Verification method, verification device and electronic equipment

Abstract

The invention provides a verification method, a verification device and electronic equipment, and relates to the field of image processing and information security. The verification method comprises the following steps: in response to a verification instruction for a first image collected by a target collection device, obtaining a target similarity between the first image and a target image; and if the target similarity is higher than a first similarity threshold, obtaining a result that the first image does not pass verification.

Description

Technical Field

[0001] The present disclosure relates to the fields of image processing and information security, and more particularly to a verification method, a verification device, and an electronic device. Background Art

[0002] Currently, when users use electronic devices, they often need to use their own biometric information to perform verification operations on the electronic devices, such as unlocking.

[0003] However, if illegal personnel obtain the user's biometric information through illegal means, such as printed photos, face electronic pictures, face videos, 3D face masks, etc., they can use them to perform these verification operations on the electronic devices, which may lead to the misappropriation of personal identities, threats to property safety, damage to reputation, and even may involve public safety, causing serious consequences. Summary of the Invention

[0004] In view of the above problems, the present disclosure provides a verification method, a verification device, and an electronic device.

[0005] According to a first aspect of the present disclosure, there is provided a verification method, including: in response to a verification instruction for a first image collected by a target acquisition device, obtaining a target similarity between the first image and a target image; if the target similarity is higher than a first similarity threshold, obtaining a result that the verification of the first image fails.

[0006] According to an embodiment of the present disclosure, the verification method further includes: if the target similarity is not higher than the first similarity threshold and is higher than a second similarity threshold, obtaining a result that the verification of the first image passes.

[0007] According to an embodiment of the present disclosure, the first image is an image collected by the target acquisition device at a first moment; the target image is an image collected by the target acquisition device at a second moment, where the second moment is earlier than the first moment.

[0008] According to an embodiment of the present disclosure, the time difference between the first moment and the second moment is less than a first time difference; or the time difference between the first moment and the second moment is greater than a second time difference, and the target image is a suspicious image stored at a target storage location.

[0009] According to an embodiment of the present disclosure, obtaining the target similarity between the first image and the target image is selected from one of the following combinations: obtaining a first similarity between the target object contour features included in the first image and the target object contour features included in the target image; obtaining a second similarity between the first adjacent region features corresponding to the first image and the second adjacent region features corresponding to the target image; the adjacent region features characterize the features of the partial background region in the corresponding image that is in contact with the contour region of the included target object.

[0010] According to an embodiment of the present disclosure, the target object contour feature includes a first contour feature of a first part corresponding to the target object and a second contour feature of a second part corresponding to the target object.

[0011] According to an embodiment of the present disclosure, the verification method further includes: if the target similarity is higher than the first similarity threshold, storing the first image at a target storage location.

[0012] According to an embodiment of the present disclosure, the target similarity characterizes the similarity between the features of the partial background region in the first image that contacts the contour region of the included target object and the features of the partial background region in the target image that contacts the contour region of the included target object. The verification method further includes: if the partial background region in the first image that contacts the contour region of the included target object does not meet the adjacency region condition, and / or, the partial background region in the target image that contacts the contour region of the included target object does not meet the adjacency region condition; outputting a target prompt message, where the target prompt message is used to prompt the acquisition of target biometric information of the target object, where the target biometric information characterizes a specified action of a specified part of the target object and / or status information of a specified part of the target object.

[0013] A second aspect of the present disclosure provides a verification device, including: an acquisition module configured to obtain a target similarity between a first image and a target image in response to a verification instruction for the first image acquired by a target acquisition device; a verification module configured to, if the target similarity is higher than the first similarity threshold, obtain a result that the verification of the first image fails.

[0014] A third aspect of the present disclosure provides an electronic device, including: a target acquisition device configured to acquire a first image; a processor communicatively connected to the target acquisition device, where the processor is configured to: in response to a verification instruction for the first image, obtain a target similarity between the first image and the target image; if the target similarity is higher than the first similarity threshold, obtain a result that the verification of the first image fails.

