WO2020248497A1

WO2020248497A1 - Picture scanning document processing method and apparatus, computer device, and storage medium

Info

Publication number: WO2020248497A1
Application number: PCT/CN2019/118237
Authority: WO
Inventors: 孙强; 陆凯杰
Original assignee: 平安科技（深圳）有限公司
Priority date: 2019-06-12
Filing date: 2019-11-14
Publication date: 2020-12-17
Also published as: CN110390260A; CN110390260B

Abstract

Embodiments of the present application provide a picture scanning document processing method and apparatus, a computer device, and a storage medium. The picture scanning document processing method comprises: pre-processing an initial picture scanning document according to a preset image pre-processing method so as to generate a first picture scanning document; segmenting the first picture scanning document according to a preset image segmentation method to form a plurality of areas to be identified; obtaining a feature parameter of each of said areas and setting a corresponding feature tag according to the feature parameter of each of said areas; obtaining an object identification model corresponding to the feature tag and identifying said areas according to the object identification model so as to obtain target objects; and obtaining a target combination template and generating a target document according to the target combination template and the plurality of target objects.

Description

Image scanning processing method, device, computer equipment and storage medium

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on June 12, 2019, the application number is 201910505226.X, and the application name is "Image Scanning Processing Method, Device, Computer Equipment and Storage Medium", all of which The content is incorporated in this application by reference.

Technical field

This application relates to the field of computer technology, and in particular to a method, device, computer equipment and storage medium for processing scanned images.

Background technique

In the prior art, a paper document containing text, symbols, and graphics is scanned to generate a scanned image of the image, which is used as an electronic archive of the paper document. Scanned documents are usually not convenient for users to edit and modify according to their needs. For example, the user cannot replace part of the text in the scanned document as a whole, or replace the graphics in the scanned document. This makes the scanned document only another non-editable form of the paper document under the computer system, which affects the user experience.

Summary of the invention

The embodiment of the present application proposes a method, device, computer equipment, and storage medium for processing scanned images, which aim to intelligently process scanned images to improve user experience.

In the first aspect, this application provides a method for processing scanned images, which includes:

Preprocess the initial picture scan according to a preset image preprocessing method to generate a first picture scan; divide the first picture scan according to a preset image segmentation method to form a plurality of regions to be recognized; obtain Each feature parameter of the region to be identified, and a corresponding feature label is set according to the feature parameter of each region to be identified; an object recognition model corresponding to the feature label is acquired, and the object recognition model The region to be identified is identified to obtain a target object; a target combination template is obtained, and a target file is generated according to the target combination template and the plurality of target objects.

In a second aspect, this application provides a device for processing scanned images, which includes:

The preprocessing unit is configured to preprocess the initial picture scan according to the preset image preprocessing method to generate a first picture scan; the segmentation unit is configured to perform the first picture scan according to the preset image segmentation method Segmentation to form a plurality of regions to be identified; an acquisition unit for acquiring the characteristic parameters of each region to be identified, and setting corresponding feature labels according to the characteristic parameters of each region to be identified; identification unit for Obtain an object recognition model corresponding to the feature tag, and recognize the area to be recognized according to the object recognition model to obtain a target object; a target file generating unit is used to obtain a target combination template, and according to the target combination A template and a plurality of the target objects generate a target file.

In a third aspect, an embodiment of the present application also provides a computer device, which includes a memory and a processor connected to the memory; the memory is used to store a computer program; the processor is used to run the A computer program to perform the following steps: preprocess the initial picture scan according to a preset image preprocessing method to generate a first picture scan; and divide the first picture scan according to the preset image segmentation method to Forming a plurality of regions to be identified; acquiring the characteristic parameters of each of the regions to be identified, and setting corresponding characteristic labels according to the characteristic parameters of each region to be identified; acquiring the object recognition model corresponding to the characteristic labels, The region to be recognized is recognized according to the object recognition model to obtain a target object; a target combination template is obtained, and a target file is generated according to the target combination template and the plurality of target objects.

