A method and device for processing image information

Abstract

The present invention discloses a method and device for processing image information, and relates to the field of artificial intelligence technology. The specific implementation of the method includes: receiving a first image sent by a client; dividing the first image into multiple sub-slices; splicing multiple second images that are unrelated to the user information with the multiple sub-slices respectively to obtain multiple third images, and sending the multiple third images to a recognition module, so that the recognition module recognizes the user information based on the multiple third images. This implementation can accurately and completely obtain image information, improve the efficiency of image transmission and image information processing, ensure the security of image information, prevent the leakage of sensitive information, and improve user experience.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method and device for processing image information. Background Art

[0002] With the gradual development and maturity of Internet technology, various applications such as shopping, entertainment, social networking, finance, communications, government affairs, and medical care all involve uploading pictures. Pictures are likely to contain personal information, such as name, address, and ID number, and the public is paying more and more attention to the protection of privacy information. Therefore, the protection of personal information when uploading pictures is even more important.

[0003] When uploading existing pictures, personal information is mainly entered through automatic image recognition, or the picture is encrypted when it is uploaded and then decrypted by backend staff and entered manually.

[0004] Information leakage may occur during the process of automatic image recognition, and when manual input is used, back-end staff can obtain all the information, which also poses a risk of leakage. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a method and device for processing image information. Since the staff cannot obtain the complete image, the security of the image information can be guaranteed, the leakage of sensitive information can be prevented, and the credibility of the protection of personal privacy during image information processing can be improved, thereby enhancing the user experience.

[0006] Furthermore, according to the image information processing method and device of the present invention, the efficiency of image transmission and image information processing can be improved by determining the feature area through intercepting the template, and the image information can be accurately and completely obtained through the verification of the spliced ​​image.

[0007] To achieve the above object, according to one aspect of an embodiment of the present invention, a method for processing image information is provided, comprising:

[0008] Receiving a first picture sent by a client; wherein the first picture indicates user information corresponding to the client;

[0009] Dividing the first picture into a plurality of sub-slices;

[0010] A plurality of second images that are not related to the user information are respectively spliced ​​with the plurality of sub-slices to obtain a plurality of third images, and the plurality of third images are sent to a recognition module, so that the recognition module recognizes the user information according to the plurality of third images.

[0011] Optionally, it also includes:

[0012] Receive the recognition result corresponding to each of the third pictures returned by the recognition module, and determine the user information according to the recognition result.

[0013] Optionally, each of the recognition results includes first verification information of the corresponding second picture and image information of the corresponding sub-slice; and determining the user information according to the recognition result includes:

[0014] Identify second verification information from each of the third images;

[0015] determining whether the first verification information and the second verification information match, and if so, determining that the image information corresponding to the first verification information is correct;

[0016] The user information is determined based on each correct image information.

[0017] Optionally, determining the user information according to each correct image information includes:

[0018] Determining target image information corresponding to the user information from the correct image information;

[0019] The target image information is spliced ​​to obtain the user information.

[0020] Optionally, when there are multiple identification modules, determining the user information according to the identification result includes:

[0021] According to the multiple recognition results respectively returned by the multiple recognition modules, a target recognition result with the highest frequency among the multiple recognition results is determined, and the user information is determined according to the target recognition result.

[0022] Optionally, it is determined whether every two recognition results are the same; if so, the two recognition results are merged into one recognition result, and the occurrence frequency of the recognition result is incremented.

[0023] Optionally, determining the user information according to the recognition result includes:

[0024] Based on the identification result, sensitive data in the user information is determined.

[0025] Optionally, it also includes:

[0026] In response to the target service request of the client, the target service request is processed according to the sensitive data.

[0027] Optionally, dividing the first picture into a plurality of sub-slices includes:

[0028] Determining a feature area corresponding to the user information in the first picture;

[0029] The feature area is segmented to obtain the plurality of sub-slices, so that each of the sub-slices corresponds to part of the user information.

[0030] Optionally, when the user information includes a plurality of characteristic characters, segmenting the characteristic area includes:

[0031] Determine in the feature area a plurality of first areas corresponding to the plurality of feature characters respectively, and a second area between every two feature characters;

[0032] determining a first segmentation boundary in the second region;

[0033] The multiple first regions are divided according to the first segmentation boundary to obtain the multiple sub-slices, each sub-slice including one or more of the first regions.

