Image processing method, device, electronic device and storage medium

By using the audit model in the image processing method to verify whether the image meets the conditions and receives new images collected by the user when they are not met, the problem of low image audit efficiency in the prior art is solved, and a more efficient image audit process is achieved.

CN112906741BActive Publication Date: 2024-11-12BEIJING DIDI INFINITY TECH & DEV CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202110064146.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2019-05-21
Publication Date
2024-11-12
Estimated Expiration
2039-05-21

AI Technical Summary

Technical Problem

In the prior art, image auditing efficiency is low. When users need to reshoot images, the entire auditing process is longer, which reduces the image auditing efficiency.

Method used

An image processing method is provided, by obtaining the image to be reviewed and using the corresponding audit model to verify whether the audit conditions are met. If not, a new image to be reviewed collected by the user is received, and the image audit efficiency is improved using the type verification and quality verification model.

Benefits of technology

This greatly saves image review time and improves image review efficiency. Users do not need to reshoot images frequently to pass the review.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112906741B_ABST
    Figure CN112906741B_ABST
Patent Text Reader

Abstract

The present application provides an image processing method, device, electronic device and storage medium, which relates to the field of image processing technology. The method includes: obtaining an image to be reviewed, the image to be reviewed includes information to be reviewed; using at least one review model corresponding to the image to be reviewed, verifying whether the image to be reviewed meets the review conditions, and obtaining and outputting the review result; if the review result indicates that the image to be reviewed does not meet the review conditions, receiving a new image to be reviewed collected by the user based on the review result. The method uses multiple review models on the terminal to combine the review models according to preset rules and the information of the image to be reviewed, reviews the collected image to be reviewed, and feeds back the review results to the user, which greatly saves the image review time and improves the image review efficiency to a certain extent.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] This application is a divisional application of an invention patent application filed on May 21, 2019, with the parent application number 201910425249X and the invention name “Image processing method, device, electronic device and storage medium”. Technical Field

[0002] The present application relates to the field of image processing technology, and in particular to an image processing method, device, electronic device and storage medium. Background Art

[0003] With the rapid development of mobile terminals and the convenience brought by applications, more and more people are involved in information registration and identity authentication on applications (APPs). In particular, in APPs that need to review identity information, it is often necessary to collect image information such as ID cards or bank cards.

[0004] In the prior art, an image is usually captured by a terminal, and then a solidified model is loaded through a software or hardware chip algorithm to extract the content of the captured image, and the extracted image content is sent to a server for image quality detection and content authentication.

[0005] However, in the prior art, when the collected images are sent to the server and the server fails the review, the review failure information is fed back to the terminal, requiring the user to re-take the image at the terminal and then re-submit it, which will cause the entire review process to take a long time and reduce the efficiency of image review. Summary of the invention

[0006] In view of this, the purpose of the embodiments of the present application is to provide an image processing method, device, electronic device and storage medium to solve the problem of low image review efficiency existing in the prior art.

[0007] In a first aspect, an embodiment of the present application provides an image processing method, the method comprising:

[0008] Acquire an image to be reviewed, wherein the image to be reviewed includes information to be reviewed;

[0009] Using at least one audit model corresponding to the image to be audited, verifying whether the image to be audited meets the audit conditions, and obtaining and outputting the audit result;

[0010] If the review result indicates that the image to be reviewed does not meet the review condition, a new image to be reviewed collected by the user based on the review result is received.

[0011] Optionally, receiving a new image to be reviewed collected by the user based on the review result includes:

[0012] receiving the new image to be reviewed that is captured by the user based on the review result; or,

[0013] The new image to be reviewed uploaded by the user based on the review result is received.

[0014] Optionally, obtaining the image to be reviewed includes:

[0015] In response to a target audit function start instruction, an image to be audited corresponding to the target audit function is acquired.

[0016] Optionally, the adopting at least one audit model corresponding to the image to be audited to verify whether the image to be audited meets the audit condition includes:

[0017] Determining at least one audit model corresponding to the image to be reviewed according to the audit information of the image to be reviewed;

[0018] At least one audit model corresponding to the image to be audited is used to verify whether the image to be audited meets the audit conditions.

[0019] Optionally, the image to be reviewed includes at least one of the following: a user face image, an ID card image, a bank card image, and a driver's license image.

[0020] Optionally, determining at least one audit model corresponding to the image to be reviewed according to the review information of the image to be reviewed includes:

[0021] According to the type of the to-be-audited information of the to-be-audited image, at least one corresponding audit model is adaptively called through a model calling interface.

