Information comparison method, device, electronic device and storage medium
By setting analog images and obtaining matching image sets, the false alarms and missed reports caused by a single similarity threshold in face recognition are solved, and the accuracy of identity information comparison is improved.
Patent Information
- Application Number
- CN202111549194.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-12-17
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2041-12-17
AI Technical Summary
In the existing facial recognition technology, there are false alarms and missed identification information comparison based on a single similarity threshold, resulting in low recognition accuracy.
By obtaining the image to be compared for the target object, set the reference image with the greatest similarity to the image to be compared in the reference library as an analog image. When the similarity between the analog image and the image to be compared is greater than the preset threshold, obtain a match The image set is set, and the second information verification is performed in the case where there are multiple different objects in the matching image set to improve the recognition accuracy.
The personnel information is filtered using multiple similarity thresholds to avoid false alarms or misreports of recognition results caused by a single threshold, and improve the accuracy of the personnel information comparison of facial recognition.
Smart Images

Figure CN114495194B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of face recognition, and in particular to an information comparison method, device, electronic device and storage medium. Background Art
[0002] With the development of economy and the advancement of science and technology, face recognition technology has been widely used in production and life. For example, in the consumption system, the face of the consumer can be identified with the help of face recognition technology, so as to obtain the identity information of the consumer to realize the deduction operation. However, in the process of comparing the identity information of personnel based on face recognition, the identity recognition is mainly based on the similarity of face images. By setting a single similarity threshold, the similarity between the face image and the image in the personnel library is compared with the single similarity threshold, and the recognition result of the face image is determined when the similarity is greater than the similarity threshold. This method has a high probability of false alarm or missed alarm, so the accuracy of personnel identity information recognition is not high.
[0003] With regard to the problem of low accuracy of information comparison based on face recognition in related technologies, no effective solution has been proposed so far. Summary of the invention
[0004] In this embodiment, an information comparison method, device, electronic device and storage medium are provided to solve the problem of low accuracy of information comparison based on face recognition in the related art.
[0005] In a first aspect, an information comparison method is provided in this embodiment, including:
[0006] Acquire an image to be compared of the target object collected during the process of verifying the first information of the target object;
[0007] The reference image in the reference library with the greatest similarity to the image to be compared is set as the analog image of the image to be compared, and when the similarity between the analog image and the image to be compared is greater than a preset first threshold, a matching image set of the analog image predetermined in the reference library is obtained; wherein the matching image set is composed of reference images in the reference library whose similarity to the analog image meets a preset similarity condition;
[0008] When there are multiple reference images in the matching image set that belong to different objects and whose similarity with the image to be compared is greater than the first threshold, second information verification is performed on the target object to obtain identity information of the target object.
[0009] In some embodiments, setting the reference image in the reference library with the greatest similarity to the image to be compared as the analog image of the image to be compared includes:
[0010] Obtaining the similarity between the image to be compared and the reference image according to the image features of the image to be compared and the image features of the reference images in the reference library;
[0011] The reference image in the reference library having the greatest similarity to the image to be compared is set as the analog image of the image to be compared.
[0012] In some embodiments, the step of setting the reference image in the reference library having the greatest similarity to the image to be compared as the analog image of the image to be compared further comprises:
[0013] In the case where there is a reference image in the reference library whose similarity with the image to be compared is greater than a preset second threshold, the reference image in the reference library with the greatest similarity with the image to be compared is set as the analog image of the image to be compared; wherein the second threshold is smaller than the first threshold.
[0014] In some embodiments, when there are multiple reference images in the matching image set that belong to different objects and whose similarity to the image to be compared is greater than the first threshold, performing second information verification on the target object to obtain the identity information of the target object includes:
[0015] The identity information of the target object is verified based on the identity identifier of the target object and the identity identifier of a reference image in the matching image set whose similarity with the image to be compared is greater than the first threshold to obtain the identity information of the target object.
[0016] In some embodiments, the method further comprises:
[0017] When the similarity between the analog image and the image to be compared is less than the first threshold, the identity information of the target object is determined according to the identity information associated with the analog image.
[0018] In some embodiments, the method further comprises:
[0019] When the similarities between all reference images in the matching image set and the image to be compared are less than the first threshold, the second information verification is performed on the target object.