In a fourth aspect, the embodiments of the present application also provide a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the following steps: Upon receiving the query instruction, it is determined whether the query range distance of the query instruction is greater than the preset threshold, wherein the query instruction includes the query location point and the query range distance; if the query range distance of the query instruction is not greater than the preset threshold, Then an expanded dictionary tree constructed in advance based on the Geohash algorithm is used to query the location points in the query domain and return the queried target location points; if the query range distance of the query instruction is greater than the preset threshold, the pre-order based on the Z curve is used The constructed R-tree queries the location points in the query domain and returns the queried target location points.

Description of the drawings

In order to explain the technical solutions of the embodiments of the present application more clearly, the following will briefly introduce the drawings needed in the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present application. Ordinary technicians can obtain other drawings based on these drawings without creative work.

FIG. 1 is a schematic flowchart of a method for processing a scanned image according to an embodiment of the application;

2 is a schematic diagram of a sub-flow of a method for processing a scanned image according to an embodiment of the application;

3 is a schematic diagram of a sub-flow of a method for processing a scanned image according to another embodiment of the application;

4 is a schematic diagram of a sub-flow of a method for processing a scanned image according to another embodiment of the application;

FIG. 5 is a schematic diagram of a sub-flow of a method for processing a scanned image according to another embodiment of this application;

FIG. 6 is a schematic diagram of a sub-flow of a method for processing a scanned image according to another embodiment of this application;

FIG. 7 is a schematic diagram of a sub-flow of a method for processing a scanned image according to another embodiment of this application;

FIG. 8 is a schematic diagram of a sub-flow of a method for processing a scanned image according to another embodiment of this application;

FIG. 9 is a schematic block diagram of a device for processing scanned images according to an embodiment of the application;

FIG. 10 is a schematic block diagram of a device for processing scanned images according to another embodiment of the application;

FIG. 11 is a schematic block diagram of a device for processing scanned images according to another embodiment of the application;

FIG. 12 is a schematic block diagram of a device for processing scanned images according to another embodiment of this application;

FIG. 13 is a schematic block diagram of a device for processing scanned images according to another embodiment of this application;

FIG. 14 is a schematic block diagram of a device for processing scanned images according to another embodiment of this application;

FIG. 15 is a schematic block diagram of a device for processing scanned images according to another embodiment of the application;

FIG. 16 is a schematic block diagram of a device for processing scanned images according to still another embodiment of the application;

FIG. 17 is a schematic block diagram of a computer device provided by an embodiment of the application.

Detailed ways

The technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of them. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

It should be understood that when used in this specification and the appended claims, the terms "including" and "including" indicate the existence of the described features, wholes, steps, operations, elements and/or components, but do not exclude one or The existence or addition of multiple other features, wholes, steps, operations, elements, components, and/or collections thereof.

It should also be understood that the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in the specification of this application and the appended claims, unless the context clearly indicates other circumstances, the singular forms "a", "an" and "the" are intended to include plural forms.

It should be further understood that the term "and/or" used in the specification and appended claims of this application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations .

Please refer to FIG. 1. FIG. 1 is a schematic flowchart of a method for processing a scanned image according to an embodiment of the present application. As shown in FIG. 1, an embodiment of the present application proposes a method for processing a scanned image, which includes steps S110 to S140.

S110. Preprocess the initial picture scan according to a preset image preprocessing method to generate a first picture scan.

In the embodiment of the present application, the initial image scan needs to be preprocessed by using a preset image preprocessing method to obtain the processed first image scan. Specifically, the scan of the initial picture is usually a color picture. In order to facilitate the identification of the scan of the picture, in this embodiment, the scan of the picture may be grayscaled first, so as to convert the scan of the color picture into an initial gray. Degree image. In the process of generating the original scanned image, the image scan may have a distortion area due to the distortion of the scanning lens, causing the text, symbols or graphics in the distortion area to be deformed, which affects the scanning of the image. Accuracy of recognition. Therefore, it is also necessary to perform distortion detection on the original image scan by using a preset image distortion detection algorithm to determine whether the original image scan has a distortion area. If the initial image scan has a distortion area, the initial image scan can be subjected to distortion correction processing according to a preset distortion correction algorithm, and the obtained corrected image scan is used as the first image scan.