[0022] Optionally, the adopting at least one audit model corresponding to the image to be audited to verify whether the image to be audited meets the audit condition includes:

[0023] Using a type verification model to verify whether the image to be reviewed is a preset type image;

[0024] If the image to be reviewed is of the preset type, a quality verification model is used to verify whether the image quality of the image to be reviewed meets preset requirements.

[0025] Optionally, the adopting a type verification model to verify whether the image to be reviewed is an image of a preset type includes:

[0026] Using a preset position frame, determining whether the shooting parameters of the image to be reviewed meet the preset requirements;

[0027] If the shooting parameters of the image to be reviewed meet the preset requirements, it is verified whether the image to be reviewed is an image of a preset type.

[0028] Optionally, the method further comprises:

[0029] If the review result indicates that the image to be reviewed meets the review condition, a preset recognition model is used to identify and obtain target content in the image to be reviewed;

[0030] And send an audit notification to the server, the audit notification including: user identification, the audit result and the target content.

[0031] Optionally, the output audit result includes:

[0032] Displaying the audit result on a display screen; and / or,

[0033] The audit result is indicated by the color of the indicator light.

[0034] In a second aspect, an embodiment of the present application provides an image processing device, including: an acquisition module, a verification module, and a receiving module;

[0035] The acquisition module is used to acquire the image to be reviewed, and the image to be reviewed includes information to be reviewed;

[0036] The verification module is used to use at least one audit model corresponding to the image to be audited to verify whether the image to be audited meets the audit conditions, and obtain and output the audit result;

[0037] The receiving module is configured to receive a new image to be reviewed collected by a user based on the review result if the review result indicates that the image to be reviewed does not meet the review condition.

[0038] Optionally, the receiving module is specifically configured to receive the new image to be reviewed that is photographed and acquired by the user based on the review result; or, to receive the new image to be reviewed that is uploaded by the user based on the review result.

[0039] Optionally, the acquisition module is specifically used to respond to a target audit function start instruction to acquire an image to be audited corresponding to the target audit function.

[0040] Optionally, the verification module is specifically used to determine at least one audit model corresponding to the image to be reviewed based on the review information of the image to be reviewed; and use at least one audit model corresponding to the image to be reviewed to verify whether the image to be reviewed meets the audit conditions.

[0041] Optionally, the image to be reviewed includes at least one of the following: a user face image, an ID card image, a bank card image, and a driver's license image.

[0042] Optionally, the verification module is specifically configured to adaptively call at least one corresponding review model through a model calling interface according to the type of the information to be reviewed of the image to be reviewed.

[0043] Optionally, the verification module is specifically used to use a type verification model to verify whether the image to be reviewed is a preset type image; if the image to be reviewed is the preset type image, a quality verification model is used to verify whether the image quality of the image to be reviewed meets preset requirements.

[0044] Optionally, the verification module is specifically used to use a preset position frame to determine whether the shooting parameters of the image to be reviewed meet preset regulations; if the shooting parameters of the image to be reviewed meet preset regulations, verify whether the image to be reviewed is a preset type image.

[0045] Optionally, the device further includes: an identification module and a sending module;

[0046] The recognition module is configured to use a preset recognition model to recognize and obtain target content in the image to be reviewed if the review result indicates that the image to be reviewed meets the review condition;

[0047] The sending module is used to send an audit notification to the server, and the audit notification includes: a user identifier, the audit result and the target content.

[0048] Optionally, the outputting the audit result includes: displaying the audit result through a display screen; and / or indicating the audit result through the color of an indicator light.

[0049] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the storage medium communicate through the bus, and the processor executes the machine-readable instructions to perform the steps of the image processing method provided in the first aspect.

[0050] In a fourth aspect, an embodiment of the present application provides a storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the image processing method provided in the first aspect are executed.

[0051] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program / instructions, which, when executed by a processor, implement the steps of the image processing method provided in the first aspect.

[0052] The image processing method, device, electronic device and storage medium provided in the embodiments of the present application obtain an image to be reviewed, which includes information to be reviewed; adopt at least one review model corresponding to the image to be reviewed to verify whether the image to be reviewed meets the review conditions, and obtain and output the review result; if the review result indicates that the image to be reviewed does not meet the review conditions, receive a new image to be reviewed collected by the user based on the review result, which greatly saves image review time and improves image review efficiency to a certain extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0054] Figure 1 is a block diagram of an image processing system according to some embodiments of the present application;

[0055] Figure 2 A schematic diagram showing exemplary hardware and software components of an electronic device of some embodiments of the present application;

[0056] Figure 3 A schematic diagram of an image processing method provided in an embodiment of the present application is shown;

