Personnel identity recognition method and device and related equipment

Abstract

The embodiment of the invention provides a personnel identity recognition method and device and related equipment. The method comprises the steps of generating target stylized image encryption data according to a target image; according to the target stylized image encryption data and the target collection image data, target person identities are recognized, and the target person identities comprise stranger identities and / or non-stranger identities; and executing the target operation according to the identity of the target person. In this way, the privacy leakage risk of the user can be reduced while the personnel identity recognition precision is ensured, and the protection of the privacy of the user is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computer technology, and in particular to a method, apparatus, and related equipment for identifying a person. Background Art

[0002] Personnel identity recognition mainly uses technical means to confirm or verify the identity of a person. Personnel identity recognition technology is widely used in security systems, access control, financial transactions, smart device unlocking and other fields.

[0003] At present, most related technologies compare the facial images collected by the collection end with the facial images stored in the cloud platform to identify the identity of the visitor. The above method has problems such as easy to cause user privacy leakage. Summary of the Invention

[0004] According to the embodiments of the present application, a personnel identity recognition method, apparatus, and related equipment are provided, which can reduce the risk of user privacy leakage while ensuring the accuracy of personnel identity recognition and improve the protection of user privacy.

[0005] In a first aspect of the present application, a method for identifying a person is provided, comprising: Generate target stylized image encryption data according to the target image; Identify the identity of the target person according to the target stylized image encrypted data and the target collected image data, wherein the target person identity includes: a stranger identity and / or a non-stranger identity; Execute target operations based on the identity of the target person.

[0006] In some feasible implementations, generating target stylized image encrypted data based on the target image includes: Determine target features based on the target image; Generate target stylized images based on target features; The target features include: target spacing features, target outline features, target skeleton features, target hairstyle features, target attribute features, and / or target clothing features.

[0007] In some feasible implementations, generating a stylized image of a target based on target features includes: Determine the target relative coordinate information based on the target spacing characteristics; generating target relative angle information according to target contour features and / or target bone features; A first target stylized image is generated according to the target relative coordinate information and / or the target relative angle information.

[0008] In some feasible implementations, the above method further includes: According to the target attribute feature, a corresponding target feature processing operation is performed on the first target stylized image to generate a second target stylized image.

[0009] In some feasible implementations, the above method further includes: A target encryption operation is performed on the second target stylized image to generate target stylized image encrypted data, wherein the target encryption operation includes: a target salting operation and / or a target key encryption operation.

[0010] In some feasible implementations, the above-mentioned identification of the target person based on the target stylized image encrypted data and the target captured image data includes: Determine target difference features based on target stylized image encryption data and target collected image data; When it is determined that the difference value of any target difference feature is greater than the corresponding preset threshold, it is determined that the identity of the target person corresponds to the identity of a stranger.

[0011] In some feasible implementations, the above-mentioned execution of the target operation based on the identity of the target person includes: When it is determined that the identity of the target person corresponds to the identity of a stranger, a target alarm operation is performed.

[0012] In a second aspect of the present application, a personal identification device is provided, comprising: A generating unit, configured to generate target stylized image encryption data according to a target image; an identification unit, configured to identify the identity of a target person based on the target stylized image encrypted data and the target captured image data, wherein the target person identity includes: a stranger identity and / or a non-stranger identity; The execution unit is used to execute the target operation according to the identity of the target person.

[0013] In a third aspect of the present application, an electronic device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the method described above when executing the computer program.

[0014] In a fourth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method described above is implemented.

[0015] The present application provides a method, apparatus, and related equipment for identifying a person. The method includes: generating encrypted data of a stylized target image based on a target image; identifying the identity of a target person based on the encrypted data of the stylized target image and the target captured image data, wherein the target person identity includes a stranger identity and / or a non-stranger identity; and performing a target operation based on the target person identity. This application can ensure the accuracy of person identification while reducing the risk of user privacy leakage and improving the protection of user privacy.

[0016] It should be understood that the contents described in the Summary of the Invention are not intended to limit the key or important features of the embodiments of the present application, nor are they intended to limit the scope of the present application. Other features of the present application will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein: Figure 1 A schematic diagram of a process for identifying a person according to an embodiment of the present application; Figure 2 A structural diagram of a personal identification device provided according to an embodiment of the present application; Figure 3 Schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present application. DETAILED DESCRIPTION

[0018] To make the purpose, technical solutions, and advantages of the embodiments of the present disclosure more clear, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of the present disclosure.