Please refer to FIG. 2, which is a schematic diagram of a sub-flow of a method for processing a scanned image according to an embodiment of the present application. As shown in FIG. 2, in some embodiments, such as this embodiment, the step S110 includes substeps S1100 to S1102.

S1100: Perform grayscale processing on the scan of the initial picture to generate an initial grayscale image corresponding to the scan of the initial picture.

By performing grayscale processing on the scan of the initial picture, the color image can be converted into a grayscale image to facilitate the identification of the scan.

S1101, according to a preset image distortion detection method, determine whether the initial gray image has a distortion area.

In the formation of image scans, due to flaws in the lens’ process itself, the resulting image will have distortion problems, and the degree of distortion is related to the lens’ process. The degree of image distortion caused by lenses produced by different manufacturers is also Different. According to a preset image distortion detection algorithm, it can be determined whether the gray image has a distortion area, so that the gray image can be corrected by a distortion correction algorithm to improve the recognition accuracy of characters, symbols and graphics. Wherein, the preset image distortion detection algorithm may be: acquiring a plurality of sampling points of the initial gray image; calculating the correction value of each sampling point according to a preset distortion detection calculation formula; judging each sampling point Whether the difference between the point and the corresponding correction value is within a preset threshold range, if it is within the preset threshold range, it is confirmed that the grayscale image has a distortion area.

S1102, if the initial grayscale image has a distortion area, perform distortion correction on the initial grayscale image according to a preset distortion correction algorithm to generate the first picture scan.

In the embodiment of the present application, if the judgment result is that the initial gray image has a distortion area, the initial gray image is subjected to distortion correction according to a preset distortion correction algorithm to generate the first image scan. Wherein, the preset distortion correction algorithm is: obtaining the coordinate value of each pixel point of the initial gray image, and calculating the target coordinate value of each pixel point coordinate value according to a preset distortion correction formula. For example, for radial distortion, the preset distortion correction formula is:

u'=u(1+k ₁ r ² + k ₂ r ⁴ + k ₃ r ⁶ ) (1)

v'=v(1+k ₁ r ² + k ₂ r ⁴ + k ₃ r ⁶ ) (2)

Among them, (u, v) is the target coordinate value, and (u', v') is the pixel coordinate value, k ₁ , k ₂ , and k ₃ are distortion coefficients, and r ² =u ² +v ² .

S120. Segment the scan of the first picture according to a preset image segmentation method to form multiple regions to be identified.

In the embodiment of the present application, the scan of the first picture may have multiple text areas, symbol areas, and graphic areas. In order to facilitate the identification of the contents of different areas, in this embodiment, the first picture is scanned The files are processed according to the preset image segmentation method to generate multiple regions to be recognized. Wherein, the object feature vector of the scan of the first picture can be obtained according to the preset feature vector calculation method, and the feature vector of the scan of the first picture can be determined from the preset feature vector group by way of feature vector comparison. The difference of the object feature vector is less than the first preset feature vector of the first preset threshold, and then the image segmentation template associated with the first preset feature vector is obtained, and then the first preset feature vector is analyzed according to the image segmentation template. The scanned image is segmented to generate a plurality of regions to be identified. Obtain the sub-object feature vector of each region to be identified according to the preset feature vector calculation method. If there is a second preset feature vector in the preset feature vector group whose difference with the feature vector of the sub-object is less than a second preset threshold, acquiring feature parameters associated with the second preset feature vector. Using the characteristic parameter as a characteristic label, each region to be identified is associated with the characteristic label.