[0015] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. Description of the Drawings

[0016] Through the following description of the embodiments of the present disclosure with reference to the drawings, the above and other objects, features, and advantages of the present disclosure will become clearer. In the drawings:

[0017] Figure 1 Schematically shows a flowchart of a verification method according to a first embodiment of the present disclosure;

[0018] Figure 2 Schematically shows the schematic diagram of the verification method according to the second embodiment of the present disclosure;

[0019] Figure 3 Schematically shows the schematic diagram of the verification method according to the third embodiment of the present disclosure;

[0020] Figure 4 Schematically shows the schematic diagram of the verification method according to the fourth embodiment of the present disclosure;

[0021] Figure 5 Schematically shows the flowchart of the verification method according to the eighth embodiment of the present disclosure;

[0022] Figure 6 Schematically shows the block diagram of the verification device according to the embodiment of the present disclosure;

[0023] Figure 7 Schematically shows the block diagram of the electronic device according to the embodiment of the present disclosure. Detailed implementation manners

[0024] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present disclosure. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily confusing the concepts of the present disclosure.

[0025] The terms used herein are merely for describing specific embodiments and are not intended to limit the present disclosure. The terms "including", "comprising", etc. used herein indicate the presence of the described features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0026] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0027] In the technical solution of the present disclosure, the user information involved (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) are all information and data authorized by the user or fully authorized by all parties. Moreover, the processing of relevant data, such as collection, storage, use, processing, transmission, provision, disclosure, and application, all complies with relevant laws, regulations, and standards, takes necessary confidentiality measures, does not violate public order and good customs, and provides corresponding operation entrances for users to choose to authorize or refuse.

[0028] In the scenario of making automated decisions using personal information, the methods, devices, and systems provided by the embodiments of the present disclosure all provide corresponding operation entrances for users to choose to agree or reject the results of automated decisions; if the user chooses to reject, the expert decision-making process will be entered. The expression "automated decision" here refers to the activity of automatically analyzing and evaluating an individual's behavior habits, hobbies, or economic, health, credit status, etc. through a computer program and making decisions. The expression "expert decision" here refers to the activity of making decisions by personnel who are engaged in work in a specific field, have specialized experience, knowledge, and skills, and have reached a certain professional level.

[0029] The embodiments of the present disclosure provide a verification method, including: in response to a verification instruction for a first image collected by a target acquisition device, obtaining a target similarity between the first image and a target image; if the target similarity is higher than a first similarity threshold, obtaining a result that the verification of the first image fails. This verification method can be applied to an electronic device and can verify the first image collected by the target acquisition device to obtain a verification result of passing or failing the verification.

[0030] The electronic device includes but is not limited to smartphones, tablet computers, laptop portable computers, desktop computers, and so on. The purpose of this verification method can be important verification operations such as unlocking the electronic device by the user, making payments, reading important files, setting permissions, logging in to the device, etc.

[0031] For example, when the user performs an unlocking operation on the electronic device, before performing the unlocking operation on the electronic device, the electronic device generates a verification instruction and performs a verification operation in response to this verification instruction. When the verification of the first image fails, the electronic device cannot be unlocked. On the contrary, when the verification of the first image passes, the electronic device can switch from the original standby state to the working state, and the user can use the electronic device in the working state of the electronic device, including using various functions that the electronic device has.

[0032] Figure 1 Schematically shows a flowchart of the verification method according to the first embodiment of the present disclosure.

[0033] As Figure 1 shown, the verification method 100 of the first embodiment of the present disclosure includes operations S110 to S120, and this verification method can be executed by an electronic device.

[0034] In operation S110, in response to a verification instruction for a first image collected by a target acquisition device, obtain a target similarity between the first image and a target image.

[0035] The target acquisition device and the electronic device on which the verification method is executed can be physically discrete or integrated. In the separated state, the target acquisition device and the electronic device transmit data through a network, which can include various connection types, such as wired, wireless communication links, or fiber optic cables, etc. In the integrated state, the target acquisition device can be integrated into the electronic device.

[0036] The target acquisition device can be a device with real-time image acquisition capabilities, including but not limited to cameras, cameras, image sensors, lidar, dash cams, ultrasonic imaging probes, etc.

[0037] The first image can be acquired by the target acquisition device at the current moment or at a historical moment before the current moment. The first image can contain information related to the target object to be verified (such as the user of the electronic device), such as the appearance information of the target object (including face information), posture, movement, micro-expression, identity information, etc.