[0057] Figure 4 A schematic diagram of another image processing method provided in an embodiment of the present application is shown;

[0058] Figure 5 A schematic diagram of another image processing method provided in an embodiment of the present application is shown;

[0059] Figure 6 A schematic diagram of another image processing method provided in an embodiment of the present application is shown;

[0060] Figure 7 A schematic diagram of another image processing method provided in an embodiment of the present application is shown;

[0061] Figure 8 A schematic diagram of another image processing method provided in an embodiment of the present application is shown;

[0062] Fig. 9 A schematic diagram of another image processing method provided in an embodiment of the present application is shown;

[0063] Fig.10 A schematic diagram of the structure of an image processing device provided in an embodiment of the present application is shown;

[0064] Fig.11 A schematic diagram of the structure of another image processing device provided in an embodiment of the present application is shown;

[0065] Fig.12 A schematic diagram of the structure of another image processing device provided in an embodiment of the present application is shown;

[0066] Fig.13 A schematic diagram of the structure of another image processing device provided in an embodiment of the present application is shown;

[0067] Fig.14 A schematic diagram of the structure of another image processing device provided in an embodiment of the present application is shown;

[0068] Fig.15 A schematic diagram of the structure of another image processing device provided in an embodiment of the present application is shown;

[0069] Fig.16 A schematic diagram of the structure of another image processing device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0070] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the present application, or remove one or more operations from the flowchart.

[0071] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0072] In order to enable those skilled in the art to use the contents of this application, the following implementation methods are provided in conjunction with the specific application scenario "identity authentication". For those skilled in the art, the general principles defined herein can be applied to other embodiments and application scenarios without departing from the spirit and scope of this application. Although this application is mainly described around identity authentication, it should be understood that this is only an exemplary embodiment. This application can be applied to any other scenario. For example, this application can be applied to information registration, account activation, etc.

[0073] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0074] Figure 1 is a block diagram of an image processing system of some embodiments of the present application. For example, the image processing system may be an application platform for identity authentication, information registration, account activation, etc.

[0075] The image processing system may include one or more of a server 110 , a network 120 , a terminal 130 , and a database 140 . The server 110 may include a processor for executing instruction operations.

[0076] In some embodiments, server 110 may be a single server or a server group. The server group may be centralized or distributed (for example, server 110 may be a distributed system). In some embodiments, server 110 may be local or remote relative to the terminal. For example, server 110 may access information and / or data stored in terminal 130 or database 140, or any combination thereof, via network 120. As another example, server 110 may be directly connected to at least one of terminal 130 and database 140 to access stored information and / or data. In some embodiments, server 110 may be implemented on a cloud platform; by way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an inter-cloud, a multi-cloud, etc., or any combination thereof. In some embodiments, server 110 may be implemented on a cloud platform having the cloud computing capabilities described in this application. Figure 2 One or more of the components shown are implemented on the electronic device 200 .

[0077] In some embodiments, the server 110 may include a processor. In some embodiments, the processor may include one or more processing cores (e.g., a single-core processor (S) or a multi-core processor (S)). By way of example only, the processor may include a central processing unit (CPU), an application specific integrated circuit (ASIC), an application specific instruction set processor (ASIP), a graphics processing unit (GPU), a physical processing unit (PPU), a digital signal processor (DSP), a field programmable gate array (FPGA), a programmable logic device (PLD), a controller, a microcontroller unit, a reduced instruction set computer (RISC), or a microprocessor, or any combination thereof.

[0078] The network 120 may be used for the exchange of information and / or data. In some embodiments, the network 120 may be any type of wired or wireless network, or a combination thereof. By way of example only, the network 120 may include a wired network, a wireless network, a fiber optic network, a telecommunications network, an intranet, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network (MAN), a wide area network (WAN), a public switched telephone network (PSTN), a Bluetooth network, a ZigBee network, or a near field communication (NFC) network, or any combination thereof. In some embodiments, the network 120 may include one or more network access points. For example, the network 120 may include a wired or wireless network access point, such as a base station and / or a network switching node, through which one or more components of the service data prediction system may be connected to the network 120 to exchange data and / or information.

[0079] In some embodiments, the database 140 may be connected to the network 120 to communicate with one or more components in the image processing system (e.g., the server 110, the terminal 130, etc.). One or more components in the image processing system may access data or instructions stored in the database 140 via the network 120. In some embodiments, the database 140 may be directly connected to one or more components in the image processing system (e.g., the server 110, the terminal 130, etc.); or, in some embodiments, the database 140 may also be part of the server 110.

