point 1 2, feature point 2 1,..., feature point 1 N, feature point 2 2,..., feature point 2 N. That is, the arrangement order of the feature data of different face images is random, and it is not necessary to distinguish the feature data of each face image.

[0032] After obtaining the mixed feature data of the plurality of targets, the mixed feature data can be compared with specific data to obtain a matching result of the plurality of targets.

[0033] The specific data is feature data of a specific target pre-stored in the user terminal, and the specific target can be set according to actual needs, for example, a target image.

[0034] The matching result of the plurality of targets can be whether the plurality of targets match, that is, if the plurality of targets match, it indicates that the specific target exists in the plurality of targets, or if the plurality of targets do not match, it indicates that the specific target does not exist in the plurality of targets.

[0035] The matching result can be represented by 1 or 0, for example, 1 represents matching, and 0 represents non-matching.

[0036] Taking a target image as an example, if a target image exists in a plurality of face images included in the image, the matching result is 1, otherwise, the matching result is 0.

[0037] In the embodiments of the present disclosure, by obtaining the mixed feature data of the plurality of targets, the matching result of the plurality of targets is obtained based on the mixed feature data, which can improve the image processing efficiency compared with the matching mode of a single target.

[0038] In some embodiments, the matching result of the plurality of targets is obtained based on the mixed feature data, including: comparing the mixed feature data with specific data pre-stored in the user terminal to obtain the matching result of the plurality of targets.

[0039] Taking a target as a face image as an example, as shown in Figure 2 , the matching can be performed on the user terminal.

[0040] For example, referring to Figure 2 , the user terminal can use a camera on the user terminal to collect an image, the image can include a plurality of faces, the user terminal can perform feature extraction on each face in the plurality of faces, the feature extraction can be realized by using existing technology, so that the feature data of each face can be obtained, and the feature data of each face can be combined to form mixed feature data.

[0041] After the user terminal obtains the mixed feature data, the user terminal can compare the specific data pre-stored in the user terminal to obtain the matching result.

[0042] When matching, assuming that there are a plurality of target images, the mixed feature data can be compared with the feature data of each target image, if the mixed feature data contains the feature data of a certain target image, the matching result is matching, otherwise, it is non-matching.

[0043] Further, assuming that for each face, there are a plurality of feature points, the feature data of each feature point can be compared respectively, and when the mixed feature data contains the feature data of all feature points of the face of a certain target image, it is determined that the matching result is matching, and the current matching is ended, without the need to match the feature data of all feature points.

[0044] For example, the feature data of the face of a target image includes feature point 01, feature point 02,..., feature point 0N, and the mixed feature data includes feature point 11, feature point 12, feature point 21,..., feature point 1N, feature point 22,..., feature point 2N. It is assumed that after comparison, feature point 11, feature point 12,..., feature point 1N correspond to the same as feature point 01, feature point 02,..., feature point 0N respectively, and it is assumed that there are unmatched feature points 22,..., feature point 2N in the mixed feature data at this time. At this time, since the mixed feature data already contains the feature data of all feature points of the target image, the feature data of the unmatched feature points can no longer be matched, thereby improving processing efficiency.

[0045] Further, after obtaining the mixed feature data, the mixed feature data can be encrypted and saved for subsequent processes.

[0046] Matching through a user terminal can improve processing efficiency and can be suitable for weak network or even offline scenarios.

[0047] In some embodiments, the method further includes: sending the mixed feature data to the cloud, and receiving the matching result of the plurality of targets sent by the cloud, wherein the mixed feature data is used to compare with specific data pre-stored in the cloud to obtain the matching result.

[0048] Further, after obtaining the mixed feature data, the method further includes: encrypting the mixed feature data to obtain encrypted mixed feature data; and sending the encrypted mixed feature data to the cloud.

[0049] For example, as shown in Figure 3 , matching can be performed on the cloud.

[0050] For example, as shown in Figure 3 , the user terminal can use the camera on the user terminal to collect images, and the images can include multiple faces. The user terminal can extract features from each face in the multiple faces. Feature extraction can be achieved using existing technology, thereby obtaining feature data of each face and forming mixed feature data from the feature data of each face.

[0051] After the user terminal obtains the mixed feature data, the user terminal can send the mixed feature data to the cloud. The cloud can pre-store specific data. After the cloud receives the mixed feature data, the cloud can compare the mixed feature data with the specific data to obtain a matching result. Then, the cloud can feed back the matching result to the user terminal.

[0052] By matching through the cloud, the matching accuracy can be improved due to the powerful processing capability of the cloud.