[0034] Optionally, segmenting the characteristic region includes:

[0035] The feature region is segmented according to a segmentation template with a preset segmentation size to obtain the sub-slices.

[0036] Optionally, according to a segmentation template having a preset segmentation size, a second segmentation boundary to be segmented is determined in the feature area;

[0037] Determine whether the second segmentation boundary is in the second region, and if so, segment the feature region according to the segmentation template to obtain sub-slices with the preset segmentation size.

[0038] Optionally, when it is determined that the second segmentation boundary is not in the second area, the method further includes:

[0039] Determine a second region having the shortest distance from the second segmentation boundary;

[0040] A third segmentation boundary is determined in the second region, and the feature region is segmented according to the third segmentation boundary.

[0041] Optionally, the characteristic character is determined by optical character recognition.

[0042] Optionally, the second picture has the same data type as the first picture.

[0043] Optionally, the second picture is selected from a pre-built picture library.

[0044] According to another aspect of an embodiment of the present invention, there is provided a picture information processing device, comprising:

[0045] A receiving module, configured to receive a first picture sent by a client; wherein the first picture indicates user information corresponding to the client;

[0046] A segmentation module, used for segmenting the first image into a plurality of sub-slices;

[0047] A splicing module is used to splice multiple second pictures that are unrelated to the user information with the multiple sub-slices respectively to obtain multiple third pictures, and send the multiple third pictures to the recognition module, so that the recognition module recognizes the user information according to the multiple third pictures.

[0048] According to another aspect of an embodiment of the present invention, there is provided an electronic device for processing picture information, comprising:

[0049] one or more processors;

[0050] a storage device for storing one or more programs,

[0051] When the one or more programs are executed by the one or more processors, the one or more processors implement the image information processing method provided by the present invention.

[0052] According to another aspect of an embodiment of the present invention, a computer-readable medium is provided, on which a computer program is stored, and when the program is executed by a processor, the image information processing method provided by the present invention is implemented.

[0053] An embodiment of the above invention has the following advantages or beneficial effects: because a technical means is adopted to divide a picture into multiple sub-slices, each sub-slice only contains part of the user information, and the sub-slices are spliced ​​with irrelevant pictures and transmitted to the recognition module for recognition, the technical problem of the risk of leakage in the existing information entry is overcome, thereby achieving the technical effect of ensuring the security of picture information, preventing the leakage of sensitive information, and improving the credibility of the protection of personal privacy when processing picture information, thereby enhancing the user experience.

[0054] Furthermore, by using the technical means of intercepting templates to determine feature areas, a technical effect of improving the efficiency of image transmission and image information processing is achieved; by using the technical means of verifying spliced ​​images, a technical effect of accurately and completely obtaining image information is achieved.

[0055] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0057] Figure 1 is an exemplary system architecture diagram suitable for applying to the image information processing method or image information processing device of the embodiment of the present invention;

[0058] Figure 2 is a schematic diagram of the main process of the image information processing method according to an embodiment of the present invention;

[0059] Figure 3 is a schematic diagram of a detailed process of a method for processing image information according to an embodiment of the present invention;

[0060] Figure 4 is a schematic diagram of main modules of a picture information processing device according to an embodiment of the present invention;

[0061] Figure 5 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0062] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0063] Figure 1 An exemplary system architecture diagram of a method or device for processing image information suitable for use in an embodiment of the present invention is shown. Figure 1 As shown, an exemplary system architecture of the image information processing method or image information processing device according to an embodiment of the present invention includes:

[0064] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0065] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as financial applications, shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, life service applications, government applications, etc.

[0066] The terminal devices 101 , 102 , and 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0067] The server 105 may be a server that provides various services, such as a background management server that provides support for financial websites browsed by users using the terminal devices 101, 102, and 103. The background management server may analyze and process the received data such as the personal information upload request, and feed back the processing results (such as obtaining personal information based on the picture sent by the terminal device) to the terminal devices 101, 102, and 103.