[0019] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the related objects are in an "or" relationship.

[0020] In a first aspect of the present application, a method for identifying a person's identity is provided. Figure 1 A flow chart of a method 100 for identifying a person according to an embodiment of the present application is shown in FIG. Figure 1As shown, the method 100 includes: Step S1: Generate target stylized image encryption data based on the target image.

[0021] For example, the target user can capture and generate the target image using the target app, and / or upload the target image through the target terminal's corresponding image library to generate the target stylized image encrypted data. The target terminal may include a mobile phone, PC, and / or tablet. The storage location of the target image can be displayed on the target app's corresponding interface.

[0022] It should be noted that the clarity of the target image is greater than or equal to a preset clarity threshold, and / or the occlusion rate of the target image is less than a preset occlusion rate.

[0023] Exemplarily, the target user can follow the prompts on the corresponding interface of the target App to make the clarity of the target image greater than or equal to a preset clarity threshold, and / or the occlusion rate of the target image less than a preset occlusion rate.

[0024] Among them, the above-mentioned preset clarity threshold is positively correlated with the recognition accuracy requirement of the target person's identity and / or the execution accuracy requirement of the target operation, that is, the higher the recognition accuracy requirement of the target person's identity and / or the execution accuracy requirement of the target operation, the higher the above-mentioned preset clarity threshold.

[0025] Among them, the above-mentioned preset occlusion rate is negatively correlated with the recognition accuracy requirement of the target person's identity and / or the execution accuracy requirement of the target operation, that is, the higher the recognition accuracy requirement of the target person's identity and / or the execution accuracy requirement of the target operation, the lower the above-mentioned preset occlusion rate.

[0026] It should be noted that, in some feasible implementations, multiple sets of target stylized image encryption data can be generated based on multiple target images to improve the recognition accuracy and efficiency of the target person's identity, and / or the execution accuracy and efficiency of the target operation.

[0027] Exemplarily, corresponding target stylized image encryption data can be generated based on the corresponding target image of the target user before makeup; corresponding target stylized image encryption data can also be generated based on the corresponding target image of the target user after makeup; so as to improve the recognition accuracy and efficiency of the target person's identity, and / or the execution accuracy and efficiency of the target operation.

[0028] In some feasible implementations, the above step S1: generating target stylized image encrypted data according to the target image, includes: Step S11: Determine target features based on the target image; wherein the target features include: target spacing features, target contour features, target skeleton features, target hairstyle features, target attribute features, and / or target clothing features.

[0029] It should be noted that the above-mentioned target spacing features, target contour features, target bone features, target hairstyle features, target attribute features, and / or target clothing features can be determined based on multiple target images to improve the determination accuracy of the target spacing features, target contour features, target bone features, target hairstyle features, target attribute features, and / or target clothing features.

[0030] Exemplarily, the target distance features may include facial features distance features, such as eye distance features, eyebrow distance features, and / or nose-mouth distance features.

[0031] For example, the target contour features may include target facial contour point features and / or target contour line features. The target facial contour point features may correspond to prominent point features on the target user's face. The target contour line features may include target jawline features.

[0032] Illustratively, the target bone feature may include a target zygomatic bone feature, such as a target zygomatic bone position feature.

[0033] Illustratively, the target hairstyle characteristics may include hair shape characteristics, such as hair color, hair length characteristics, and / or hair curl characteristics.

[0034] Exemplarily, the above-mentioned target attribute characteristics may include: age attribute characteristics, and / or gender attribute characteristics, etc.

[0035] For example, the target clothing characteristics may include: accessories worn characteristics, and / or clothing preference characteristics, etc.

[0036] Step S12: Generate a target stylized image based on the target features.

[0037] For example, the target spacing features, target outline features, target skeleton features, target hairstyle features, target attribute features, and / or target clothing features may be abstracted to generate the target stylized image. The target stylized image may include a target cartoon stylized image, etc.

[0038] Therefore, the above method can accurately determine the target spacing characteristics, target contour characteristics, target bone characteristics, target hairstyle characteristics, target attribute characteristics, and / or target clothing characteristics corresponding to the target user based on the target image corresponding to the target user, so as to improve the generation accuracy of the target stylized image corresponding to the target user, thereby improving the generation accuracy of the target stylized image encrypted data.