[0053] Further, referring to Figure 3 After the user terminal obtains the mixed feature data, the user terminal can encrypt the mixed feature data to obtain encrypted mixed feature data, and send the encrypted mixed feature data to the cloud. After the cloud receives the encrypted mixed feature data, the cloud can decrypt the encrypted mixed feature data to obtain the mixed feature data. Then, the mixed feature data can be compared with the specific data pre-stored in the cloud to obtain a matching result.

[0054] It can be understood that the user terminal and the cloud use consistent encryption and decryption algorithms, so that the cloud can obtain the mixed feature data after decrypting the encrypted mixed feature data.

[0055] The matching process of the cloud is similar to the matching process of the user terminal in the previous embodiment. If there are multiple target images, the mixed feature data can be compared with the feature data of the face of each target image. If the mixed feature data contains the feature data of the face of a certain target image, the matching result is matched, otherwise it is not matched.

[0056] Further, if there are multiple feature points corresponding to each face, the feature data of each feature point can be compared respectively, and when the mixed feature data contains the feature data of all feature points of the face of a certain target image, it is determined that the matching result is matched, and the current matching is ended without the need to match all the feature data of the feature points.

[0057] For example, the feature data of the face of a certain target image includes feature point 01, feature point 02,..., feature point 0N, and the mixed feature data includes feature point 11, feature point 12, feature point 21,..., feature point 1N, feature point 22,..., feature point 2N. After comparison, it is assumed that feature point 11, feature point 12,..., feature point 1N correspond to the same as feature point 01, feature point 02,..., feature point 0N respectively. It is assumed that at this time, there are unmatched feature points 22,..., feature point 2N in the mixed feature data. At this time, since the mixed feature data already contains the feature data of all feature points of the target image, the feature data of the unmatched feature points can no longer be matched, thereby improving the processing efficiency.

[0058] The mixed feature data is encrypted, so that the security of the mixed feature data is protected, and the privacy of the user is protected.

[0059] In some embodiments, the method further includes: if the matching result is matching, collecting an image of each target in the plurality of targets; and based on the image of each target, obtaining a matching result of each target.

[0060] For example, an image includes 30 face images, and after the matching process of the user terminal or the cloud, it is determined that the matching result is matching, that is, the 30 face images include the target image. At this time, the matching process of a single face image can be used to determine which one or more of the 30 face images is the target image.

[0061] The matching process of a single face image, for example, the user terminal can collect the face image of each person in turn, and send the face image of a single person to the cloud. After the cloud performs feature extraction and feature data matching, the target image in the 30 face images of the 30 people is determined. Alternatively, after the user terminal collects the face image of a single person, the face image of the single person can be extracted to obtain the feature data of the single person, and the feature data of the single person or the encrypted feature data of the single person is sent to the cloud for feature data matching.

[0062] By obtaining the matching result of each target based on the image of each target, the specific single target can be located.

[0063] In some embodiments, the method further includes: if the mixed feature data includes pre-stored specific data, determining that the matching result is matching.

[0064] That is, in this embodiment, when determining the matching of multiple targets, attention is paid to whether the mixed feature data includes specific data. If it does, the matching result is matching, otherwise it is not matching, and attention is not paid to which target the matching feature data is of.

[0065] By including specific data in the mixed feature data, the matching result is matching, which can improve the determination efficiency.

[0066] In some embodiments, the target is a face, and the method further includes: using a special intelligent device for collecting faces to collect a face image including multiple faces.

[0067] The special intelligent device is, for example, a smart helmet. In a high-traffic scene, such as a train station, a smart helmet can be worn by a check person to collect an image including multiple faces each time, for example, an image collected each time can include about 30 faces.

[0068] Afterwards, the matching results of the 30 face images can be obtained through the process of any of the above embodiments, such as determining whether the target image exists in the 30 face images.

[0069] The image containing multiple face images can be collected by the special intelligent device, and the face recognition can be applied to the special field.

[0070] Figure 4 is a schematic diagram of the fourth embodiment of the present disclosure, which takes the interaction between the intelligent helmet and the cloud as an example. The present embodiment provides an image processing method, which comprises:

[0071] 401. The intelligent helmet collects face images containing multiple faces.

[0072] For example, in a scene with a large number of people, such as a train station, an airport, etc., the detection personnel can wear an intelligent helmet to collect face images, and at this time, each face image can contain multiple faces.

[0073] 402. The intelligent helmet extracts feature data of each face in the multiple faces to obtain mixed feature data.

[0074] For example, the feature data extraction algorithm can be pre-set in the intelligent helmet, and the existing algorithm can be used to extract the feature data of the face, and the feature data of multiple faces can be mixed together to form mixed feature data.

[0075] 403. The intelligent helmet encrypts the mixed feature data to obtain encrypted mixed feature data.