[0020] In some embodiments, the method further comprises:
[0021] When there is a unique reference image in the matching image set whose similarity with the image to be compared is greater than the first threshold, the identity information of the target object is confirmed based on the identity information associated with the unique reference image in the matching image set whose similarity with the image to be compared is greater than the first threshold, and the identity information associated with the analog image.
[0022] In some embodiments, the method further comprises:
[0023] After determining the identity information of the target object, the identity information of the target object is output to an associated business system.
[0024] In a second aspect, an information comparison device is provided in this embodiment, characterized in that it includes: an acquisition module, a comparison module, and a verification module, wherein:
[0025] The acquisition module is used to acquire the image to be compared of the target object collected during the process of verifying the first information of the target object;
[0026] The comparison module is used to set the reference image with the greatest similarity to the image to be compared in the reference library as the analog image of the image to be compared, and to obtain a matching image set of the analog image predetermined in the reference library when the similarity between the analog image and the image to be compared is greater than a preset first threshold; wherein the matching image set is composed of reference images in the reference library whose similarity to the analog image meets a preset similarity condition;
[0027] The verification module is used to perform second information verification on the target object to obtain the identity information of the target object when there are multiple reference images in the matching image set that belong to different objects and whose similarity with the image to be compared is greater than the first threshold.
[0028] In a third aspect, an electronic device is provided in this embodiment, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the information comparison method described in the first aspect when executing the computer program.
[0029] In a fourth aspect, a storage medium is provided in this embodiment, on which a computer program is stored, and when the program is executed by a processor, the information comparison method described in the first aspect is implemented.
[0030] The above-mentioned information comparison method, device, electronic device and storage medium obtain the target object to be compared image collected during the first information verification process of the target object, set the reference image with the greatest similarity with the image to be compared in the reference library as the analog image of the image to be compared, and obtain the matching image set of the analog image predetermined in the reference library when the similarity between the analog image and the image to be compared is greater than a preset first threshold, wherein the matching image set is composed of reference images in the reference library whose similarity with the analog image meets the preset similarity condition, and when there are multiple reference images belonging to different objects in the matching image set and whose similarity with the image to be compared is greater than the first threshold, the target object is subjected to the second information verification to obtain the identity information of the target object. It realizes filtering of personnel information by using multiple similarity thresholds, thereby avoiding the false positive or false negative of the recognition result caused by a single similarity threshold, thereby improving the accuracy of personnel information comparison based on face recognition.
[0031] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS
[0032] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0033] Figure 1 It is a hardware structure block diagram of a terminal of the information comparison method of the related art;
[0034] Figure 2 is a flow chart of an information comparison method of this embodiment;
[0035] Figure 3 is a flow chart of the personnel information comparison method of the preferred embodiment;
[0036] Figure 4 This is a personnel registration flow chart provided in this embodiment;
[0037] Figure 5 It is a structural block diagram of the information comparison device of this embodiment. DETAILED DESCRIPTION
[0038] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.
[0039] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the general meaning understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the", "these" and the like in this application do not represent quantitative restrictions, and they can be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether directly or indirectly. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. Usually, the character " / " indicates that the objects associated with each other are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.
[0040] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. For example, running on a terminal, Figure 1 FIG. 1 is a hardware structure diagram of a terminal of the information comparison method of this embodiment. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown in the figure) processor 102 and memory 104 for storing data, wherein processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.
[0041] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the information comparison method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0042] The transmission device 106 is used to receive or send data via a network. The above network includes a wireless network provided by the communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.
[0043] In this embodiment, an information comparison method is provided. Figure 2 is a flow chart of the information comparison method of this embodiment. Figure 2 As shown, the process includes the following steps:
[0044] Step S210: obtaining an image to be compared of the target object collected during the first information verification process of the target object.
[0045] The target object can be any object that needs to be identified by image recognition. For example, a person to be identified in a face recognition scenario. The first information verification is specifically image verification, and the identity information of the target object is confirmed by collecting image information of the target object. Among them, the image to be compared of the target object is an image containing features of the target object for identifying identity information. For example, a facial image of a person to be identified. Further, the image to be compared of the target object can be obtained through a video stream collected by a front-end device. By performing liveness detection on the video stream containing the target object collected by the front end, it is determined that the collected image to be compared of the target object is an image collected in real time, rather than a photo of the target object taken before the first information verification is performed. The liveness detection is specifically a detection of the color of the collected image to be compared, and based on the analysis result of the color, it is determined that the collected image to be compared is an image obtained by real-time shooting of the target object.