[0080] Figure 2 A schematic diagram showing exemplary hardware and software components of an electronic device according to some embodiments of the present application.

[0081] For example, the processor may be used on the electronic device 200 and configured to execute the functions in the present application.

[0082] The electronic device 200 can be a general-purpose computer or a special-purpose computer, both of which can be used to implement the resource processing method of the present application. Although only one computer is shown in the present application, for convenience, the functions described in the present application can be implemented in a distributed manner on multiple similar platforms to balance the processing load.

[0083] For example, the electronic device 200 may include a network port 210 connected to a network, one or more processors 220 for executing program instructions, a communication bus 230, and storage media 240 in different forms, such as a disk, ROM, or RAM, or any combination thereof. Exemplarily, the computer platform may also include program instructions stored in ROM, RAM, or other types of non-temporary storage media, or any combination thereof. The method of the present application may be implemented according to these program instructions. The electronic device 200 also includes an input / output (I / O) interface 250 between the computer and other input / output devices (e.g., a keyboard, a display screen).

[0084] For ease of explanation, only one processor is described in the electronic device 200. However, it should be noted that the electronic device 200 in the present application may also include multiple processors, so the steps performed by one processor described in the present application may also be performed jointly or individually by multiple processors. For example, if the processor of the electronic device 200 performs step A and step B, it should be understood that step A and step B may also be performed jointly by two different processors or individually in one processor. For example, the first processor performs step A, the second processor performs step B, or the first processor and the second processor perform steps A and B together.

[0085] Figure 3 FIG. 1 shows a flow chart of an image processing method provided by an embodiment of the present application. The execution subject of the present embodiment may be a terminal, or a device with processing functions such as a server or a processor. Figure 3 As shown, the method includes:

[0086] S101, collecting and obtaining images to be reviewed, where the images to be reviewed include information to be reviewed.

[0087] Usually, when a user registers software or applies for application access authorization, it is necessary to collect the user's portrait or a photo of the user's relevant ID and match it with the relevant information of the user stored in the server backend database for identity verification.

[0088] Optionally, an image to be reviewed is obtained, which may be a real-time user portrait, or an ID card image, a bank card image, or a driver's license image of the user. The image may be collected by a camera built into the terminal or by an external camera, without any specific limitation.

[0089] The acquired image to be reviewed includes the information to be reviewed, for example, when the acquired image is a user's face image, the corresponding information to be reviewed may be facial features, etc.; when the acquired image is an ID card image, the corresponding information to be reviewed may include: ID card number, user name, ID card portrait page, ID card national emblem page, etc.; when the acquired image is a bank card image, the corresponding information to be reviewed may include: bank card number, bank name, etc. Specifically, the acquired information to be reviewed is different depending on the type of image.

[0090] S102: using at least one audit model corresponding to a preset audit rule to verify whether the image to be audited meets the audit conditions, and obtaining the audit result.

[0091] In step S101, the audit information of the image to be reviewed is acquired, and the audit information is the image feature information contained in the image to be reviewed. The terminal can review the acquired audit information according to the audit model pre-trained and encapsulated in the terminal to verify whether the acquired image to be reviewed meets the requirements.

[0092] It should also be noted that in this application, different models are required for different audit information, for example, the model for processing faces is different from the model for processing vehicles. Accordingly, a unified model calling interface can also be configured in the client. Different types of audit information may be required for different functions enabled by the user on the client. For example, when the user identity audit function is enabled, the corresponding collected images to be audited can be face images, ID card images, etc.; and when the vehicle monitoring function is enabled, the corresponding collected images to be audited can be car images, etc. The client can adaptively call one or more corresponding models through the model calling interface to perform image detection, recognition and other operations without additional changes to the specific content of the client or terminal.

[0093] Optionally, different audit models can be selected for image audit according to the audited information of different images to be audited. For example, for image text information, an image type classification model, a quality classification model, or a text content classification model can be used for audit; for audio and video images, a sound quality classification model, a video target detection model, or a video fluency detection model can be used for audit.

[0094] In some embodiments, the audit models all correspond to preset audit rules, and the preset audit rules of the audit model are used to audit the audited information. For example, for ID card images, the image classification can be performed according to the rules such as the image location box or the length of the ID number in the image type classification model. Usually the ID card number is 18 digits and the bank card number is 19 digits. Then, the correctness of the ID card type can be determined based on the length of the target number. In addition, there are differences in the size of the ID card and the bank card, and auxiliary judgment can be performed based on the set location box size.

[0095] S103. Display the audit results.