Please refer to FIG. 3, which is a schematic diagram of a sub-flow of a method for processing scanned images according to another embodiment of the present application. As shown in FIG. 3, in some embodiments, such as this embodiment, the step S120 includes sub-steps S1200 to S1202.

S1200. Obtain an object feature vector of the scan of the first picture according to a preset feature vector calculation method.

In this embodiment of the present application, the feature vector comparison method is used to determine the segmentation template used to segment the scan of the first picture. Therefore, the first image scan is calculated according to the preset feature vector calculation method to generate the object feature vector of the first image scan. Wherein, the preset feature vector calculation method may be a principal component analysis algorithm, which calculates the object feature vector of the first image scan through the principal component analysis algorithm. Wherein, the preset feature vector group can be stored in advance, and each preset feature vector in the preset feature vector group and the corresponding image segmentation template can be associated, so as to obtain the data from the preset feature vector group. For a first preset feature vector whose difference value of the object feature vector is within a preset threshold value range, the first image scan is segmented by using an image segmentation template associated with the first preset feature vector.

S1201. If there is a first preset feature vector in the preset feature vector group whose difference with the object feature vector is less than a first preset threshold, obtain an image segmentation template associated with the first preset feature vector.

The corresponding image segmentation template is determined by calculating the difference between the feature vector in the preset feature vector group and the feature vector of the object, and comparing it with the first preset threshold. Wherein, in this embodiment, if there is a first preset feature vector in the preset feature vector group whose difference with the object feature vector is less than the first preset threshold, obtain the first preset feature vector related to the first preset The image segmentation template of the joint.

S1202. Segment the scan of the first picture according to the image segmentation template to generate a plurality of regions to be identified.

In this embodiment of the present application, the first image scan is segmented according to the image segmentation template to generate multiple regions to be recognized, so that different regions to be recognized can be subsequently recognized, and corresponding Recognition results.

S130. Obtain the characteristic parameter of each of the regions to be identified, and set a corresponding characteristic label according to the characteristic parameter of each region to be identified.

In the embodiment of the present application, there may be multiple text areas, symbol areas, and graphic areas in the generated multiple to-be-recognized areas. In order to facilitate the recognition of the content of different areas, in this embodiment, it is also necessary to use the preset The feature vector calculation method obtains the sub-object feature vector of each of the regions to be identified. If there is a second preset feature vector in the preset feature vector group whose difference with the feature vector of the sub-object is less than a second preset threshold, the feature parameter associated with the second preset feature vector is acquired. Using the characteristic parameter as a characteristic label, each region to be identified is associated with the characteristic label.

Please refer to FIG. 4, which is a schematic diagram of a sub-flow of a method for processing a scanned image according to another embodiment of the present application. As shown in FIG. 4, in some embodiments, such as this embodiment, the step S130 includes sub-steps S1300 to S1302.

S1300. Obtain a sub-object feature vector of each region to be identified according to the preset feature vector calculation method.

In the embodiment of the present application, the feature vector of each region to be identified is obtained as a sub-object feature vector by using the preset feature vector calculation method, so as to determine the feature parameter corresponding to each region to be identified , And then determine the recognition model used for recognizing the region to be recognized according to the characteristic parameter.

S1301. If there is a second preset feature vector in the preset feature vector group whose difference with the feature vector of the sub-object is less than a second preset threshold, obtain a feature parameter associated with the second preset feature vector.

In the embodiment of the present application, if there is a second preset feature vector in the preset feature vector group whose difference with the feature vector of the sub-object is less than the second preset threshold, obtain the second preset feature vector related to the second preset feature vector The characteristic parameters of the joint. Wherein, the characteristic parameter may be a keyword. For example, if the scan of the first picture can be divided into three areas to be recognized, which are text to be recognized, graphics to be recognized, and symbols to be recognized. In the recognition area, the sub-object feature vector obtained by calculation and the second preset feature vector in the preset feature vector group, the difference between which is less than the second preset threshold, and the feature associated with the second preset feature vector The parameter is the keyword "text"; in the same way, for the area to be recognized by the figure, the corresponding keyword obtained is "graphic", and for the area to be recognized by the symbol, the corresponding keyword obtained is " symbol".