[0046] In addition, before performing information comparison, the registration and information entry of the target object can also be completed. Specifically, the image to be registered of the object to be registered that is collected in real time can be input into the background server. According to the comparison between the image to be registered and the reference image in the constructed reference library, the similarity between the image to be registered and all the reference images in the reference library is obtained, and according to a pre-set similarity threshold, the similar image of the image to be registered in the reference library is determined. Specifically, when the similarity between the image to be registered and the reference image is greater than the pre-set similarity threshold, the reference image is set as the similar image of the image to be registered, and the image features of the image to be registered and the identity information of the associated object to be registered are recorded in the reference library. The reference library can be a pre-constructed database for storing image information and identity information of registered objects, and the image of the registered object in the reference library is the reference image.
[0047] Step S220, setting the reference image in the reference library with the greatest similarity to the image to be compared as the analog image of the image to be compared, and obtaining a matching image set of analog images predetermined in the reference library when the similarity between the analog image and the image to be compared is greater than a preset first threshold; wherein the matching image set is composed of reference images in the reference library whose similarity to the analog image meets a preset similarity condition.
[0048] The image features of the image to be compared can be extracted and compared with the image features of other reference images in the reference library, so as to obtain the similarity between each reference image in the reference library and the image to be compared. The image features of the image to be compared can be determined according to the actual application scenario. For example, when the image to be compared is a face, the image features in the image to be compared can be extracted based on the key point detection algorithm.
[0049] After determining the analog image of the image to be compared in the reference library, it can be further determined whether the similarity between the analog image and the image to be compared is greater than a preset first threshold. The first threshold is also a similarity threshold set according to the actual application scenario. For example, in face recognition based on key point detection, the first threshold can be 95%. If the similarity between the two images is greater than the first threshold, there is a high probability that the objects to which the two images belong are the same object. In the case of determining that the similarity between the analog image and the image to be compared is greater than the preset first threshold, in order to avoid false detection or missed detection and improve the accuracy of face recognition, a matching image set of the analog image in the reference library can be obtained. The matching image set can be specifically established by comparing the object to which the analog image belongs with the reference image in the reference library during the registration process, and the matching image set includes the analog image. Further, the preset similarity condition can specifically be whether the similarity with the analog image in the reference library is greater than the similarity threshold determined according to the actual application scenario. The similarity threshold can specifically be the first threshold or other thresholds. In addition, if the similarity between the analog image and the image to be compared is less than the first threshold, the identity information associated with the analog image can be obtained and used as the identity information of the image to be compared, and the information comparison is terminated.
[0050] Step S230: When there are multiple reference images in the matching image set that belong to different objects and whose similarity with the image to be compared is greater than a first threshold, second information verification is performed on the target object to obtain identity information of the target object.
[0051] If there are multiple reference images in the matching image set whose similarity with the image to be compared is greater than the first threshold, and the multiple reference images belong to different objects, it indicates that the first information verification process fails to compare the information of the target object, and thus the target object needs to be subjected to a second information verification. Specifically, the identity identifier input by the target object, such as several digits of an ID number, a mobile phone number, or a card number, can be obtained. Based on the identity identifier input by the target object, a comparison is performed from the identity identifiers associated with the images in the matching image set whose similarity with the image to be compared is greater than the first threshold, thereby obtaining the identity information of the target object. In the case where there are multiple reference images in the matching image set that belong to different objects and whose similarity with the image to be compared is greater than the first threshold, by performing a second information verification on the target object, false positives or negatives caused by the first threshold can be avoided, thereby improving the accuracy of information comparison.
[0052] Furthermore, after the identity information of the target object is determined, the identity information can be sent to other associated business systems to execute the corresponding business. For example, in a consumer business based on face recognition, after completing face recognition and determining the identity information of the consumer, the identity information can be sent to the associated consumer system to complete transactions, deductions, and other operations. In an attendance business based on face recognition, after completing face recognition and determining the identity information of the attendance personnel, the identity information can be sent to the associated attendance system to execute the corresponding attendance operation.