[0096] Optionally, the image review can be conducted through multiple review models integrated on the terminal, and the terminal can obtain the review results and feed back the review results to the user. Optionally, the results can be displayed on the terminal display screen or by indicator lights, for example, if the review is passed, the terminal indicator light is green, if the review is not passed, the indicator light is red, etc. The embodiment does not impose any specific restrictions on the display method of the results.

[0097] In summary, the image processing method provided in the embodiment of the present application, through multiple audit models on the terminal, combines the audit models according to preset rules and the image information to be audited, audits the collected images to be audited, and feeds back the audit results to the user, which greatly saves the image audit time and improves the image audit efficiency to a certain extent.

[0098] Figure 4 FIG. 1 shows another flow chart of an image processing method provided by an embodiment of the present application. Further, as shown in FIG. Figure 4 As shown, at least one audit model corresponding to the preset audit rule is used to verify whether the image to be audited meets the audit conditions and obtain the audit result, including:

[0099] S201: Use a type verification model to verify whether the image to be reviewed is an image of a preset type.

[0100] It should be noted that the type verification model is used to judge the type of the collected image to be reviewed, that is, to make a preliminary judgment on the image. If the type of the collected image is incorrect, the subsequent review process will be terminated directly to improve the efficiency of image review.

[0101] The types of images to be reviewed may include: ID card images, driver's license images, bank cards, etc. For ID card images, the front and back images are different from the driver's license images and the front and back images of bank cards. Based on these feature information and preset type image information, a type verification model can be used to determine the image type.

[0102] S202: If the image to be reviewed is of a preset type, a quality verification model is used to verify whether the image quality of the image to be reviewed meets preset requirements, and a review result is obtained.

[0103] For the verification result obtained through the type verification model verification, if the verification result is that the image to be reviewed is a preset type image, the quality verification model can be used to further verify whether the quality of the obtained image meets the requirements.

[0104] Usually, when verifying identity information or registering information, the quality requirements for the collected image information are relatively high. The clarity of the image largely determines whether the specific content information in the image can be correctly extracted. The above-mentioned images to be reviewed that meet the type requirements can be further reviewed through the quality verification model, and similarly, the review results can be obtained.

[0105] Figure 5 A schematic diagram of another image processing method provided in an embodiment of the present application is shown. Figure 5 As shown, a type verification model is used to verify whether the image to be reviewed is a preset type image, including:

[0106] S301: Using a preset position frame, determine whether the shooting parameters of the image to be reviewed meet preset requirements.

[0107] It should be noted that before conducting an image type review, you can first use the preset position box to determine whether the angle, position, distance, etc. of the captured image meet the requirements during the image acquisition process. For different types of images, the corresponding position box sizes may also be different. When acquiring images, if the image to be reviewed is located within the position box, the image to be reviewed will comply with the preset rules; when part of the image is outside the box, the captured image is incomplete, and type verification cannot be performed.

[0108] S302: If the shooting parameters of the image to be reviewed meet the preset requirements, verify whether the image to be reviewed is a preset type of image.

[0109] After the parameter verification is performed according to the preset position frame, if the shooting parameters meet the preset regulations, the type verification model can be further used to verify the image type and obtain the verification result.

[0110] Figure 6 FIG. 1 shows another flow chart of an image processing method provided by an embodiment of the present application. Further, as shown in FIG. Figure 6 As shown, the method also includes:

[0111] S401: Acquire a first sample image, and classify the first sample image.

[0112] It should be noted that before using the above audit model for image audit, model training is required. Optionally, a first sample image is obtained, wherein the first sample image may include multiple types of images to be audited, such as: identity card images, bank card images, driver's license images, etc., and these first samples are classified.

[0113] Optionally, classification can be performed manually or by image classification algorithms. In some embodiments, a network detection model (e.g., YOLO2, You Only LiveOnce) that uses a mobile convolutional neural network to extract features can be used in conjunction with convolutional networks such as VGG (Visual Geometry Group, deep convolutional network) and Resnet (Residual Network) as a feature extraction method. Specifically, it is not limited to the above methods, and other image feature extraction and classification algorithms can also be used, such as wavelet transform, SVM (Support Vector Machine), etc.

[0114] S402 : Label the type information and shooting parameters of the classified first sample images respectively, and obtain a plurality of labeled groups of first sample images to be trained.

[0115] After the first sample image is classified, multiple sets of training samples are obtained. The multiple sets of training sample images are labeled. For example, for the ID card image class, all images contained therein are labeled as ID cards, and for the bank card image class, all images contained therein are labeled as bank cards, etc. Thus, multiple training samples are obtained.

[0116] S403: Use the labeled groups of first sample images to be trained to obtain a type verification model.