[0039] In some feasible implementations, the above step S12: generating a target stylized image according to target features, includes: Step S121: Determine target relative coordinate information based on target spacing characteristics.

[0040] Exemplarily, the relative coordinate information between the two eyes, the relative coordinate information between the eyes and eyebrows, and / or the relative coordinate information between the nose and mouth, etc. can be determined based on the above-mentioned eye distance features, eyebrow distance features, and / or nose-to-mouth distance features, so as to determine the relative position between the two eyes, the relative position between the eyes and eyebrows, and / or the relative position between the nose and mouth, etc. based on the above-mentioned relative coordinate information between the two eyes, the relative coordinate information between the eyes and eyebrows, and / or the relative coordinate information between the nose and mouth, etc.

[0041] Specifically, the relative position between the two eyes can be determined based on the distance between the inner corners of the eyes; the relative position between the eyes and eyebrows can be determined based on the vertical distance from the eyebrows to the eyes; and the relative position between the nose and mouth can be determined based on the vertical distance from the nose tip to the peak of the lips.

[0042] Step S122: Generate target relative angle information based on target contour features and / or target bone features.

[0043] For example, the angle information between the mandibular angle connection line and the horizontal plane can be determined based on the target mandibular line features, and / or the angle information between the zygomatic highest point connection line and the horizontal plane can be determined based on the target zygomatic bone features.

[0044] Step S123: Generate a first target stylized image according to the target relative coordinate information and / or the target relative angle information.

[0045] For example, the first target stylized image can be generated based on the relative coordinate information between the eyes, the relative coordinate information between the eyes and eyebrows, the relative coordinate information between the nose and mouth, the angle information between the jaw angle line and the horizontal plane, and / or the angle information between the highest point of the cheekbones and the horizontal plane.

[0046] Specifically, the target cartoon stylized image can be generated based on the relative coordinate information between the eyes, the relative coordinate information between the eyes and eyebrows, the relative coordinate information between the nose and mouth, the angle information between the jaw angle connection line and the horizontal plane, and / or the angle information between the highest point of the cheekbones and the horizontal plane.

[0047] Therefore, the above method can accurately determine the corresponding target relative coordinate information based on the above target spacing characteristics, accurately generate target relative angle information based on the above target contour characteristics and / or target bone characteristics, and accurately generate a first target stylized image based on the above target relative coordinate information and / or target relative angle information. This is conducive to ensuring that the first target stylized image carries the relative position information between the target user's eyes, the relative position information between the eyes and eyebrows, the relative position information between the nose and mouth, the angle information between the jaw angle line and the horizontal plane, and / or the angle information between the highest point of the zygomatic bone and the horizontal plane, to achieve the initial encryption of the target image corresponding to the target user, so as to provide data support for accurately identifying the target person's identity based on the encrypted data of the target stylized image and the target collected image data, ensure the accuracy of personnel identity recognition, reduce the risk of user privacy leakage, and improve the protection of user privacy.

[0048] In some feasible implementations, the above step S12: generating a target stylized image according to target features, further includes: Step S124: performing corresponding target feature processing operations on the first target stylized image according to the target attribute features to generate a second target stylized image.

[0049] For example, a corresponding skin feature processing operation and / or a hair feature processing operation may be performed on the first target stylized image according to the age attribute feature to generate the second target stylized image.

[0050] Specifically, when it is determined that the age of the target user is greater than or equal to 1 year old and less than or equal to 6 years old, a facial rounding operation may be performed on the first target stylized image to generate the second target stylized image.

[0051] Specifically, when it is determined that the target user is older than or equal to 7 years old and younger than or equal to 17 years old, an acne-adding processing operation may be performed on the first target stylized image to generate the second target stylized image.

[0052] Specifically, when it is determined that the target user is older than or equal to 18 and younger than or equal to 35, a skin smoothing operation may be performed on the first target stylized image to generate the second target stylized image.

[0053] Specifically, when it is determined that the target user is older than or equal to 36 and younger than or equal to 50, a processing operation of adding a small number of wrinkles to the forehead may be performed on the first target stylized image to generate the second target stylized image.