[0053] In the above steps S210 to S230, in the process of performing the first information verification on the target object, the image to be compared of the target object collected is obtained, and the reference image with the greatest similarity to the image to be compared in the reference library is set as the analog image of the image to be compared. When the similarity between the analog image and the image to be compared is greater than a preset first threshold, a matching image set of analog images predetermined in the reference library is obtained, wherein the matching image set is composed of reference images in the reference library whose similarity to the analog image meets the preset similarity condition. When there are multiple reference images belonging to different objects in the matching image set and whose similarity to the image to be compared is greater than the first threshold, the target object is subjected to the second information verification to obtain the identity information of the target object. It realizes filtering of personnel information by using multiple similarity thresholds, thereby avoiding the false positive or false negative of the recognition result caused by a single similarity threshold, thereby improving the accuracy of personnel information comparison based on face recognition.
[0054] Further, in one embodiment, based on the above step S220, the reference image in the reference library with the greatest similarity to the image to be compared is set as the analog image of the image to be compared, which specifically includes the following steps:
[0055] Step S221 , obtaining the similarity between the image to be compared and the reference image according to the image features of the image to be compared and the image features of the reference images in the reference library.
[0056] Step S222: setting the reference image in the reference library with the greatest similarity to the image to be compared as the analog image of the image to be compared.
[0057] Additionally, in one embodiment, based on the above step S220, the reference image in the reference library having the greatest similarity to the image to be compared is set as the analog image of the image to be compared, and the following steps may also be included:
[0058] Step S223, when there is a reference image in the reference library whose similarity with the image to be compared is greater than a preset second threshold, the reference image in the reference library with the greatest similarity with the image to be compared is set as the analog image of the image to be compared; wherein the second threshold is less than the first threshold.
[0059] The second threshold value may be an empirical value set according to the actual application scenario. If the similarity between the two images is greater than the second threshold value, it indicates that the objects contained in the two images are relatively similar. For example, in face recognition, the second threshold value may be set to 89%. When the similarity between two face images is greater than 89%, the two face images may belong to the same person. Therefore, by presetting the second threshold value, it can be used to determine whether there are similar objects to the target object in the reference library, thereby completing the preliminary screening of information comparison. In addition, the second threshold value is less than the first threshold value, and is used to perform preliminary screening of the reference images in the reference library before filtering through the first threshold value to obtain similar persons to the target object.
[0060] In the case where there is a reference image in the reference library whose similarity with the image to be compared is greater than a preset second threshold, there is an object relatively similar to the target object in the reference library, so the reference image in the reference library with the greatest similarity with the image to be compared can be set as the analog image of the image to be compared. It can be understood that in this case, the similarity between the analog image and the image to be compared is greater than the second threshold, so it can be determined that the object contained in the analog image is relatively similar to the target object. In addition, if the similarity between all reference images in the reference library and the image to be compared is less than the preset second threshold, it indicates that there is no object similar to the target object in the reference library, and it can be determined that the image information and identity information of the target object previously registered do not exist in the reference library, so the information comparison of the target object in the reference library can be terminated.
[0061] In one embodiment, based on the above step S230, when there are multiple reference images in the matching image set that belong to different objects and whose similarity with the image to be compared is greater than a first threshold, the second information verification is performed on the target object to obtain the identity information of the target object, which specifically includes the following steps:
[0062] Step S231, based on the identity identifier of the target object and the identity identifier associated with the reference image in the matching image set whose similarity with the image to be compared is greater than a first threshold, the identity information of the target object is verified to obtain the identity information of the target object. Specifically, based on the identity identifier of the target object, the identity identifier is compared within the range of the reference image in the matching image set whose similarity with the image to be compared is greater than the first threshold, thereby determining the identity information of the target object.
[0063] In one embodiment, the method further comprises the following steps:
[0064] Step S240, when the similarity between the analog image and the image to be compared is less than the first threshold, the identity information of the target object is determined according to the identity information associated with the analog image. Specifically, when the similarity between the analog image and the image to be compared is less than the first threshold, the similarity between all reference images in the reference library and the image to be compared is less than the first threshold, and it can be determined that the analog image with the highest similarity and greater than the first threshold belongs to the same object as the image to be compared, thereby determining the identity information of the target object according to the identity information of the object associated with the analog image.