[0117] It should be noted that labeling the multiple groups of classified images separately can facilitate inputting the labeled images into a computer, so that the computer can train and obtain a type verification model based on the labeled information.

[0118] Figure 7 A schematic diagram of another image processing method provided in an embodiment of the present application is shown. Figure 7 As shown, the method also includes:

[0119] S501: Acquire second sample images, and group the second sample images according to the quality of each image.

[0120] Similarly, as in the above step S401, it is also necessary to train and obtain a quality verification model. Optionally, a second sample image is obtained, wherein the images in the second sample image include: clear images, blurred images, or images of various qualities such as reflective images, and the second sample images are grouped according to the various quality conditions in the second sample image. Among them, clear images are grouped, blurred images are grouped, reflective images are grouped, and so on. Optionally, the image quality is not limited to clarity, blur and reflection, but can also be defects, wrinkles, etc.

[0121] S502 : Label the quality attribute information of the grouped second sample images respectively, and obtain a plurality of labeled groups of second sample images to be trained.

[0122] Similarly, as in step S402, the grouped information of the plurality of samples to be trained is labeled to obtain a plurality of groups of labeled second sample images to be trained.

[0123] Optionally, in some embodiments, an SVM support vector machine may also be used for image classification, and a Res18 (Residual Network-18) deep network classification model may also be used for image classification.

[0124] S503: Use the labeled groups of second sample images to be trained to obtain a quality verification model.

[0125] Similarly, the labeled groups of second sample images to be trained can be used as the input of the computer, and the quality verification model can be obtained by training according to the image classification algorithm.

[0126] Figure 8 FIG. 1 shows another flow chart of an image processing method provided by an embodiment of the present application. Further, as shown in FIG. Figure 8 As shown, at least one audit model corresponding to the preset audit rule is used to verify whether the image to be audited meets the audit conditions. After obtaining the audit result, it also includes:

[0127] S601: If the audit result indicates that the image to be audited meets the audit conditions, a preset recognition model is used to identify and obtain target content in the image to be audited.

[0128] The aforementioned image information to be reviewed has been preliminarily reviewed through the type verification model and the quality verification model. It only judges whether the type and quality of the required image are qualified, but cannot judge whether it is the required user's ID image. Therefore, it is usually necessary to extract the specific text content information in the image to be reviewed for accurate verification, so as to avoid mistakenly reviewing user A's ID information as user B's ID information.

[0129] Optionally, after the image to be reviewed passes the verification of the type verification model and the quality verification model, a preset recognition model may be further used to verify the target content in the image to be reviewed.

[0130] S602, and sending an audit notification to the server, the audit notification includes: user identification, audit results and target content.

[0131] Optionally, the preset recognition model can be integrated into the terminal, and the terminal uses the preset recognition model to review the images to be reviewed that have passed the preliminary review. The review result is sent to the server, specifically, the target content in the image to be reviewed can be sent to the server, so that the server can store the content information of the image to be reviewed corresponding to the user identifier.

[0132] Fig. 9 A schematic diagram of a flow chart of another image processing method provided in an embodiment of the present application is shown. Further, the method further includes:

[0133] S701: Acquire a third sample image, where the third sample image includes: annotated target content.

[0134] Similarly, it is necessary to train and obtain the preset recognition model. Optionally, obtain a third sample image, and specifically obtain the annotated target content included in the third sample image. It should be noted that the preset recognition model can be trained by text annotation of key fields in the image. For example: for an ID card image, the corresponding target content can be information such as the ID card number, name, birthday, etc.; for a bank card image, the corresponding target content can be the bank card number, bank name, etc.

[0135] S702: Use the third sample image to train and obtain a preset recognition model.

[0136] Optionally, the preset recognition model may be trained and acquired by using the third sample image after the above annotation and a corresponding recognition method.

[0137] In some embodiments, text positioning, rule segmentation, and CNN convolutional neural network algorithms can be used for training. Model training can also be performed using methods such as CTPN (Connectionist Text Proposal Network, natural scene text detection), combined with CRNN (Convolutional Recurrent Neural Network, convolutional recurrent neural network), or DenseNet (Dense Convolutional Network, dense convolutional network) combined with CTC (Connectionist Temporal Classification, temporal classification algorithm), etc., specifically, not limited to the methods listed here.

[0138] Furthermore, at least one audit model corresponding to the preset audit rule is used to verify whether the image to be audited meets the audit condition. After the audit result is obtained, the method further includes:

[0139] If the audit result indicates that the image to be audited meets the audit conditions, an audit instruction is sent to the server. The audit instruction is used to instruct the server to extract the target content of the image to be audited. The audit instruction includes: user identification, audit result and image to be audited.