[0054] Specifically, when it is determined that the age of the target user is greater than or equal to 51 years old, eyebrow and / or hair thinning processing operations may be performed on the first target stylized image to generate the second target stylized image.

[0055] It should be noted that a feature magnification operation, a feature shortening operation, and / or a contour softening operation may be performed on the first target stylized image to generate the second target stylized image.

[0056] Specifically, the above steps S121 to S124 can be input into a target diffusion model (Diffusion Model) for training and optimization to obtain a Diaffusion Model variant (Diaffusion Model Y, DMY), so as to generate a target noisy image based on the DMY model, and then perform target denoising on the target noisy image to obtain the above second target stylized image.

[0057] It should be noted that the above method performs corresponding target feature processing operations on the first target stylized image carrying the relative position information between the target user's eyes, the relative position information between the eyes and eyebrows, the relative position information between the nose and mouth, the angle information between the jaw angle line and the horizontal plane, and / or the angle information between the highest point of the cheekbones and the horizontal plane according to the target attribute characteristics to generate a second target stylized image, which is conducive to achieving secondary encryption of the target image corresponding to the target user, so as to provide data support for accurately identifying the target person's identity based on the encrypted data and target collected image data according to the target stylized image, thereby ensuring the accuracy of personnel identity recognition, further reducing the risk of user privacy leakage, and further improving the protection of user privacy.

[0058] In some feasible implementations, the above step S1: generating target stylized image encrypted data according to the target image, further includes: Step S13: Perform a target encryption operation on the second target stylized image to generate target stylized image encrypted data, wherein the target encryption operation includes: a target salting operation and / or a target key encryption operation.

[0059] For example, a dynamic salt value may be generated based on the target user's account information to perform a target salting operation on the second target stylized image to generate the target stylized image encrypted data.

[0060] Specifically, the dynamic salt value and the target user's account may be bound to generate a target dynamic salt value, and a target salting operation may be performed on the second target stylized image to generate the target stylized image encrypted data.

[0061] For example, a target key may be generated based on the device information of the target user to perform a target key encryption operation on the second target stylized image to generate the target stylized image encrypted data.

[0062] Specifically, the target key can be generated based on the target user's International Mobile Equipment Identity (IMEI) and the target feature vector corresponding to the target user, such as the target user's facial vector, to perform a target key encryption operation on the second target stylized image to generate the target stylized image encrypted data. For example, a SHA-256 target key can be generated based on the first six digits of the target user's mobile phone's International Mobile Equipment Identity (IMEI) and the target feature vector corresponding to the target user, such as the target user's facial vector, to perform a target key encryption operation on the second target stylized image to generate the target stylized image encrypted data.

[0063] It should be noted that the non-zero number corresponding to the target position of the above target key can also be inserted into the interval of the above dynamic salt value as a salt value, and the salt value can be inserted into the target feature vector corresponding to the above target user, for example, the face vector corresponding to the target user.

[0064] It should be noted that after completing the target feature vector corresponding to the above-mentioned target user, for example, after the salting operation of the face vector corresponding to the target user, the AES encryption operation can be performed according to the above-mentioned target key, and then the above-mentioned target key can be spliced ​​to the end to generate the above-mentioned target stylized image encrypted data, and the above-mentioned target stylized image encrypted data can be stored in the target storage location, and the target image of the target user can be deleted.

[0065] For example, the dynamic salt value can be: dK9pR3FqY0JzTmV0, where the number of bits in the dynamic salt value is random. The first six digits of the mobile phone IMEI can be: 358224. The facial feature data can be: [0.768, -0.234, 0.512, ..., 0.021], where the facial feature data can be: 128 floating-point numbers, 256 floating-point numbers, 512 floating-point numbers, etc. The facial feature data can be concatenated with the first six digits of the mobile phone IMEI to generate a string of data, which can be encrypted using SHA256 to obtain a 64-bit target key. For example: 8bc1ff051c6a205f961e38b92dd9bfc3a412a397024d38fa1892febbe7a74ffb. Based on the target key, the target salting interval can be determined. For example, the target salting interval can be determined by finding the target number starting from the last digit of the target key. For example, the target salting interval can be determined to be 4. Then, one digit of the salt value can be inserted into the facial feature data at intervals of 4. The resulting data after salting may be: [0.7d68, -K0.2394, 0.p512, R...]. Note that the data above is not complete; only dK9pR has been inserted. Salting can be continued until all salt values ​​have been inserted. AES encryption can then be performed on the target key and the salted data to produce a string of data, which can then be concatenated with the target key to complete the encryption operation.