[0065] Furthermore, in one embodiment, the method may further include the following steps:
[0066] Step S250: When the similarity between all reference images in the matching image set and the image to be compared is less than a first threshold, second information verification is performed on the target object.
[0067] Additionally, in one embodiment, the method may further include the following steps:
[0068] Step S260, in the case that there is a unique reference image in the matching image set whose similarity with the image to be compared is greater than a first threshold, the identity information of the target object is confirmed based on the identity information associated with the unique reference image in the matching image set whose similarity with the image to be compared is greater than the first threshold, and the identity information associated with the analog image. Specifically, if there is a unique reference image in the matching image set whose similarity with the image to be compared is greater than the first threshold, it can be determined that the probability that the reference image and the analog image belong to the same object is high, and the identity information of the target object can be confirmed based on the identity information of the reference image and the image to be compared.
[0069] In one embodiment, the method further comprises the following steps:
[0070] Step S270, after determining the identity information of the target object, output the identity information of the target object to the associated business system. Specifically, the business system may be a consumption system, and after determining the identity information of the target object, a deduction operation may be performed in the associated consumption system based on the identity information of the target object. Similarly, the business system may also be an attendance system, and after determining the identity information of the target object, a preset attendance operation may be performed in the associated attendance information based on the identity information of the target object, such as clocking in for attendance.
[0071] In the above steps, the similarity between the image to be compared and the reference image is obtained based on the image features of the image to be compared and the image features of the reference image. When the similarity is greater than a preset second threshold, the reference image in the reference library with the greatest similarity to the image to be compared is set as the analog image of the image to be compared, thereby filtering the reference image based on the second threshold. In the case where there are multiple reference images in the matching image set that belong to different objects and whose similarity to the image to be compared is greater than the first threshold, the identity information of the target object is filtered based on the identity identifier of the target object and the identity identifier of the reference image in the matching image set whose similarity to the image to be compared is greater than the first threshold. Verification is performed to obtain the identity information of the target object, thereby improving the accuracy of the target object's identity information comparison by using the second information verification; when there is a unique reference image in the matching image set whose similarity with the image to be compared is greater than a first threshold, the identity information of the target object is confirmed based on the identity information associated with the unique reference image in the matching image set whose similarity with the image to be compared is greater than the first threshold, and the identity information associated with the analog image, thereby realizing the confirmation of the target object's identity information based on multiple similarity thresholds, avoiding the false positive or false negative of the recognition result caused by a single similarity threshold, and thus improving the accuracy of personnel information comparison based on face recognition.
[0072] The present embodiment is described and illustrated below through preferred embodiments.
[0073] Figure 3 : is a flow chart of the personnel information comparison method of this preferred embodiment. Figure 4 As shown, the personnel information comparison method includes the following steps:
[0074] Step S310, comparing the facial features of the image to be compared containing the facial information of the person to be compared with the facial features in the face database;
[0075] Step S320, determining whether there is a reference image in the face database whose similarity with the image to be compared is greater than a second threshold, if yes, executing step S330, otherwise executing step S410;
[0076] Step S330, taking the reference image in the face database with the highest similarity to the image to be compared as the analog image of the image to be compared;
[0077] Step S340, determining whether the similarity between the analog image and the image to be compared is greater than a first threshold, if so, executing step S350, otherwise executing step S420;
[0078] Step S350, obtaining a matching image set of analog images in the face database;
[0079] Step S360, obtaining a comparison result of the similarity between the matching image set and the image to be compared;
[0080] Step S370, taking the comparison result that is greater than a preset first threshold;
[0081] Step S380, determine whether the number of comparison results is greater than 0, if so, execute step S390, otherwise execute step S430;
[0082] Step S390, determining whether the number of comparison results is greater than 1, if so, executing step S400, otherwise executing step S440;
[0083] Step S400, sending the personnel information associated with the set of matching images whose similarity with the image to be compared is greater than a first threshold to a secondary verification module;
[0084] Step S410, prompting that personnel information comparison fails;
[0085] Step S420, sending the personnel information associated with the analog image to the billing module;
[0086] Step S430, sending the personnel information associated with the reference image in the matching image set whose similarity with the image to be compared is greater than a second threshold to the secondary verification module;
[0087] Step S440: sending the personnel information associated with the reference image in the matching image set whose similarity with the image to be compared is greater than a first threshold to the billing module.