[0038] The data type of the verification instruction is not specifically limited. For example, the verification instruction can be expressed in at least one of the formats such as text, audio, picture, video, etc.

[0039] The verification instruction can be issued for the verification need of the first image acquired by the target acquisition device. When the first image needs to be verified, a corresponding verification instruction can be generated. The electronic device responds to the verification instruction and obtains the target similarity between the first image and the target image.

[0040] The target image can be pre-stored in the electronic device.

[0041] The target similarity can be a quantitative index that measures the degree of closeness between the first image and the target image in terms of visual content, structure, or semantic features.

[0042] In operation S120, if the target similarity is higher than the first similarity threshold, a result that the verification of the first image fails is obtained.

[0043] The first similarity threshold can be pre-stored in the electronic device. The first similarity threshold can be set according to actual needs. For example, the first similarity threshold is 95%. When the target similarity is higher than 95%, it can be determined that the verification of the first image fails.

[0044] The target similarity being higher than the first similarity threshold indicates that the features of the first image and the target image are the same or similar.

[0045] Through the verification method of the embodiments of the present disclosure, when it is necessary to verify the first image collected by the target acquisition device, the target similarity between the first image and the target image is obtained. By comparing the target similarity with the first similarity threshold, the verification result of the first image can be obtained. Due to external factors such as the verification scenario, verification timing, surrounding environment, acquisition angle of the target acquisition device, and the angle of the user's handheld electronic device, there will always be some differences in the images during user verification. If the target similarity between the first image and the target image is very high and can almost be considered the same, then the first image is likely to be an existing image before and is not trustworthy. Further, after the verification of the first image fails, it may not affect the relevant operations of the electronic device, or generate a prompt message indicating verification failure, etc. Furthermore, it can prevent illegal personnel from obtaining relevant information of the electronic device through illegal means to conduct a network attack on the electronic device and ensure the security of the electronic device.

[0046] For example, the electronic device is a smart phone, and the target acquisition device is the camera of the smart phone. When the electronic device is triggered to perform an unlocking operation in the screen-off state, it is necessary to verify the first image collected by the camera and generate a corresponding verification instruction. After receiving the verification instruction, the electronic device can compare the features of the first image with the pre-stored target image to obtain the target similarity between the two. If the target similarity is higher than the first similarity threshold, it can be determined that the first image is the same as or similar to the target image, and further, the result that the verification of the first image fails can be obtained. The electronic device can generate a verification result indicating that the verification fails and does not actually unlock the current unlocking operation, that is, the unlocking fails, and the electronic device remains in the current screen-off state. Furthermore, it can prevent illegal personnel from obtaining relevant information of the electronic device through illegal means to conduct a network attack on the electronic device and ensure the security of the electronic device.

[0047] Figure 2 Schematically shows the principle diagram of the verification method according to the second embodiment of the present disclosure.

[0048] As Figure 2 shown, the second embodiment of the present disclosure provides a verification method 200. Different from the foregoing first embodiment, after the above operation S110, it further includes: if the target similarity is not higher than the first similarity threshold and higher than the second similarity threshold, obtaining the result that the verification of the first image passes.

[0049] Specifically, the target similarity can be first compared with the first similarity threshold. If the target similarity is not higher than the first similarity threshold, the target similarity is continuously compared with the second similarity threshold. At this time, if the target similarity is higher than the second similarity threshold, the result that the verification of the first image passes can be obtained.

[0050] The second similarity threshold may be pre-stored in the electronic device. The second similarity threshold can be set according to actual needs, and the second similarity threshold is lower than the first similarity threshold.

[0051] For example, the first similarity threshold is 98%, and the second similarity threshold is 90%. When the target similarity is higher than 98%, it can be determined that the verification of the first image fails; when the target similarity is higher than 90% and not higher than 98%, it can be determined that the verification of the first image passes.

[0052] That the target similarity is higher than the second similarity threshold can indicate that there is a minimum degree of feature similarity between the first image and the target image. If the target similarity is lower than or equal to the second similarity threshold, it indicates that the first image and the target image are not comparable, and thus the first image cannot be verified based on the target similarity between the first image and the target image.