[0068] It should be noted that the picture information processing method provided in the embodiment of the present invention is generally executed by the server 105 , and accordingly, the picture information processing device is generally disposed in the server 105 .

[0069] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0070] Figure 2 is a schematic diagram of the main process of the image information processing method according to an embodiment of the present invention, such as Figure 2 As shown, the picture information processing method of the present invention includes:

[0071] Step S201, receiving a first picture sent by a client; wherein the first picture indicates user information corresponding to the client.

[0072] In various types of applications such as shopping, entertainment, social networking, finance, communications, and government affairs, it is often necessary to input the user's personal information. In order to improve the user experience and facilitate the user's operation, various applications provide channels for uploading pictures, and the user's personal information can be obtained from the pictures uploaded by the client. When processing picture information, the method of the present invention receives a first picture sent by the client and processes the picture information in the first picture. The first picture indicates the user information corresponding to the picture sent by the client. Exemplarily, the picture information included in the first picture can be various, including standard template information other than user information, irrelevant background information, etc.

[0073] Step S202: divide the first picture into multiple sub-slices.

[0074] After receiving the first image indicating the user information corresponding to the client, the first image is segmented into multiple sub-slices. When segmenting the first image, the feature area corresponding to the user information in the first image is determined by intercepting the template; the user information may include multiple feature characters, and the multiple feature characters are identified by optical character recognition, so as to determine multiple first areas corresponding to the multiple feature characters in the feature area, and the second area between every two feature characters, based on the multiple second areas, the segmentation boundary is determined according to the segmentation template, and the feature area is segmented to obtain multiple sub-slices. Each sub-slice corresponds to part of the user information.

[0075] Step S203: splice a plurality of second images that are not related to the user information with the plurality of sub-slices respectively to obtain a plurality of third images, and send the plurality of third images to a recognition module, so that the recognition module recognizes the user information according to the plurality of third images.

[0076] After the first image is divided into multiple sub-slices, based on a pre-built image library including multiple second images that are not related to user information, multiple second images corresponding to the number of sub-slices are selected, and the multiple second images are respectively spliced ​​with the multiple sub-slices to obtain multiple third images. Exemplarily, the second image can be a verification code image, which is used for subsequent comparison to determine whether the image information corresponding to the sub-slice is correct. The multiple third images are sent to the recognition module, and the recognition module can include one or more, so that the recognition module recognizes the user information based on the multiple third images; when there are multiple recognition modules, the multiple recognition results are compared to determine the target recognition result with the highest frequency in the multiple recognition results, so as to determine the user information based on the target recognition result.

[0077] In an embodiment of the present invention, by receiving a first image sent by a client; dividing the first image into multiple sub-slices; respectively splicing multiple second images that are unrelated to the user information with the multiple sub-slices to obtain multiple third images, and sending the multiple third images to a recognition module, so that the recognition module recognizes the user information based on the multiple third images, etc., it is possible to accurately and completely obtain image information, improve the efficiency of image transmission and image information processing, ensure the security of image information, prevent the leakage of sensitive information, and improve user experience.

[0078] Figure 3 is a schematic diagram of a detailed process of a method for processing image information according to an embodiment of the present invention, such as Figure 3 As shown, the picture information processing method of the present invention includes:

[0079] Step S301: receiving a first picture sent by a client.

[0080] The method of the present invention obtains various information from the received picture and processes the picture when processing the picture information, thereby obtaining the required user information. The first picture sent by the client is received and processed to obtain the user information corresponding to the client; wherein the first picture indicates the user information corresponding to the client, or the first picture may indicate other information unrelated to the user information while indicating the user information corresponding to the client.

[0081] Step S302: determining a feature area corresponding to the user information in the first image according to the captured template.

[0082] After receiving the first picture sent by the client indicating the user information corresponding to the client, the area corresponding to the user information in the first picture is intercepted according to the preset interception template, thereby determining the feature area corresponding to the user information in the first picture. Exemplarily, the first picture sent by the client may be a bill picture, and the preset interception template is used to intercept the area corresponding to the user information such as the number, account number, name, telephone number, address, etc. in the bill picture, thereby determining the feature area corresponding to the user information in the bill picture; wherein the number, account number, name, ID number, telephone number, address, etc. are the core key information in the bill picture.