[0066] It should be noted that even if the encrypted data of the above-mentioned target stylized image is illegally obtained, the illegal acquirer will not be able to view the target image carrying the target user's facial data, but can only view the target stylized image, which is conducive to improving the protection of the target user's privacy.

[0067] Therefore, the above method performs a target salting operation and / or a target key encryption operation on the second target stylized image generated by the target processing operation to accurately generate target stylized image encryption data, which is conducive to achieving three encryption of the target image corresponding to the target user, so as to provide data support for accurately identifying the identity of the target person based on the target stylized image encryption data and the target collected image data, thereby ensuring the accuracy of personnel identity recognition, further reducing the risk of user privacy leakage, and further improving the protection of user privacy.

[0068] Step S2: Identify the target person's identity based on the target stylized image encryption data and the target captured image data, wherein the target person's identity includes: a stranger identity and / or a non-stranger identity.

[0069] Exemplarily, the target collected image data may be obtained based on an Internet Protocol Camera (IPC).

[0070] Specifically, the interactive comparison between the encrypted data of the target stylized image and the captured image data of the target can be implemented based on Bluetooth communication to improve data transmission efficiency and reduce the probability of data being illegally intercepted.

[0071] In some feasible implementations, the above step S2: identifying the identity of the target person based on the target stylized image encrypted data and the target captured image data, includes: Step S21: Determine target difference features based on the target stylized image encryption data and the target captured image data.

[0072] It should be noted that a first decryption operation can be performed on the encrypted data of the target stylized image to generate a second target stylized image; a corresponding de-stylization processing operation can be performed on the above-mentioned second target stylized image to generate a first target stylized image; a corresponding de-stylization processing operation can be performed on the above-mentioned first target stylized image to determine the target features corresponding to the target user; based on the above-mentioned target acquisition image data, the target features corresponding to the target acquisition image data are determined; and the target difference features are determined by comparing the target features corresponding to the encrypted data of the target stylized image with the target features corresponding to the target acquisition image data.

[0073] Exemplarily, a first decryption operation can be performed on the encrypted data of the target stylized image to generate a second target stylized image; a corresponding de-stylization processing operation can be performed on the above-mentioned second target stylized image to generate a first target stylized image; a corresponding de-stylization processing operation can be performed on the above-mentioned first target stylized image to determine the target spacing characteristics, target contour characteristics, target bone characteristics, target hairstyle characteristics, target attribute characteristics, and / or target clothing characteristics corresponding to the target user; based on the above-mentioned target collected image data, the corresponding target spacing characteristics, target contour characteristics, target bone characteristics, target hairstyle characteristics, target attribute characteristics, and / or target clothing characteristics, etc. are determined to compare and determine the above-mentioned target difference characteristics.

[0074] Step S22: When it is determined that the difference value of any target difference feature is greater than the corresponding preset threshold, it is determined that the identity of the target person corresponds to the identity of a stranger.

[0075] Exemplarily, when it is determined that the difference value corresponding to the target distance feature is greater than the corresponding preset threshold, it can be determined that the target person identity corresponds to the stranger identity.

[0076] Exemplarily, when it is determined that the difference value corresponding to the target profile feature is greater than the corresponding preset threshold, it can be determined that the target person identity corresponds to the stranger identity.

[0077] Exemplarily, when it is determined that the difference value corresponding to the target bone feature is greater than the corresponding preset threshold, it can be determined that the identity of the target person corresponds to the identity of a stranger.

[0078] Exemplarily, when it is determined that the difference value corresponding to the target hairstyle feature is greater than the corresponding preset threshold, it can be determined that the target person identity corresponds to the stranger identity.

[0079] Exemplarily, when it is determined that the difference value corresponding to the target attribute feature is greater than the corresponding preset threshold, it can be determined that the target person identity corresponds to the stranger identity.

[0080] Exemplarily, when the difference value corresponding to the target clothing feature is greater than the corresponding preset threshold, it can be determined that the target person's identity corresponds to the stranger's identity.