S1302, using the characteristic parameter as a characteristic label, and associating each of the regions to be identified with the characteristic label. In the embodiment of the present application, the characteristic parameter is used as a characteristic label, and each region to be identified is associated with the characteristic label, so that the region to be identified can be identified through the characteristic label.

S140. Obtain an object recognition model corresponding to the feature tag, and recognize the area to be recognized according to the object recognition model to obtain a target object. In the embodiment of the present application, the objects contained in the initial image scan may include text, symbols, and graphics. For different objects, different recognition models are used for recognition. Wherein, if the feature tag is a text tag, a text recognition model is obtained; the region to be recognized is recognized according to the text recognition model to obtain a text recognition result. If the feature tag is a symbol tag, a symbol recognition model is obtained; the region to be recognized is recognized according to the symbol recognition model to obtain a symbol recognition result. If the feature tag is a graphic tag, a graphic recognition model is obtained; the area to be recognized is recognized according to the graphic recognition model to obtain a graphic recognition result.

Please refer to FIG. 5. FIG. 5 is a schematic diagram of a sub-flow of a method for processing a scanned image according to another embodiment of the present application. As shown in FIG. 5, in some embodiments, such as this embodiment, the step S140 includes sub-steps S1400 and S1401.

S1400: If the feature label is a text label, obtain a text recognition model. In the embodiment of the present application, if the feature label is a text label, that is, the content of the region to be recognized is text, then a text recognition model is obtained.

S1401. Recognize the region to be recognized according to the text recognition model to obtain a text recognition result. In this embodiment, the text recognition result is obtained by recognizing the region to be recognized according to the text recognition model.

In another embodiment, please refer to FIG. 6, which is a schematic diagram of a sub-flow of a method for processing a scanned image according to another embodiment of the present application. As shown in FIG. 6, in some embodiments, such as this embodiment, the step S140 includes sub-steps S1402 and S1403.

S1402, if the feature tag is a symbol tag, obtain a symbol recognition model. In the embodiment of the present application, if the feature label is a symbol label, that is, the content of the area to be identified is a symbol, then a symbol recognition model is obtained.

S1403. Recognize the region to be recognized according to the symbol recognition model to obtain a symbol recognition result. In this embodiment, the symbol recognition result is obtained by recognizing the region to be recognized according to the symbol recognition model.

Please refer to FIG. 7, which is a schematic diagram of a sub-flow of a method for processing a scanned image according to another embodiment of the present application. As shown in FIG. 7, in some embodiments, such as this embodiment, the step S140 includes sub-steps S1404 and S1405.

S1404: If the feature tag is an image tag, obtain a graphic recognition model. In the embodiment of the present application, if the feature label is a graphic label, that is, the content of the area to be recognized is a graphic, a graphic recognition model is obtained.

S1405. Recognize the region to be recognized according to the graphic recognition model to obtain a graphic recognition result. In this embodiment, the pattern recognition result is obtained by recognizing the region to be recognized according to the pattern recognition model.

S150. Obtain a target combination template, and generate a target file according to the target combination template and the multiple target objects. In the embodiment of the present application, a user interface may be generated, and multiple preset combination templates may be displayed on the user interface to obtain the target combination template generated by the user selecting the multiple preset combination templates, and then The target file is generated according to the target combination template and the plurality of target objects.

Please refer to FIG. 8. FIG. 8 is a schematic diagram of a sub-flow of a method for processing a scanned image according to still another embodiment of the present application. As shown in FIG. 8, in some embodiments, such as this embodiment, the step S140 includes sub-steps S1500 to S1502.

S1500. Generate a user interface, and display multiple preset combination templates on the user interface. In this embodiment, the system stores multiple preset combination templates. By generating a user interface and displaying the multiple preset combination templates on the user interface, it is convenient for the user to select.