[0076] Among them, the existing encryption algorithm can be used for encryption processing.

[0077] 404. The intelligent helmet sends the encrypted mixed feature data to the cloud.

[0078] 405. The cloud decrypts the encrypted mixed feature data to obtain the mixed feature data.

[0079] Among them, the intelligent helmet and the cloud can be pre-configured with consistent encryption and decryption algorithms, so that the cloud can decrypt the encrypted mixed feature data to obtain the mixed feature data.

[0080] 406. The cloud compares the mixed feature data with the pre-stored specific data to obtain a matching result.

[0081] Among them, the specific data can be the face feature data of the target image, and the target image can be multiple. When comparing, the mixed feature data can be compared with the face feature data of each target image to obtain a matching result.

[0082] Further, taking the facial feature data of a certain target image as an example, in the comparison, the comparison can be ended when the facial feature data of A exists in the mixed feature data, without the need to match all the mixed feature data.

[0083] 407. The cloud sends the matching result to the smart helmet.

[0084] 408. The smart helmet judges whether the matching result is a match. If yes, step 410 is performed, otherwise step 409 is performed.

[0085] 409. End this matching.

[0086] After that, a new facial image containing multiple faces can be re-collected and subsequent steps can be performed.

[0087] 410. Perform the matching process of a single facial image.

[0088] For example, the smart helmet collects the facial image of each face in the multiple faces to obtain a single facial image of each face, and sends the single facial image to the cloud. After receiving the single facial image, the cloud can perform feature extraction to obtain feature data of the single facial image. Then, the cloud can compare the feature data of the single facial image with the pre-stored facial feature data of the target image to determine whether the single facial image is the target image.

[0089] The above example of cloud comparison can be understood as that the comparison of the single facial image can also be performed locally on the user terminal.

[0090] The above example of the user terminal sending the single facial image to the cloud can be understood as that the user terminal can also extract the feature data of the single facial image, send the feature data of the single facial image or the encrypted feature data of the single facial image to the cloud, and the cloud compares the feature data of the single facial image with the pre-stored facial feature data of the target image.

[0091] It can be understood that the contents not described in detail in the present embodiment can be referred to the related descriptions in other embodiments.

[0092] It can be understood that the timing relationship between the above steps is not limited without timing limitation.

[0093] In the present embodiment, by comparing the mixed feature data of multiple targets, the processing efficiency can be improved; by sending the mixed feature data to the cloud instead of the single facial image, the data transmission amount can be reduced; by encrypting the mixed feature data, the user privacy can be protected. Therefore, by combining the above process steps, the matching speed can be accelerated to achieve weak network millisecond-level batch matching.

[0094] Figure 5 is a schematic diagram of a fifth embodiment of the present disclosure, and the embodiment provides an image processing apparatus, which comprises an acquisition module 501, an extraction module 502, and a first matching module 503.

[0095] The acquisition module 501 is configured to acquire an image comprising a plurality of targets; the extraction module 502 is configured to extract feature data of the plurality of targets to obtain mixed feature data, wherein the mixed feature data comprises the feature data of the plurality of targets; and the first matching module 503 is configured to acquire a matching result of the plurality of targets based on the mixed feature data.

[0096] In some embodiments, the first matching module 503 is specifically configured to:

[0097] compare the mixed feature data with specific data pre-stored locally by a user terminal to obtain the matching result of the plurality of targets.

[0098] In some embodiments, the first matching module 503 is specifically configured to: send the mixed feature data to a cloud server, and receive the matching result of the plurality of targets sent by the cloud server, wherein the mixed feature data is used to be compared with specific data pre-stored by the cloud server to obtain the matching result.

[0099] In some embodiments, the apparatus 500 further comprises an encryption module configured to perform encryption processing on the mixed feature data to obtain encrypted mixed feature data; and the first matching module 503 is specifically configured to send the encrypted mixed feature data to the cloud server.

[0100] In some embodiments, the apparatus 500 further comprises a collection module configured to collect images of each target in the plurality of targets if the matching result is matching; and a second matching module configured to acquire a matching result of each target based on the images of each target.

[0101] In some embodiments, the first matching module 503 is specifically configured to: if the mixed feature data comprises pre-stored specific data, determine that the matching result is matching.

[0102] In some embodiments, the target is a face, and the acquisition module 501 is specifically configured to collect face images comprising a plurality of faces by using a special intelligent device for collecting faces.

[0103] In the embodiments of the present disclosure, the mixed feature data of the plurality of targets is obtained, and the matching result of the plurality of targets is obtained based on the mixed feature data, which can improve the image processing efficiency compared with the matching mode of a single target.

[0104] It can be understood that the same or similar content in different embodiments in the embodiments of the present disclosure can be referred to each other.