[0140] Optionally, image type review and quality review can be performed at the terminal, and the review results can be sent to the server. The server can extract the target content in the sent image to be reviewed, and verify the extracted target content according to a preset recognition model.

[0141] Optionally, the user identifier may be a user terminal number, a user's mobile phone number, etc. In addition, the server may also match the target content in the image to be reviewed corresponding to the extracted user identifier with the user information stored in the server backend to conduct content review.

[0142] It should be noted that when the review is passed, the server stores the review information, and when the review is not passed, the image to be reviewed can be re-acquired through the terminal until the review is passed.

[0143] The image processing method provided in the embodiment of the present application uses multiple audit models on the terminal to combine the audit models according to preset rules and the image information to be audited, audits the collected images to be audited, and feeds back the audit results to the user. At the same time, for the case of failure in the audit, the audit results can be fed back in time, and the image can be re-collected for re-audit. This method greatly saves the image audit time and improves the image audit efficiency to a certain extent.

[0144] Fig.10 A schematic diagram of the structure of an image processing device provided in an embodiment of the present application is shown. Fig.10 As shown, the device includes: a collection module 801, a verification module 802 and a display module 803;

[0145] The acquisition module 801 is used to acquire the image to be reviewed, which includes the information to be reviewed; the verification module 802 is used to use at least one review model corresponding to the preset review rules to verify whether the image to be reviewed meets the review conditions and obtain the review results; the display module 803 is used to display the review results.

[0146] Furthermore, the verification module 802 is specifically used to use a type verification model to verify whether the image to be reviewed is a preset type image; if the image to be reviewed is a preset type image, a quality verification model is used to verify whether the image quality of the image to be reviewed meets preset requirements to obtain the review result.

[0147] Furthermore, the verification module 802 is specifically used to use a preset position frame to determine whether the shooting parameters of the image to be reviewed meet the preset regulations; if the shooting parameters of the image to be reviewed meet the preset regulations, verify whether the image to be reviewed is a preset type image.

[0148] Fig.11 FIG. 4 shows a schematic diagram of another image processing device structure provided in an embodiment of the present application. Fig.11 As shown, further, the device also includes: a classification module 804, a first labeling module 805 and a first training module 806;

[0149] The classification module 804 is used to obtain the first sample image and classify the first sample image; the first labeling module 805 is used to respectively label the type information and shooting parameters of the classified first sample image, and obtain multiple groups of labeled first sample images to be trained; the first training module 806 is used to use the multiple groups of labeled first sample images to be trained to obtain a type verification model.

[0150] Fig.12 A schematic diagram of the structure of another image processing device provided in an embodiment of the present application is shown. Fig.12 As shown, further, the device also includes: a grouping module 807, a second labeling module 808 and a second training module 809;

[0151] The grouping module 807 is used to obtain the second sample images and group them according to the quality of each image in the second sample images; the second labeling module 808 is used to label the quality attribute information of the grouped second sample images respectively and obtain multiple groups of labeled second sample images to be trained; the second training module 809 is used to use the multiple groups of labeled second sample images to be trained to obtain the quality verification model.

[0152] Fig.13 A schematic diagram of the structure of another image processing device provided in an embodiment of the present application is shown. Fig.13 As shown, further, it also includes: an identification module 810 and a first sending module 811;

[0153] The recognition module 810 is used to use a preset recognition model to identify and obtain the target content in the image to be reviewed if the review result indicates that the image to be reviewed meets the review conditions; the first sending module 811 is used to send a review notification to the server, and the review notification includes: user identification, review results and target content.

[0154] Fig.14 FIG. 4 shows a schematic diagram of another image processing device structure provided by an embodiment of the present application. Fig.14 As shown, further, it also includes: an acquisition module 812 and a third training module 813;

[0155] The acquisition module 812 is used to acquire a third sample image, where the third sample image includes: annotated target content; the third training module 813 is used to use the third sample image to train and acquire a preset recognition model.

[0156] Fig.15 FIG. 4 shows a schematic diagram of another image processing device structure provided by an embodiment of the present application. Fig.15 As shown, further, it also includes a second sending module 814; the second sending module 814 is used to send an audit instruction to the server if the audit result indicates that the image to be audited meets the audit conditions, and the audit instruction is used to instruct the server to extract the target content of the image to be audited. The audit instruction includes: user identification, audit results and image to be audited.

[0157] The above-mentioned device can be used to execute the method provided by the above-mentioned method embodiment. The specific implementation method and technical effect are similar and will not be repeated here.