S1501. Obtain a target combination template generated by a user selecting a plurality of the preset combination templates. By acquiring a target combination template generated by a user selecting a plurality of the preset combination templates, it is convenient to subsequently combine multiple target objects through the target combination template to generate a target file.

S1502. Generate the target file according to the target combination template and the multiple target objects.

The target file is generated by combining the target template and the plurality of target objects. For example, if the number of regions to be recognized in the initial image scan is 5, there are 3 text areas, 1 symbol area, and 1 graphic area, and there are 5 areas in the initial image scan It is a top-down layout. By obtaining a target combination template, for example, the target combination template is a pattern of three left and two right, by displaying the corresponding text content in the three left columns of the target combination template, displaying the symbol content in the upper column on the right, and The lower column displays the graphic content, which can present a more beautiful layout than the scanned one. In addition, the content of each column under the target combination template can be edited and modified, for example, the text column can be added, modified or deleted.

Refer to FIG. 9, which is a schematic block diagram of an image scan processing apparatus 200 provided in an embodiment of the application. As shown in FIG. 9, the image scan processing device 200 proposed in the embodiment of the present application includes: a preprocessing unit 210, a segmentation unit 220, an acquisition unit 230, an identification unit 240, and a target file generation unit 250.

The preprocessing unit 210 is configured to preprocess the initial picture scan according to a preset image preprocessing method to generate a first picture scan;

The segmentation unit 220 is configured to segment the first image scan according to a preset image segmentation method to form a plurality of regions to be identified, and set a feature label for each region to be identified;

The acquiring unit 230 is configured to acquire the characteristic parameters of each of the regions to be identified, and set a corresponding characteristic label according to the characteristic parameters of each of the regions to be identified;

The recognition unit 240 is configured to obtain an object recognition model corresponding to the feature tag, and recognize the area to be recognized according to the object recognition model to obtain a target object;

The target file generating unit 250 is configured to obtain a target combination template, and generate a target file according to the target combination template and multiple target objects.

Refer to FIG. 10, which is a schematic block diagram of an image scan processing apparatus 200 provided by another embodiment of the application. As shown in FIG. 10, the image scan processing device 200 proposed in this embodiment of the application includes: a preprocessing unit 210, a segmentation unit 220, an acquisition unit 230, an identification unit 240, and a target file generation unit 250, wherein the preprocessing The unit 210 includes a grayscale processing unit 2100, a judgment unit 2101, and a distortion correction unit 2102.

The gray-scale processing unit 2100 is configured to perform gray-scale processing on the scan of the initial picture to generate an initial gray image corresponding to the scan of the initial picture.

The determining unit 2101 is configured to determine whether the initial grayscale image has a distortion area according to a preset image distortion detection method.

The distortion correction unit 2102 is configured to perform distortion correction on the initial grayscale image according to a preset distortion correction algorithm to generate the first image scan if it is determined that the initial grayscale image has a distortion area.

Refer to FIG. 11, which is a schematic block diagram of an image scan processing apparatus 200 provided by another embodiment of the application. As shown in FIG. 11, the image scan processing device 200 proposed in this embodiment of the application includes: a preprocessing unit 210, a segmentation unit 220, an acquisition unit 230, an identification unit 240, and a target file generation unit 250, wherein the segmentation unit 220 includes: an object feature vector obtaining unit 2200, an image segmentation template obtaining unit 2201, and a region to be recognized generating unit 2202.

The object feature vector obtaining unit 2200 is configured to obtain the object feature vector of the first image scan according to a preset feature vector calculation method.

The image segmentation template obtaining unit 2201 is configured to, if there is a first preset feature vector in the preset feature vector group whose difference with the object feature vector is less than the first preset threshold, obtain the first preset feature vector and the first preset feature vector The associated image segmentation template.