[0088] Figure 4 A personnel registration flow chart provided for this embodiment includes the following steps:
[0089] Step S41, inputting a face image to be registered;
[0090] Step S42, extracting facial features of the person to be registered from the facial image to be registered;
[0091] Step S43, determining a first threshold of image comparison similarity as X;
[0092] Step S44, searching the face database;
[0093] Step S45, determining whether there is a reference image in the face database whose similarity with the face feature to be registered is greater than X, if so, executing step S46, otherwise executing step S47;
[0094] Step S46, recording the reference image having a similarity greater than X with the facial features of the person to be registered and the facial image to be registered as a set of matching images;
[0095] Step S47, adding the facial features and person information of the face image to be registered to the face database.
[0096] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0097] In this embodiment, an information comparison device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. The terms "module", "unit", "subunit" and the like used below can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware is also possible and conceived.
[0098] Figure 5 is a structural block diagram of the information comparison device 50 of this embodiment, such as Figure 5 As shown, the information comparison device 50 includes: an acquisition module 52, a comparison module 54, and a verification module 56, wherein:
[0099] An acquisition module 52 is used to acquire an image to be compared of the target object collected during the first information verification process of the target object;
[0100] The comparison module 54 is used to set the reference image with the greatest similarity to the image to be compared in the reference library as the analog image of the image to be compared, and when the similarity between the analog image and the image to be compared is greater than a preset first threshold, obtain a matching image set of the analog image predetermined in the reference library; wherein the matching image set is composed of reference images in the reference library whose similarity to the analog image meets a preset similarity condition;
[0101] The verification module 56 is used to perform second information verification on the target object to obtain the identity information of the target object when there are multiple reference images belonging to different objects in the matching image set and whose similarity with the image to be compared is greater than a first threshold.
[0102] The above-mentioned information comparison device 50 obtains the target object to be compared image collected during the first information verification process of the target object, sets the reference image with the greatest similarity to the image to be compared in the reference library as the analog image of the image to be compared, and obtains a matching image set of analog images predetermined in the reference library when the similarity between the analog image and the image to be compared is greater than a preset first threshold, wherein the matching image set is composed of reference images in the reference library whose similarity to the analog image meets the preset similarity condition, and when there are multiple reference images belonging to different objects in the matching image set and whose similarity to the image to be compared is greater than the first threshold, the target object is subjected to second information verification to obtain the identity information of the target object. It realizes filtering of personnel information by using multiple similarity thresholds, thereby avoiding false positives or false negatives of recognition results caused by a single similarity threshold, thereby improving the accuracy of personnel information comparison based on face recognition.
[0103] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.
[0104] In this embodiment, an electronic device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.
[0105] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.
[0106] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:
[0107] Acquire an image of the target object to be compared collected during the process of verifying the first information of the target object;
[0108] The reference image with the greatest similarity to the image to be compared in the reference library is set as the analog image of the image to be compared, and when the similarity between the analog image and the image to be compared is greater than a preset first threshold, a matching image set of the analog image predetermined in the reference library is obtained; wherein the matching image set is composed of reference images in the reference library whose similarity to the analog image meets a preset similarity condition;
[0109] When there are multiple reference images in the matching image set that belong to different objects and whose similarity with the image to be compared is greater than a first threshold, the second information of the target object is verified to obtain the identity information of the target object.
[0110] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and will not be repeated in this embodiment.
[0111] In addition, in combination with the information comparison method provided in the above embodiments, a storage medium may be provided in this embodiment to implement the information comparison method. The storage medium stores a computer program; when the computer program is executed by a processor, any one of the information comparison methods in the above embodiments is implemented.
[0112] It should be understood that the specific embodiments described herein are only used to explain the application, rather than to limit it. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of this application.