[0053] Through the verification method of the embodiments of the present disclosure, by comparing the target similarity with the first similarity threshold and the second similarity threshold in sequence, a verification result of whether the verification of the first image passes or fails can be obtained.

[0054] Figure 3 Schematically shows the schematic diagram of the verification method according to the third embodiment of the present disclosure.

[0055] As Figure 3 shown, the third embodiment of the present disclosure provides a verification method 300. Different from the foregoing first embodiment, the first image is an image collected by the target acquisition device at the first moment t1; the target image is an image collected by the target acquisition device at the second moment t2, where the second moment t2 is earlier than the first moment t1.

[0056] On the time axis t, that the second moment t2 is earlier than the first moment t1 indicates that the acquisition time of the target image is earlier than the acquisition time of the first image. For example, the first image is collected by the target acquisition device at the current moment, and the target image is collected by the target acquisition device at any historical moment before the current moment. When the electronic device needs to verify the first image, it obtains the target similarity between the first image and the pre-collected target image.

[0057] For example, the target image and the first image are two consecutive images collected by the target acquisition device in time. Based on the target similarity between the two consecutive images, a verification result of the first image can be obtained.

[0058] Figure 4 Schematically shows the schematic diagram of the verification method according to the fourth embodiment of the present disclosure.

[0059] As Figure 4As shown, the fourth embodiment of the present disclosure provides a verification method 400. Different from the foregoing third embodiment, the time difference between the first moment t1 and the second moment t2 is less than the first time difference T1; or

[0060] the time difference between the first moment t1 and the second moment t2 is greater than the second time difference T2, and the target image is a suspicious image stored at the target storage location.

[0061] Specifically, the first time difference or the second time difference can be pre-stored in the electronic device. The first time difference or the second time difference can be set according to actual needs, and the first time difference is less than the second time difference.

[0062] As Figure 4 shown in (a) below, the time difference between the first moment t1 and the second moment t2 is less than the first time difference T1, indicating that the target image and the first image are two consecutive images captured by the target acquisition device in a short period of time. For example, the target image and the first image can be two consecutive images captured by the target acquisition device of the electronic device in a short acquisition time span in response to the same verification instruction.

[0063] As Figure 4 shown in (b) below, the time difference between the first moment t1 and the second moment t2 is greater than the second time difference T2, indicating that the target image and the first image are two consecutive images captured by the target acquisition device with a long acquisition time span. For example, the target image with an earlier acquisition time can be an image determined to be unverified in response to the previous verification instruction; and the first image with a later acquisition time can be an image captured in real time by the target acquisition device for the subsequent verification instruction.

[0064] Further, when the target image is an image determined to be unverified in response to the previous verification instruction, the target image can be stored at the target storage location as a suspicious image for use by the electronic device in response to the subsequent verification instruction.

[0065] The target storage location can be a designated storage location inside the electronic device, or other storage locations communicatively connected to the electronic device, such as a cloud server, a network disk, a server of a distributed system, etc.

[0066] The fifth embodiment of the present disclosure provides a verification method. Different from the foregoing fourth embodiment, this verification method further includes: if the target similarity is higher than the first similarity threshold, storing the first image to the target storage location.

[0067] For example, if the target similarity is not higher than the first similarity threshold, that is, the first image verification fails, the first image is stored at the target storage location. Then, when the electronic device responds to a subsequent verification instruction, it can be used as a suspicious image stored at the target storage location, that is, the target image.

[0068] In addition, after storing the first image at the target storage location, it is also possible to respond to the determination that the target object has passed the verification and remove the first image from the target storage location to avoid occupying storage space. For example, in the case where the verification of the first image by the electronic device fails and the unlocking fails, after the user re-enters the basic password and successfully unlocks, it is confirmed that it is the operation of the device owner himself, and then the first image can be removed from the target storage location.

[0069] The sixth embodiment of the present disclosure provides a verification method. Different from the foregoing first embodiment, the target similarity between the first image and the target image obtained in the above operation S110 is selected from one of the following combinations:

[0070] Obtain the first similarity between the target object contour feature included in the first image and the target object contour feature included in the target image;

[0071] Obtain the second similarity between the first adjacent region feature corresponding to the first image and the second adjacent region feature corresponding to the target image; the adjacent region feature represents the feature of the partial background region in the corresponding image that is in contact with the contour region of the included target object.