[0081] It should be noted that the difference values ​​corresponding to the above-mentioned target spacing features, the difference values ​​corresponding to the target contour features, the difference values ​​corresponding to the target bone features, the difference values ​​corresponding to the target hairstyle features, the difference values ​​corresponding to the target attribute features, and / or the difference values ​​corresponding to the target clothing features can be set differently according to the contribution of the above-mentioned target spacing features, target contour features, target bone features, target hairstyle features, target attribute features, and / or target clothing features to the recognition accuracy of the target person's identity, and / or the execution accuracy of the target operation.

[0082] Specifically, the difference value corresponding to the target attribute feature can be set to be smaller than the difference value corresponding to the target spacing feature; the difference value corresponding to the target spacing feature can be set to be smaller than the difference value corresponding to the target bone feature; the difference value corresponding to the target bone feature can be set to be smaller than the difference value corresponding to the target contour feature; the difference value corresponding to the target contour feature can be set to be smaller than the difference value corresponding to the target hairstyle feature; the difference value corresponding to the target hairstyle feature can be set to be smaller than the difference value corresponding to the target clothing feature.

[0083] It should be noted that, in the case of the above-mentioned target person identification error, the target user can perform a corrective operation.

[0084] Exemplarily, based on the above-mentioned correction operation, the difference value corresponding to the target spacing feature, the difference value corresponding to the target contour feature, the difference value corresponding to the target bone feature, the difference value corresponding to the target hairstyle feature, the difference value corresponding to the target attribute feature, and / or the difference value corresponding to the target clothing feature can be automatically corrected to further improve the accuracy of target person identity recognition.

[0085] Therefore, the above method can accurately determine the target difference characteristics based on the target stylized image encryption data and the target collected image data; when it is determined that the difference value of any target difference characteristic is greater than the corresponding preset threshold, the target person identity is accurately and automatically determined to correspond to the stranger identity, which is beneficial to improve the recognition accuracy and recognition efficiency of the stranger identity while reducing the risk of user privacy leakage and improving the protection of user privacy.

[0086] Step S3: Execute the target operation according to the identity of the target person.

[0087] Exemplarily, the corresponding target operation may be performed based on the stranger identity identified and determined in step S2; and / or the corresponding target operation may be performed based on the non-stranger identity identified and determined in step S2.

[0088] In some feasible implementations, the above step S3: performing the target operation according to the identity of the target person, includes: Step S31: When it is determined that the identity of the target person corresponds to that of a stranger, a target alarm operation is performed.

[0089] For example, if the target person's identity is determined to be a stranger, a video recording operation can be performed on the target stranger, and the video of the target stranger can be uploaded to the target cloud platform to facilitate the execution of the target alarm operation and / or subsequent tracking and determination of the target stranger's identity. The alarm information corresponding to the target alarm operation can be pushed to the client corresponding to the target user.

[0090] Exemplarily, when it is determined that the identity of the target person corresponds to a non-stranger identity, security system, access control, financial transaction, and / or smart device unlocking operations may be performed.

[0091] Therefore, the above method is beneficial to improving the accuracy and efficiency of alarm operation execution of security systems, access control, financial transactions, and / or smart devices by executing the target alarm operation when it is determined that the identity of the target person corresponds to the identity of a stranger, thereby improving the protection of the personal and property safety of the target user.

[0092] Based on this, the person identification method proposed in this application includes: generating encrypted data of a target stylized image based on a target image; identifying the target person's identity based on the encrypted data of the target stylized image and the target captured image data, where the target person's identity includes: a stranger identity and / or a non-stranger identity; and performing a target operation based on the target person's identity. This application can reduce the risk of user privacy leakage while ensuring the accuracy of person identification, thereby improving the protection of user privacy.

[0093] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all optional embodiments, and the actions and modules involved are not necessarily required by this application.

[0094] The above is an introduction to the method embodiment. The following is a system embodiment to further illustrate the solution described in this application.

[0095] Figure 2 A structural diagram of a personnel identification device 200 proposed in an embodiment of the present application is shown. Figure 2 As shown, the personal identification device 200 includes: a generating unit 210 , an identifying unit 220 and an executing unit 230 .

[0096] A generating unit 210 is configured to generate target stylized image encryption data based on the target image; The identification unit 220 is configured to identify the identity of a target person based on the target stylized image encryption data and the target collected image data, wherein the target person identity includes: a stranger identity and / or a non-stranger identity; The execution unit 230 is used to execute the target operation according to the identity of the target person.