The to-be-recognized region generating unit 2202 is configured to segment the first image scan according to the image segmentation template to generate a plurality of the to-be-recognized regions.

Refer to FIG. 12, which is a schematic block diagram of an image scan processing apparatus 200 provided by another embodiment of the application. As shown in FIG. 12, the image scan processing device 200 proposed in this embodiment of the application includes: a preprocessing unit 210, a segmentation unit 220, an acquisition unit 230, an identification unit 240, and a target file generation unit 250, wherein the acquisition unit 230 includes: a sub-object feature vector obtaining unit 2300, a feature parameter obtaining unit 2301, and an associating unit 2302.

The sub-object feature vector obtaining unit 2300 is configured to obtain the sub-object feature vector of each region to be identified according to the preset feature vector calculation method.

The feature parameter acquiring unit 2301 is configured to, if there is a second preset feature vector in the preset feature vector group whose difference with the feature vector of the sub-object is less than a second preset threshold, to obtain the second preset feature vector The associated characteristic parameter.

The associating unit 2302 is configured to use the characteristic parameter as a characteristic label, and associate each of the regions to be identified with the characteristic label.

Refer to FIG. 13, which is a schematic block diagram of an apparatus 200 for processing scanned images according to another embodiment of the application. As shown in FIG. 13, the image scan processing apparatus 200 proposed in the embodiment of the present application includes: a preprocessing unit 210, a segmentation unit 220, an acquisition unit 230, an identification unit 240, and a target file generation unit 250, wherein the identification unit 240 includes a character recognition model obtaining unit 2400 and a character recognition result obtaining unit 2401.

The character recognition model obtaining unit 2400 is configured to obtain a character recognition model if the feature label is a character label.

The character recognition result obtaining unit 2401 is configured to recognize the region to be recognized according to the character recognition model to obtain a character recognition result.

Refer to FIG. 14, which is a schematic block diagram of a scanning image processing apparatus 200 provided by another embodiment of the application. As shown in FIG. 14, the image scan processing device 200 proposed in the embodiment of the present application includes: a preprocessing unit 210, a segmentation unit 220, an acquisition unit 230, an identification unit 240, and a target file generation unit 250, wherein the identification unit 240 includes a symbol recognition model acquisition unit 2402 and a symbol recognition result acquisition unit 2403.

The symbol recognition model acquisition unit 2402 is configured to acquire a symbol recognition model if the feature tag is a symbol tag.

The symbol recognition result obtaining unit 2403 is configured to recognize the region to be recognized according to the symbol recognition model to obtain a symbol recognition result.

Refer to FIG. 15, which is a schematic block diagram of an image scan processing apparatus 200 provided by another embodiment of the application. As shown in FIG. 15, the image scan processing device 200 proposed in the embodiment of the present application includes: a preprocessing unit 210, a segmentation unit 220, an acquisition unit 230, an identification unit 240, and a target file generation unit 250, wherein the identification unit 240 includes a graphic recognition model obtaining unit 2404 and a graphic recognition result obtaining unit 2405.

The graphic recognition model obtaining unit 2404 is configured to obtain a graphic recognition model if the feature tag is an image tag.

The graphic recognition result obtaining unit 2405 is configured to recognize the region to be recognized according to the graphic recognition model to obtain a graphic recognition result.

Refer to FIG. 16, which is a schematic block diagram of an image scan processing apparatus 200 provided by still another embodiment of the application. As shown in FIG. 16, the image scan processing apparatus 200 proposed in this embodiment of the application includes: a preprocessing unit 210, a segmentation unit 220, an acquisition unit 230, an identification unit 240, and a target file generation unit 250, wherein the target file The generation unit 250 includes a user interface generation unit 2500, a target combination template acquisition unit 2501, and a combination unit 2502.

The user interface generating unit 2500 is configured to generate a user interface and display a plurality of preset combination templates on the user interface.

The target combination template obtaining unit 2501 is configured to obtain a target combination template generated by a user selecting a plurality of the preset combination templates.