[0072] The target object may be an object included in the corresponding image, such as a specific person, item, symbol, text, scene, etc. Among them, the specific person may be the user of the electronic device.

[0073] The target object contour feature may be any contour feature of the target object. Taking the target object as a user as an example, the target object contour feature may be the shape information of the overall user face and local facial parts, such as the outer contour of the human face and the shape information of the facial features.

[0074] It can be understood that the adjacent region feature is the feature of the partial background region that is only in contact with the contour region of the included target object in all the background regions except the contour region of the target object in the corresponding image. The adjacent region feature can be used to set off the target object, provide the environmental information of the target object, or create a visual atmosphere. Taking the target object as a user as an example, the adjacent region feature may be the feature of the partial background region in the corresponding image that is in contact with the outer contour of the user's face.

[0075] Through the verification method of the embodiments of the present disclosure, due to external factors such as the verification scenario, verification timing, surrounding environment, acquisition angle of the target acquisition device, and the angle of the user's handheld electronic device, there will always be some differences in the images during user verification. That is, there will always be some differences in the contour features of the target object / the adjacent region features of the target object in different images, and they will not be exactly the same. If the target similarity between the first image and the target image in terms of the contour features of the target object / the adjacent region features of the target object is very high and can almost be considered the same, then the first image is likely to be an existing image before and is not credible. Thus, based on the contour features of the target object included in the corresponding image or the adjacent region features of the corresponding image, the target similarity between the first image and the target image can be obtained. Then, by comparing the target similarity with the first similarity threshold, the verification result of the first image can be obtained. Furthermore, it can prevent illegal personnel from obtaining relevant information of the target object (such as the user of the electronic device) through illegal means to conduct a network attack on the electronic device and ensure the security of the electronic device.

[0076] A seventh embodiment of the present disclosure provides a verification method. Different from the foregoing sixth embodiment, the contour features of the target object include the first contour features of the first part corresponding to the target object and the second contour features of the second part corresponding to the target object.

[0077] Taking the target object as a user as an example, the first part and the second part are two different parts among the facial features of the user. For example, the first part is the eyes, and the first contour feature is the interpupillary distance; the second part is the nose, and the second contour feature is the nose shape.

[0078] Since different parts corresponding to the target object contain various biometric data that uniquely identify the target object, the verification method of the embodiments of the present disclosure can obtain the target similarity between the first image and the target image based on the contour features of multiple parts of the target object in the corresponding image, improving the verification accuracy.

[0079] Figure 5 The flowchart of the verification method according to the eighth embodiment of the present disclosure is schematically shown.

[0080] As Figure 5 shown, an eighth embodiment of the present disclosure provides a verification method. Different from the foregoing first embodiment, the target similarity represents the similarity between the features of the partial background region in the first image that contacts the contour region of the included target object and the features of the partial background region in the target image that contacts the contour region of the included target object. On this basis, the verification method further includes operations S501 to S502.

[0081] In operation S501, if the background region of the first image that contacts the contour region of the included target object does not meet the adjacent region condition, and / or, the background region of the target image that contacts the contour region of the included target object does not meet the adjacent region condition;

[0082] In operation S502, output a target prompt message for prompting to collect target biometric information of the target object, where the target biometric information represents a specified action of a specified part of the target object, and / or, status information of the specified part of the target object.

[0083] The adjacent region condition can be preset according to the actual verification requirements of the first image. For example, the adjacent region condition can be that the background region in the corresponding image that contacts the outer contour of the human face is a blank background, a pattern-repeated filled background, or a solid-color background (such as black, blue). In this case, it is impossible to obtain the target similarity between the first image and the target image based on the adjacent region features corresponding to the first image and the target image respectively.

[0084] Thus, for any one of the first image and the target image, if the background region of the image that contacts the contour region of the included target object does not meet the adjacent region condition, output a target prompt message to prompt to collect target biometric information of the target object.