[0097] It should be noted that the above-mentioned personnel identification device 200 can be implemented based on technical means such as Internet Protocol Camera (IPC) and Bluetooth point-to-point communication.

[0098] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working process of the described module can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0099] In a third aspect of the present application, an electronic device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the method described above when executing the computer program.

[0100] Figure 3 A schematic structural diagram of an electronic device suitable for implementing the embodiments of the present application is shown.

[0101] like Figure 3As shown, the electronic device includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 into the random access memory (RAM) 303. Various programs and data required for the operation of the electronic device are also stored in the RAM 303. The CPU 301, ROM 302 and RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0102] The following components are connected to the I / O interface 305: an input section 306 including a keyboard, a mouse, and the like; an output section 307 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 308 including a hard disk; and a communication section 309 including a network interface card such as a LAN card or a modem. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. Removable media 311, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 310 as needed, so that computer programs read therefrom can be installed into the storage section 308 as needed.

[0103] In particular, according to an embodiment of the present application, the above method flow steps can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a machine-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network via the communication part 309, and / or installed from the removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, the above-mentioned functions defined in the system of the present application are executed.

[0104] In a fourth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method described above is implemented.

[0105] It should be noted that the computer-readable medium shown in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this application, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. This propagated data signal can take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wireline, optical fiber cable, RF, or any suitable combination thereof.

[0106] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the aforementioned module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0107] The units or modules involved in the embodiments described in this application may be implemented in software or hardware. The units or modules described may also be provided in a processor. The names of these units or modules do not, in certain circumstances, constitute limitations on the units or modules themselves.

[0108] As another aspect, the present application further provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiments, or may exist independently and not be incorporated into the electronic device. The computer-readable storage medium stores one or more programs, which, when used by one or more processors, execute the method described in the present application.

[0109] The above description is merely a preferred embodiment of the present application and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of application involved in this application is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the aforementioned application concept. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions applied for in this application.

Claims

1. A method for identifying a person, characterized in that: include: Generate target stylized image encryption data according to the target image; Identifying the identity of a target person according to the target stylized image encrypted data and the target collected image data, wherein the target person identity includes: a stranger identity and / or a non-stranger identity; Execute target operations according to the identity of the target person.

2. The personnel identification method according to claim 1, characterized in that: Generating target stylized image encryption data according to the target image includes: Determine target features based on the target image; generating the target stylized image according to the target features; The target features include: target spacing features, target outline features, target skeleton features, target hairstyle features, target attribute features, and / or target clothing features.

3. The personnel identification method according to claim 2, characterized in that: Generating the target stylized image according to the target features includes: Determining target relative coordinate information according to the target spacing characteristics; Generating target relative angle information according to the target contour feature and / or the target skeleton feature; A first target stylized image is generated according to the target relative coordinate information and / or the target relative angle information.

4. The personnel identification method according to claim 3, characterized in that: Also includes: According to the target attribute feature, a corresponding target feature processing operation is performed on the first target stylized image to generate a second target stylized image.

5. The personnel identification method according to claim 4, characterized in that: Also includes: Performing a target encryption operation on the second target stylized image to generate the target stylized image encrypted data, wherein the target encryption operation includes: a target salting operation and / or a target key encryption operation.

6. The method for identifying a person according to any one of claims 1 to 5, characterized in that: The identifying of the target person according to the target stylized image encrypted data and the target collected image data includes: Determine target difference features based on target stylized image encryption data and target collected image data; When it is determined that the difference value of any of the target difference features is greater than the corresponding preset threshold, it is determined that the target person identity corresponds to the stranger identity.

7. The personnel identification method according to claim 6, characterized in that: The performing of the target operation according to the identity of the target person includes: When it is determined that the identity of the target person corresponds to the identity of the stranger, a target alarm operation is performed.

8. A personal identification device, characterized in that: include: A generating unit, configured to generate target stylized image encryption data according to a target image; an identification unit, configured to identify a target person's identity based on the target stylized image encrypted data and the target captured image data, wherein the target person's identity includes: a stranger's identity and / or a non-stranger's identity; An execution unit is used to execute a target operation according to the identity of the target person.

9. An electronic device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images