[0083] The interception template may include multiple types, each of which is in a fixed format. For example, the interception template is in a rectangular shape, and the interception template can be preset by setting the four-point coordinate parameters of the rectangle. When processing the first image, the core key information related to the user information can be located in advance, and then the area corresponding to the user information in the first image can be intercepted by the rectangular interception template, so as to determine the feature area corresponding to the user information in the first image and save it; wherein the intercepted feature area can be saved in the same format as the first image. Exemplarily, based on the bill image to be processed, a interception template matching the area of ​​the core key information is drawn on the bill image of the blank template in advance and saved, so that the system can subsequently process the first image according to the saved interception template; wherein the area of ​​the bill images processed in batches relative to the core key information can be fixed.

[0084] By processing the first image through the interception template and only intercepting the area of ​​the core key information related to the user information in the first image, the accuracy of the image information determination can be improved, the amount of data transmitted by the image can be reduced, and the transmission efficiency of the image can be improved. In addition, because only a part of the image area is intercepted, the visible area of ​​the subsequent process is reduced, which further improves the security of the image information, prevents the leakage of key or irrelevant personal information that the user does not want to be viewed, and improves the user experience.

[0085] In addition to the method of step S302 above, in an embodiment of the present invention, the feature area can also be determined by an image recognition algorithm. For example, AlexNet, VGG, ResNet, Inception, DenseNet, MobileNet and other models are used to identify user information in the first picture, and then the area where the user information is located is used as the feature area.

[0086] Step S303, dividing the feature region into multiple sub-slices.

[0087] After determining the feature region corresponding to the user information in the first image, the feature region is segmented according to the segmentation template to obtain a plurality of sub-slices, each of which corresponds to part of the user information.

[0088] When segmenting the feature area, the feature area is identified by optical character recognition, and a first area corresponding to a feature character and a second area between the feature characters in the feature area are determined. The feature character corresponds to user information, and the user information may include one or more feature characters. The first area may include one or more, and the second area may include multiple. The first segmentation boundary is determined according to the multiple second areas. Based on the determined first segmentation boundary, the feature area is segmented to obtain multiple sub-slices, each of which may include one or more feature characters, or each sub-slice may include one or more first areas and multiple second areas, or each sub-slice corresponds to part of the user information. For example, the feature character may be various characters such as numbers, letters or Chinese characters, and the first area corresponds to feature characters such as numbers, letters or Chinese characters, and each first area may correspond to one or more feature characters; the second area corresponds to the blank area between numbers, letters or Chinese characters, etc. For another example, if there is only one feature character identified, the first area may be the feature character, and the second area may be the blank area outside the feature character.

[0089] When segmenting the feature region, the feature region may be segmented into a plurality of sub-slices of the same size or a plurality of sub-slices of different sizes, and selective segmentation may be performed according to actual needs.

[0090] When segmenting the feature region, the feature region may be segmented according to a segmentation template with a preset segmentation size to obtain a plurality of sub-slices. The sizes of the sub-slices obtained by segmenting according to the segmentation template with a preset segmentation size may be the same or different.

[0091] When the feature area is segmented according to a segmentation template with a preset segmentation size, the feature area is identified by an optical character recognition method, and a first area corresponding to the feature character and a second area between the feature characters in the feature area are determined based on the segmentation template with the preset segmentation size. Further, a second segmentation boundary is determined in the feature area according to the segmentation template with the preset segmentation size, and it is determined whether the second segmentation boundary is in the second area. If so, the feature area is segmented according to the segmentation template to obtain one or more sub-slices with the preset segmentation size; if not, a second area with the smallest distance from the second segmentation boundary is determined, a third segmentation boundary is determined in the second area, and the feature area is segmented according to the third segmentation boundary to obtain one or more sub-slices. Among them, the size of the sub-slices obtained by segmentation according to the third segmentation boundary can be larger or smaller than the preset segmentation size.

[0092] For example, the first picture is a bill picture, the characteristic characters can be various characters such as numbers, letters or Chinese characters, and some user information can be certain numbers, letters or a combination of the account number; certain numbers, letters or a combination of the identity account number; certain numbers of a telephone number; certain words of a name, certain numbers, letters, words or various combinations of the address, etc.