[0085] The target prompt message is used to prompt to collect target biometric information of the target object. The target biometric information is the relevant features that can represent the biometric information of the target object. Specifically, the target biometric information represents a specified action of a specified part of the target object, and / or, status information of the specified part of the target object.

[0086] The specified part can be distributed at any position of the contour region of the target object. The specified action can be an action that can be completed by the target object at the specified part, which is a dynamic feature information. For example, if the specified part of the target object is the eyes, the specified action can be blinking; if the specified part is the mouth, the specified action can be the opening and closing of the mouth.

[0087] The status information of the specified part can be the static feature information of the target object at the specified part. For example, the status information of the specified part of the target object can be tooth morphology, fingerprint, iris / retina, ear shape, hand shape, palm print, etc.

[0088] The embodiments of the present disclosure do not specifically limit the output manner of the target prompt message. For example, the target prompt message can be output on the electronic device through ways such as screen pop-up window, screen flashing, prompt sound, voice broadcast, vibration feedback, etc.

[0089] Through the verification method of the embodiment of the present disclosure, when any one of the first image and the target image has no background or a solid color background, the target biometric information can be collected to perform liveness detection on the target object, thereby making up for the deficiency of verification operations based solely on the first image.

[0090] The above description is merely exemplary, and the embodiments of the present disclosure are not limited thereto.

[0091] In some embodiments, the verification method also includes: in response to receiving target biometric information of the target object collected based on the target prompt information, determining a third similarity between the target biometric information and the pre-entered baseline feature information; if the third similarity is higher than a third similarity threshold, obtaining a result that the target object verification is passed.

[0092] In some embodiments, the verification method further includes: when a result of failure of the first image verification is obtained, issuing a prohibition instruction to prohibit the acquisition function of the target acquisition device; generating content input prompt information to prompt the input of target verification content of the target object, wherein the target verification content includes at least one of a pattern, a password, and a trajectory.

[0093] Furthermore, the verification method may also include: in response to receiving target verification content of the target object input based on the content input prompt information, determining the fourth similarity between the target verification content and the pre-entered benchmark verification content; if the fourth similarity is higher than the fourth similarity threshold, obtaining a result that the target object verification passed, and releasing the prohibition instruction.

[0094] Based on the above verification method, the present disclosure also provides a verification device, which will be combined with Figure 6 The verification device is described in detail.

[0095] Figure 6 A block diagram of a verification device according to an embodiment of the present disclosure is schematically shown.

[0096] like Figure 6 As shown, the verification device 600 of this embodiment includes an acquisition module 610 and a verification module 620 .

[0097] The acquisition module 610 is configured to acquire the target similarity between the first image and the target image in response to a verification instruction for the first image acquired by the target acquisition device.

[0098] The verification module 620 is configured to obtain a result that the first image verification fails if the target similarity is higher than a first similarity threshold.

[0099] It should be noted that each module of the verification device provided in the embodiments of the present disclosure can implement the functions of each step of the above verification method and achieve the corresponding technical effects. For the sake of brevity, the description will not be repeated here.

[0100] Based on the above verification method, the present disclosure also provides an electronic device, which will be described in detail below in conjunction with Figure 7 this.

[0101] Figure 7 FIG. schematically shows a block diagram of an electronic device according to an embodiment of the present disclosure.

[0102] As Figure 7 shown, the electronic device 700 of this embodiment includes a target acquisition device 710 and a processor 720, and the processor 720 is communicatively connected to the target acquisition device 710.

[0103] The target acquisition device 710 is configured to acquire a first image.

[0104] The processor 720 is configured to: in response to a verification instruction for the first image, obtain a target similarity between the first image and a target image; if the target similarity is higher than a first similarity threshold, obtain a result that the verification of the first image fails.

[0105] For example, the target acquisition device 710 may include a camera, a camera, an image sensor, a lidar, a dash cam, an ultrasonic imaging probe, etc.

[0106] For example, the processor 720 may include one or more single-core or multi-core processors. The processor 830 may also include any combination of a general-purpose processor and a dedicated processor (such as a graphics processor, an application processor, a baseband processor, etc.).

[0107] For example, the electronic device 700 may include a smart phone, a tablet computer, a laptop computer, a desktop computer, and so on.