[0113] Obviously, the drawings are only some examples or embodiments of the present application. For ordinary technicians in the field, the present application can also be applied to other similar situations based on these drawings without creative work. In addition, it is understandable that although the work done in this development process may be complicated and lengthy, for ordinary technicians in the field, certain changes in design, manufacturing or production based on the technical content disclosed in this application are only conventional technical means and should not be regarded as insufficient content disclosed in this application.
[0114] The term "embodiment" in this application refers to a specific feature, structure or characteristic described in conjunction with the embodiment that can be included in at least one embodiment of the present application. The appearance of this phrase in various locations in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is clearly or implicitly understood by those of ordinary skill in the art that the embodiments described in this application can be combined with other embodiments without conflict.
[0115] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of patent protection. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the attached claims.
Claims
1. An information comparison method, characterized in that: include: Acquire an image to be compared of the target object collected during the process of verifying the first information of the target object; The reference image in the reference library with the greatest similarity to the image to be compared is set as the analog image of the image to be compared, and when the similarity between the analog image and the image to be compared is greater than a preset first threshold, a matching image set of the analog image predetermined in the reference library is obtained; wherein the matching image set is composed of reference images in the reference library whose similarity to the analog image meets a preset similarity condition; When there are multiple reference images in the matching image set that belong to different objects and whose similarity with the image to be compared is greater than the first threshold, second information verification is performed on the target object to obtain identity information of the target object.
2. The information comparison method according to claim 1, characterized in that: The step of setting the reference image in the reference library having the greatest similarity to the image to be compared as the analog image of the image to be compared comprises: Obtaining the similarity between the image to be compared and the reference image according to the image features of the image to be compared and the image features of the reference images in the reference library; The reference image in the reference library having the greatest similarity to the image to be compared is set as the analog image of the image to be compared.
3. The information comparison method according to claim 1, characterized in that: The step of setting the reference image in the reference library with the greatest similarity to the image to be compared as the analog image of the image to be compared further comprises: In the case where there is a reference image in the reference library whose similarity with the image to be compared is greater than a preset second threshold, the reference image in the reference library with the greatest similarity with the image to be compared is set as the analog image of the image to be compared; wherein the second threshold is smaller than the first threshold.
4. The information comparison method according to claim 1, characterized in that: In the case where there are multiple reference images in the matching image set that belong to different objects and whose similarity with the image to be compared is greater than the first threshold, performing second information verification on the target object to obtain the identity information of the target object includes: The identity information of the target object is verified based on the identity identifier of the target object and the identity identifier associated with the reference image in the matching image set whose similarity with the image to be compared is greater than the first threshold to obtain the identity information of the target object.
5. The information comparison method according to claim 1, characterized in that: The method further comprises: When the similarity between the analog image and the image to be compared is less than the first threshold, the identity information of the target object is determined according to the identity information associated with the analog image.
6. The information comparison method according to claim 1, characterized in that: The method further comprises: When the similarities between all reference images in the matching image set and the image to be compared are less than the first threshold, the second information verification is performed on the target object.
7. The information comparison method according to claim 1, characterized in that: The method further comprises: When there is a unique reference image in the matching image set whose similarity with the image to be compared is greater than the first threshold, the identity information of the target object is confirmed based on the identity information associated with the unique reference image in the matching image set whose similarity with the image to be compared is greater than the first threshold, and the identity information associated with the analog image.
8. The information comparison method according to claim 1, characterized in that: The method further comprises: After determining the identity information of the target object, the identity information of the target object is output to an associated business system.
9. An information comparison device, characterized in that: include: Acquisition module, comparison module, and verification module, where: The acquisition module is used to acquire the image to be compared of the target object collected during the process of verifying the first information of the target object; The comparison module is used to set the reference image with the greatest similarity to the image to be compared in the reference library as the analog image of the image to be compared, and to obtain a matching image set of the analog image predetermined in the reference library when the similarity between the analog image and the image to be compared is greater than a preset first threshold; wherein the matching image set is composed of reference images in the reference library whose similarity to the analog image meets a preset similarity condition; The verification module is used to perform second information verification on the target object to obtain the identity information of the target object when there are multiple reference images in the matching image set that belong to different objects and whose similarity with the image to be compared is greater than the first threshold.
10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to execute the information comparison method according to any one of claims 1 to 8.
11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the information comparison method described in any one of claims 1 to 8 are implemented.