[0093] By segmenting the feature area through a segmentation template, the user information contained in the feature area can be divided into multiple fragments (i.e., sub-slices), so that each sub-slice only contains local user information, and the subsequent processing flow cannot view the complete user information, thereby preventing the leakage of user information, protecting the user's personal privacy, and improving the security of user information, thereby improving the user experience and ensuring the security of the user's personal information.

[0094] Step S304, constructing a picture library of multiple second pictures that are unrelated to user information.

[0095] After the feature area is divided into multiple sub-slices, a picture library including multiple second pictures that are unrelated to the user information is constructed. The data type of the second picture can be the same as that of the first picture, and / or the picture size of the second picture can be the same as that of the first picture, so as to facilitate the picture processing of the subsequent process. For example, the second picture can be a picture with verification characters, as long as it is unrelated to the user information to be processed, and the verification character related information of the second picture is saved; or the second picture can be a landscape picture, a person picture, or an animal picture, etc., as long as it is unrelated to the user information to be processed.

[0096] Exemplarily, step S304 may be selectively set before step S301, step S302 or step S303 as required.

[0097] Step S305: splice the multiple sub-slices and the multiple second pictures, and send them to the recognition module.

[0098] According to the multiple sub-slices obtained in step S303 and the multiple second pictures unrelated to the user information selected from the picture library pre-built in step S304, the multiple sub-slices are respectively spliced ​​with the multiple second pictures to obtain multiple third pictures, and the multiple third pictures are sent to the recognition module so that the recognition module can recognize the information in the multiple third pictures; after obtaining the multiple third pictures, the multiple third pictures are saved for subsequent picture processing procedures. For example, the second picture can be a picture with a verification character, and when saving the multiple third pictures, the verification character related information of the corresponding second picture is saved.

[0099] Step S306, receiving the recognition result sent by the recognition module, and confirming the target recognition result.

[0100] Receive the recognition result sent by the recognition module, confirm the target recognition result, and use it for the subsequent process to confirm the user information corresponding to the client that sent the first picture. Each recognition result is the result obtained by recognizing the image information in each third picture. Therefore, each recognition result includes two parts: the image information corresponding to the sub-slice and the first verification information corresponding to the second picture; wherein, the recognition of the recognition module can be an automatic mode such as optical character recognition, or a manual mode such as manual entry, and the image information is structured text data. The recognition module can include one or more. When there is one recognition module, the recognition result of the recognition module is the target recognition result; when there are multiple recognition modules, multiple recognition modules will return multiple recognition results, compare the multiple recognition results, and determine that the recognition result with the highest frequency of occurrence among the multiple recognition results is the target recognition result.

[0101] When comparing multiple recognition results to determine the target recognition result, compare any two recognition results separately to determine whether the two recognition results are the same. If so, merge the two recognition results into one recognition result, and increase the frequency of occurrence of the recognition result, and continue to compare the remaining any two recognition results to obtain the target recognition result; or, when comparing multiple recognition results, sort the multiple recognition results according to the receiving time or other methods, and compare the latter result with the previous result in sequence to determine whether the two recognition results are the same. If so, merge the two recognition results into one recognition result, and increase the frequency of occurrence of the recognition result, and continue to compare the remaining one or more recognition results in sequence to obtain the target recognition result.

[0102] Step S307: judging whether the image information corresponding to the sub-slice is correct according to the target recognition result.

[0103] After confirming the target recognition result, each target recognition result includes image information corresponding to the sub-slice and first verification information corresponding to the second picture. Therefore, in order to ensure the accuracy of the user information, a match is performed based on the first verification information corresponding to the second picture to determine whether the image information corresponding to the sub-slice is correct.

[0104] According to the third picture saved in step S305, the third picture corresponding to the target recognition result is recognized, and the second verification information corresponding to the second picture in the third picture is obtained. The first verification information corresponding to the second picture in the target recognition result and the second verification information corresponding to the second picture obtained from the saved third picture are compared to determine whether the first verification information and the second verification information match. If so, it is determined that the image information corresponding to the sub-slice is correct, and go to step S308; if not, it is determined that the image information corresponding to the sub-slice is wrong, and an error prompt message is returned to the recognition module.