[0105] It can be understood that "first", "second" and the like in the embodiments of the present disclosure are only used for distinction, and do not represent importance, time sequence and the like.

[0106] According to the embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0107] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, servers, blades, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present disclosure described and / or claimed in this document.

[0108] As shown in Figure 6 The electronic device 600 includes a computing unit 601 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. Various programs and data required for the operation of the electronic device 600 can also be stored in the RAM 603. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0109] Various components in the electronic device 600 are connected to the I / O interface 605, including an input unit 606, such as a keyboard, a mouse, and the like; an output unit 607, such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, an optical disk, and the like; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 609 allows the electronic device 600 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0110] The computing unit 601 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 601 performs various methods and processes described above, such as the image processing method. For example, in some embodiments, the image processing method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded onto the RAM 603 and executed by the computing unit 601, one or more steps of the image processing method described above can be performed. Alternatively, in other embodiments, the computing unit 601 can be configured to perform the image processing method by any other appropriate means, such as by means of firmware.

[0111] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a complex programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0112] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or the block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0113] In the context of this disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0114] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0115] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0116] The computer system can include clients and servers. This relationship can be. The servers are generally remote from the users and can be accessed via the Internet using a communication network. The relationship can be a client-server relationship over a communications network, and as such, the servers can be accessed by the clients using computer programs. The servers can be cloud servers, also known as cloud computing servers or cloud hosts, which are mainframe products in the cloud computing service system, and solve the defects of large management difficulty and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or simply "VPS").

[0117] It should be understood that the various forms of flow shown above can be reordered, added to, or have steps deleted. For example, the steps described in the present disclosure can be performed in parallel, in series, or in a different order, as long as the desired results of the technical solutions of the present disclosure can be achieved, and the present disclosure is not limited herein.

[0118] The above detailed description does not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. An image processing method, comprising: obtaining an image, the image comprising a plurality of targets; extracting feature data of the plurality of targets to obtain mixed feature data, the mixed feature data comprising feature data of the plurality of targets, and feature data of each target being randomly arranged; obtaining a matching result of the plurality of targets based on the mixed feature data, comprising: if the mixed feature data comprises pre-stored specific data, determining that the matching result is matching, and ending the current matching; if the matching result is matching, collecting an image of each target in the plurality of targets; obtaining a matching result of each target based on the image of each target; if the matching result of the plurality of targets is not matching, obtaining a new image comprising a plurality of targets and performing subsequent steps; the obtaining of the matching result of the plurality of targets based on the mixed feature data comprises: sending the mixed feature data to a cloud, and receiving the matching result of the plurality of targets sent by the cloud, the mixed feature data being used to compare with pre-stored specific data of the cloud to obtain the matching result.

2. The method of claim 1, after the obtaining of the mixed feature data, the method further comprises: encrypting the mixed feature data to obtain encrypted mixed feature data; the sending of the mixed feature data to the cloud comprises: sending the encrypted mixed feature data to the cloud.

3. The method according to any one of claims 1-2, wherein, The target is a face, and the obtaining of the image comprises: using a special intelligent device for collecting a face to collect a face image comprising a plurality of faces.

4. An image processing apparatus, comprising: an obtaining module configured to obtain an image, the image comprising a plurality of targets; an extracting module configured to extract feature data of the plurality of targets to obtain mixed feature data, the mixed feature data comprising feature data of the plurality of targets, and feature data of each target being randomly arranged; a first matching module configured to obtain a matching result of the plurality of targets based on the mixed feature data, comprising: if the mixed feature data comprises pre-stored specific data, determining that the matching result is matching, and ending the current matching; and if the matching result of the plurality of targets is not matching, re-triggering execution of the obtaining module and subsequent modules; a collecting module configured to, if the matching result obtained by the first matching module is matching, collect an image of each target in the plurality of targets; a second matching module configured to obtain a matching result of each target based on the image of each target; the first matching module is specifically configured to: send the mixed feature data to a cloud, and receive the matching result of the plurality of targets sent by the cloud, the mixed feature data being used to compare with pre-stored specific data of the cloud to obtain the matching result.

5. The apparatus of claim 4, further comprising: an encryption module configured to encrypt the mixed feature data to obtain encrypted mixed feature data; the first matching module is specifically configured to: send the encrypted mixed feature data to the cloud.

6. The apparatus of any one of claims 4-5, wherein, The target is a human face, and the acquisition module is specifically configured to: A special intelligent device for collecting human faces is adopted to collect the human face image including multiple human faces. 7.An electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-3.

8. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to perform the method of any one of claims 1-3. 9.A computer program product comprising a computer program which, when executed by a processor, implements the method of any one of claims 1-3.

Images