[0108] It should be noted that each module of the electronic device provided in the embodiments of the present disclosure can implement the functions of each step of the above verification method and achieve the corresponding technical effects. For the sake of brevity, the description will not be repeated here.

[0109] Any number of the modules according to embodiments of the present disclosure, or at least some functions of any of them, may be implemented in one module. Any one or more of the modules according to embodiments of the present disclosure may be split into multiple modules for implementation. Any one or more of the modules according to embodiments of the present disclosure may be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or may be implemented by any other reasonable way of integrating or packaging circuits, or in any one of the three implementation manners of software, hardware, and firmware, or in a suitable combination of any several of them. Alternatively, one or more of the modules according to embodiments of the present disclosure may be at least partially implemented as a computer program module, and when the computer program module runs, it may execute corresponding functions.

[0110] Those skilled in the art can understand that the features described in the various embodiments of the present disclosure can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in the present disclosure. In particular, without departing from the spirit and teachings of the present disclosure, the features described in the various embodiments of the present disclosure can be combined and / or combined in various ways. All such combinations and / or combinations fall within the scope of the present disclosure.

[0111] The embodiments of the present disclosure have been described above. However, these embodiments are only for illustrative purposes and not for limiting the scope of the present disclosure. Although the embodiments have been described separately above, this does not mean that the measures in each embodiment cannot be used advantageously in combination. Without departing from the scope of the present disclosure, those skilled in the art can make various substitutions and modifications, and all such substitutions and modifications should fall within the scope of the present disclosure.

Claims

1. A verification method, comprising: In response to a verification instruction for a first image collected by a target acquisition device, obtaining a target similarity between the first image and a target image; If the target similarity is higher than a first similarity threshold, obtaining a result that the verification of the first image fails.

2. The method according to claim 1, the method further comprising: If the target similarity is not higher than the first similarity threshold and is higher than a second similarity threshold, obtaining a result that the verification of the first image passes.

3. According to the method described in claim 1, the first image is an image acquired by the target acquisition device at a first moment; the target image is an image acquired by the target acquisition device at a second moment, where The second moment is earlier than the first moment.

4. The method according to claim 3, wherein: The time difference between the first moment and the second moment is less than a first time difference; or The time difference between the first moment and the second moment is greater than a second time difference, and the target image is a suspicious image stored at a target storage location.

5. The method according to claim 1, the obtaining of the target similarity between the first image and the target image is selected from one of the following combinations: Obtaining a first similarity between the target object contour feature included in the first image and the target object contour feature included in the target image; Obtaining a second similarity between a first adjacent region feature corresponding to the first image and a second adjacent region feature corresponding to the target image; the adjacent region feature characterizes the feature of a partial background region in the corresponding image that is in contact with the contour region of the included target object.

6. The method according to claim 5, the target object contour feature includes a first contour feature of a first part corresponding to the target object and a second contour feature of a second part corresponding to the target object.

7. The method according to claim 4, the method further comprising: If the target similarity is higher than the first similarity threshold, storing the first image to the target storage location.

8. The method according to claim 1, the target similarity characterizes the similarity between the feature of the partial background region in the first image that is in contact with the contour region of the included target object and the feature of the partial background region in the target image that is in contact with the contour region of the included target object, the method further comprising: If the partial background region in the first image that is in contact with the contour region of the included target object does not meet the adjacent region condition, and / or, the partial background region in the target image that is in contact with the contour region of the included target object does not meet the adjacent region condition; Outputting a target prompt message, the target prompt message being used to prompt for obtaining target biometric information of the target object, wherein the target biometric information characterizes a specified action of a specified part of the target object, and / or, status information of a specified part of the target object.

9. A verification device, comprising: An obtaining module, configured to obtain a target similarity between the first image and a target image in response to a verification instruction for a first image collected by a target acquisition device; A verification module, configured to obtain a result that the verification of the first image fails if the target similarity is higher than a first similarity threshold.

10. An electronic device, comprising: A target acquisition device for acquiring a first image; A processor communicatively connected to the target acquisition device, the processor being configured to: In response to a verification instruction for the first image, obtain a target similarity between the first image and a target image; If the target similarity is higher than a first similarity threshold, obtain a result that the verification of the first image fails.

Images