[0105] For example, the first verification information and the second verification information are character information, and the second picture can be a picture with verification characters. When obtaining the second verification information corresponding to the second picture in the third picture according to the third picture saved in step S305, the second verification information can be pre-saved information corresponding to the verification characters on the picture, or the second verification information can be information corresponding to the verification characters on the picture obtained based on optical character recognition or the like; when comparing the first verification information and the second verification information, the second verification information can be directly obtained based on the saved information of the verification characters corresponding to the third picture, or the second verification information can be obtained based on the information of the verification characters corresponding to the third picture obtained based on optical character recognition or the like. By matching the first verification information in the form of verification characters and the second verification information, it is determined whether the image information corresponding to the sub-slice is correct. When the recognition module is manually input, while ensuring the accuracy of the recognition result, it is possible to verify whether the input person is serious and accurate in input.

[0106] For another example, the first verification information and the second verification information are pixel point information, and the second picture can be a landscape picture, a person picture, or an animal picture. When obtaining the second verification information corresponding to the second picture in the third picture according to the third picture saved in step S305, the second verification information can be pixel information on the picture; when comparing the first verification information and the second verification information, the second verification information can be obtained according to each pixel point information. By verifying the match between the first verification information in the form of characters and the second verification information, it is determined whether the image information corresponding to the sub-slice is correct, and when the recognition module is manually entered, the accuracy of the recognition result can be ensured.

[0107] Step S308: determine the user information according to the correct image information corresponding to the sub-slice, and process the target service request corresponding to the client.

[0108] According to the correct image information corresponding to the multiple sub-slices, multiple target image information corresponding to the user information is determined, and the multiple target image information is spliced ​​to obtain the user information. The user information includes sensitive data corresponding to the user of the client. In response to the target service request corresponding to the user information of the client, the target service request is processed according to the sensitive data in the user information; for example, the user information may include "name - Zhang San", "ID number - 111111111111111111", "mobile phone number - 2222222222", "Zhang San", "1111111111111111111", "22222222222" are sensitive data. For example, the target service request may be payment, transfer, order, registration, modification of personal information, account opening, account transfer, account cancellation, acquisition of historical data, personal information verification, etc.

[0109] In an embodiment of the present invention, by receiving a first image sent by a client; determining a feature area in the first image corresponding to user information according to a capture template; dividing the feature area to obtain multiple sub-slices; constructing a picture library of multiple second images that are independent of user information; splicing the multiple sub-slices with the multiple second images, and sending them to a recognition module; receiving a recognition result sent by the recognition module, and confirming a target recognition result; judging whether the image information corresponding to the sub-slice is correct according to the target recognition result; determining user information according to the correct image information corresponding to the sub-slice, and processing the target service request corresponding to the client, etc., the picture information can be accurately and completely acquired, and the efficiency of picture transmission and picture information processing can be improved. Since the staff cannot obtain the complete picture, the security of the picture information can be guaranteed, the leakage of sensitive information can be prevented, and the credibility of the protection of personal privacy during picture information processing can be improved, thereby improving the user experience.

[0110] Figure 4 is a schematic diagram of the main modules of the image information processing device according to an embodiment of the present invention, such as Figure 4 As shown, the image information processing device 400 of the present invention includes:

[0111] The receiving module 401 is used to receive a first picture sent by a client; wherein the first picture indicates user information corresponding to the client.

[0112] In various types of applications such as shopping, entertainment, social networking, finance, communications, and government affairs, it is often necessary to input the user's personal information. In order to improve the user experience and facilitate the user's operation, various applications provide channels for uploading pictures, and the user's personal information can be obtained from the pictures uploaded by the client. When the method of the present invention processes the picture information, the receiving module 401 receives the first picture sent by the client, so that the subsequent modules can process the picture information in the first picture, and the first picture indicates the user information corresponding to the picture sent by the client. Exemplarily, the picture information included in the first picture can be various, including standard template information other than user information, irrelevant background information, etc.