[0158] Fig.16 A schematic diagram of the structure of another image processing device provided in an embodiment of the present application is shown. Fig.16 As shown, the device includes: a processor 901 and a memory 902, wherein: the memory 902 is used to store programs, and the processor 901 calls the program stored in the memory 902 to execute the above method embodiment. The specific implementation method and technical effect are similar and will not be repeated here.

[0159] The device can be integrated into a terminal, a server or other equipment, and is not limited in this application.

[0160] Optionally, the present invention also provides a program product, such as a computer-readable storage medium, comprising a program, which is used to execute the above method embodiment when executed by a processor.

[0161] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the method embodiment, and will not be repeated in this application. In the several embodiments provided in this application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0162] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0163] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0164] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks, or optical disks.

[0165] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An image processing method, characterized in that: include: Acquire an image to be reviewed, wherein the image to be reviewed includes information to be reviewed; Using at least one audit model corresponding to the image to be audited, verifying whether the image to be audited meets the audit conditions, and obtaining and outputting the audit result; If the review result indicates that the image to be reviewed does not meet the review condition, receiving a new image to be reviewed collected by the user based on the review result; The adopting at least one audit model corresponding to the image to be audited to verify whether the image to be audited meets the audit condition includes: Determining at least one audit model corresponding to the image to be reviewed according to the audit information of the image to be reviewed; Using at least one audit model corresponding to the image to be audited, verifying whether the image to be audited meets the audit conditions; The step of determining at least one audit model corresponding to the image to be audited according to the audit information of the image to be audited includes: Adaptively calling at least one corresponding review model through a model calling interface according to the type of the to-be-reviewed information of the to-be-reviewed image; If the review result indicates that the image to be reviewed meets the review condition, a preset recognition model is used to identify and obtain target content in the image to be reviewed; And send an audit notification to the server, the audit notification including: user identification, the audit result and the target content.

2. The method according to claim 1, characterized in that: Receiving a new image to be reviewed collected by the user based on the review result, including: The new image to be reviewed is received by the user through photographing based on the review result.

3. The method according to claim 1, characterized in that The step of obtaining the image to be reviewed includes: In response to a target audit function start instruction, an image to be audited corresponding to the target audit function is acquired.

4. The method according to claim 1, characterized in that: The image to be reviewed includes at least one of the following: a user face image, an ID card image, a bank card image, and a driver's license image.

5. The method according to claim 1, characterized in that The adopting at least one audit model corresponding to the image to be audited to verify whether the image to be audited meets the audit condition includes: Using a type verification model to verify whether the image to be reviewed is a preset type image; If the image to be reviewed is of the preset type, a quality verification model is used to verify whether the image quality of the image to be reviewed meets preset requirements.

6. The method according to claim 5, characterized in that The adopting type verification model to verify whether the image to be reviewed is a preset type image includes: Using a preset position frame, determining whether the shooting parameters of the image to be reviewed meet the preset requirements; If the shooting parameters of the image to be reviewed meet the preset requirements, it is verified whether the image to be reviewed is an image of a preset type.

7. The method according to claim 1, characterized in that The output audit results include: The audit result is displayed on a display screen; and / or the audit result is indicated by the color of an indicator light.

8. An image processing device, characterized in that: include: Acquisition module, verification module, receiving module; The acquisition module is used to acquire the image to be reviewed, and the image to be reviewed includes information to be reviewed; The verification module is used to use at least one audit model corresponding to the image to be audited to verify whether the image to be audited meets the audit conditions, and obtain and output the audit result; The receiving module is configured to receive a new image to be reviewed collected by the user based on the review result if the review result indicates that the image to be reviewed does not meet the review condition; The verification module is specifically used to determine at least one verification model corresponding to the image to be reviewed according to the information to be reviewed of the image to be reviewed; and to verify whether the image to be reviewed meets the review conditions by using at least one verification model corresponding to the image to be reviewed; The verification module is specifically used to adaptively call at least one corresponding review model through a model calling interface according to the type of the information to be reviewed of the image to be reviewed; The device also includes an identification module and a sending module; The recognition module is configured to use a preset recognition model to recognize and obtain target content in the image to be reviewed if the review result indicates that the image to be reviewed meets the review condition; The sending module is used to send an audit notification to the server, and the audit notification includes: a user identifier, the audit result and the target content.

9. An electronic device, characterized in that: include: A processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the storage medium communicate via the bus, and the processor executes the machine-readable instructions to perform the steps of the image processing method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the image processing method according to any one of claims 1 to 7 are executed.

11. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the image processing method according to any one of claims 1 to 7 are implemented.