[0113] The segmentation module 402 is configured to segment the first picture into a plurality of sub-slices.

[0114] After the receiving module 401 receives the first image indicating the user information corresponding to the client, the segmentation module 402 segments the first image into a plurality of sub-slices. When segmenting the first image, the segmentation module 402 determines the feature area corresponding to the user information in the first image by intercepting the template; the user information may include a plurality of feature characters, and the plurality of feature characters are identified by optical character recognition, thereby determining a plurality of first areas corresponding to the plurality of feature characters in the feature area, and a second area between each two feature characters. Based on the plurality of second areas, the segmentation module 402 determines the segmentation boundary according to the segmentation template, segments the feature area, and obtains a plurality of sub-slices. Each sub-slice corresponds to part of the user information.

[0115] The splicing module 403 is used to splice multiple second pictures that are unrelated to the user information with the multiple sub-slices respectively to obtain multiple third pictures, and send the multiple third pictures to the recognition module, so that the recognition module recognizes the user information according to the multiple third pictures.

[0116] After the segmentation module 402 segments the first image into a plurality of sub-slices, based on a pre-built image library including a plurality of second images that are not related to user information, the splicing module 403 selects a plurality of second images corresponding to the number of the plurality of sub-slices, and splices the plurality of second images with the plurality of sub-slices respectively, to obtain a plurality of third images. Exemplarily, the second image may be a verification code image, which is used for subsequent comparison to determine whether the image information corresponding to the sub-slices is correct. The plurality of third images are sent to the recognition module, which may include one or more recognition modules, so that the recognition module recognizes the user information based on the plurality of third images; when there are a plurality of recognition modules, the plurality of recognition results are compared to determine the target recognition result that appears most frequently among the plurality of recognition results, thereby determining the user information based on the target recognition result.

[0117] In an embodiment of the present invention, through modules such as a receiving module, a segmentation module and a splicing module, image information can be accurately and completely acquired, the efficiency of image transmission and image information processing can be improved, the security of image information can be ensured, the leakage of sensitive information can be prevented, and the user experience can be improved.

[0118] Figure 5 is a schematic diagram of the structure of a computer system of a terminal device suitable for implementing an embodiment of the present invention, such as Figure 5 As shown, the computer system 500 of the terminal device in the embodiment of the present invention includes:

[0119] A central processing unit (CPU) 501 can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage section 508 into a random access memory (RAM) 503. Various programs and data required for the operation of the system 500 are also stored in the RAM 503. The CPU 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0120] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 505 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed, so that a computer program read therefrom is installed into the storage section 508 as needed.

[0121] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 509, and / or installed from the removable medium 511. When the computer program is executed by the central processing unit (CPU) 501, the above-mentioned functions defined in the system of the present invention are executed.

[0122] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0123] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0124] The modules involved in the embodiments of the present invention may be implemented by software or hardware. The modules described may also be set in a processor. For example, they may be described as: a processor includes a receiving module, a segmentation module, and a splicing module. The names of these modules do not, in some cases, constitute limitations on the modules themselves. For example, the receiving module may also be described as a "module for receiving pictures sent by a client."

[0125] As another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device includes: receiving a first picture sent by a client; wherein the first picture indicates user information corresponding to the client; dividing the first picture into multiple sub-slices; splicing multiple second pictures that are not related to the user information with the multiple sub-slices respectively to obtain multiple third pictures, and sending the multiple third pictures to the recognition module, so that the recognition module recognizes the user information based on the multiple third pictures.

[0126] According to the technical solution of the embodiment of the present invention, it is possible to accurately and completely obtain image information, improve the efficiency of image transmission and image information processing, and because the staff cannot obtain the complete image, the security of the image information can be guaranteed, the leakage of sensitive information can be prevented, and the credibility of the protection of personal privacy during image information processing can be improved, thereby enhancing the user experience.

[0127] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for processing image information, characterized in that: include: Receiving a first picture sent by a client; wherein the first picture indicates user information corresponding to the client; The first image is divided into a plurality of sub-slices; wherein, a feature region corresponding to the user information in the first image is determined, and when the feature region is segmented according to a segmentation template with a preset segmentation size, a first region corresponding to a feature character in the feature region and a second region between the feature characters are determined based on the segmentation template with the preset segmentation size; a second segmentation boundary is determined in the feature region according to the segmentation template with the preset segmentation size, and it is determined whether the second segmentation boundary is in the second region, and if so, the feature region is segmented according to the segmentation template; if not, a second region with the smallest distance from the second segmentation boundary is determined, a third segmentation boundary is determined in the second region, and the feature region is segmented according to the third segmentation boundary; A plurality of second images that are not related to the user information are respectively spliced ​​with the plurality of sub-slices to obtain a plurality of third images, and the plurality of third images are sent to a recognition module, so that the recognition module recognizes the user information according to the plurality of third images.

2. The method according to claim 1, characterized in that Also includes: Receive the recognition result corresponding to each of the third pictures returned by the recognition module, and determine the user information according to the recognition result.

3. The method according to claim 2, characterized in that Each of the recognition results includes first verification information of the corresponding second picture and image information of the corresponding sub-slice; The determining the user information according to the recognition result includes: Identify second verification information from each of the third images; determining whether the first verification information and the second verification information match, and if so, determining that the image information corresponding to the first verification information is correct; The user information is determined based on each correct image information.

4. The method according to claim 3, characterized in that The determining the user information according to each correct image information includes: Determining target image information corresponding to the user information from the correct image information; The target image information is spliced ​​to obtain the user information.

5. The method according to claim 2, characterized in that: When there are multiple identification modules, determining the user information according to the identification result includes: According to the multiple recognition results respectively returned by the multiple recognition modules, a target recognition result with the highest frequency among the multiple recognition results is determined, and the user information is determined according to the target recognition result.

6. The method according to claim 5, characterized in that Determine whether every two recognition results are the same; if so, merge the two recognition results into one recognition result, and increase the occurrence frequency of the recognition result.

7. The method according to claim 2, characterized in that The determining the user information according to the recognition result includes: Based on the identification result, sensitive data in the user information is determined.

8. The method according to claim 7, characterized in that Also includes: In response to the target service request of the client, the target service request is processed according to the sensitive data.

9. The method according to claim 1, characterized in that: The dividing the first picture into a plurality of sub-slices includes: Determining a feature area corresponding to the user information in the first picture; The feature area is segmented to obtain the plurality of sub-slices, so that each of the sub-slices corresponds to part of the user information.

10. The method according to claim 9, characterized in that When the user information includes multiple characteristic characters, segmenting the characteristic area includes: Determine in the feature area a plurality of first areas corresponding to the plurality of feature characters respectively, and a second area between every two feature characters; determining a first segmentation boundary in the second region; The multiple first regions are divided according to the first segmentation boundary to obtain the multiple sub-slices, each sub-slice including one or more of the first regions.

11. The method according to claim 10, characterized in that The characteristic characters are determined by optical character recognition.

12. The method according to claim 1, characterized in that The data type of the second picture is the same as that of the first picture.

13. The method according to claim 1, characterized in that The second picture is selected from a pre-built picture library.

14. A picture information processing device, characterized in that: include: A receiving module, configured to receive a first picture sent by a client; wherein the first picture indicates user information corresponding to the client; A segmentation module, configured to segment the first image into a plurality of sub-slices; wherein, a feature region corresponding to the user information in the first image is determined, and when the feature region is segmented according to a segmentation template with a preset segmentation size, a first region corresponding to a feature character in the feature region and a second region between the feature characters are determined based on the segmentation template with the preset segmentation size; a second segmentation boundary is determined in the feature region according to the segmentation template with the preset segmentation size, and it is determined whether the second segmentation boundary is in the second region, and if so, the feature region is segmented according to the segmentation template; if not, a second region with the smallest distance from the second segmentation boundary is determined, a third segmentation boundary is determined in the second region, and the feature region is segmented according to the third segmentation boundary; A splicing module is used to splice multiple second pictures that are unrelated to the user information with the multiple sub-slices respectively to obtain multiple third pictures, and send the multiple third pictures to the recognition module, so that the recognition module recognizes the user information according to the multiple third pictures.

15. An electronic device for processing image information, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 13.

16. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 13 is implemented.

Images