The combining unit 2502 is configured to generate the target file according to the target combination template and multiple target objects.

The above-mentioned image scan processing device can be implemented in the form of a computer program, and the computer program can be run on a computer device as shown in FIG. 17.

Please refer to FIG. 17, which is a schematic block diagram of a computer device according to an embodiment of the present application. The computer device 300 device may be a terminal. Referring to FIG. 17, the computer device 300 includes a processor 302, a memory, and a network interface 305 connected through a system bus 301, where the memory may include a non-volatile storage medium 303 and an internal memory 304. The non-volatile storage medium 303 can store an operating system 3031 and a computer program 3032. The computer program 3032 includes program instructions. When the program instructions are executed, the processor 302 can execute a method for processing scanned images. The processor 302 is used to provide computing and control capabilities and support the operation of the entire computer device 300. The internal memory 304 provides an environment for the running of the computer program 3032 in the non-volatile storage medium 303. When the computer program 3032 is executed by the processor 302, the processor 302 can execute a method for processing scanned images. The network interface 305 is used for network communication, such as sending assigned tasks. Those skilled in the art can understand that the structure shown in FIG. 17 is only a block diagram of part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device 300 to which the solution of the present application is applied. The specific computer device 300 may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

Wherein, the processor 302 is configured to run a computer program 3032 stored in a memory, so as to implement the image scan processing method in the embodiment of the present application.

It should be understood that in the embodiment of the present application, the processor 302 may be a central processing unit (Central Processing Unit, CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor.

In another embodiment of the present application, a storage medium is provided. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the scanning image processing method described in the above embodiments.

The storage medium may be a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a magnetic disk, or an optical disk, and other media that can store program codes.

The above are only specific implementations of this application, but the protection scope of this application is not limited to this. Anyone familiar with the technical field can easily think of various equivalents within the technical scope disclosed in this application. Modifications or replacements, these modifications or replacements shall be covered within the protection scope of this application. Therefore, the protection scope of this application shall be subject to the protection scope of the claims.

Claims

A method for processing scanned images, including:

Preprocess the initial scan of the image according to the preset image preprocessing method to generate the first scan of the image;

Segment the scan of the first picture according to a preset image segmentation method to form a plurality of regions to be identified;

Acquiring the characteristic parameter of each region to be identified, and setting a corresponding characteristic label according to the characteristic parameter of each region to be identified;

Obtaining an object recognition model corresponding to the feature tag, and recognizing the area to be recognized according to the object recognition model to obtain a target object;

A target combination template is acquired, and a target file is generated according to the target combination template and the plurality of target objects.
The method of processing a scanned image of claim 1, wherein the preprocessing of the scanned image of the initial image according to a preset image processing method to generate the scanned image of the first image comprises:

Performing grayscale processing on the scan of the initial picture to generate an initial grayscale image corresponding to the scan of the initial picture;

According to a preset image distortion detection method, determine whether the initial gray image has a distortion area;

If it is determined that the initial gray-scale image has a distortion area, perform distortion correction on the initial gray-scale image according to a preset distortion correction algorithm to generate the first picture scan.
The method for processing a scanned image of a picture according to claim 1, wherein said segmenting the scanned first image according to a preset image segmentation method to form a plurality of regions to be identified comprises:

Acquiring the object feature vector of the first image scan according to a preset feature vector calculation method;

If there is a first preset feature vector in the preset feature vector group whose difference with the object feature vector is less than a first preset threshold, acquiring an image segmentation template associated with the first preset feature vector;

The first image scan is segmented according to the image segmentation template to generate a plurality of regions to be identified.
4. The image scan processing method according to claim 1, wherein said acquiring the characteristic parameters of each of the regions to be identified, and setting corresponding characteristic labels according to the characteristic parameters of each of the regions to be identified comprises:

Acquiring the sub-object feature vector of each region to be identified according to the preset feature vector calculation method;

If there is a second preset feature vector in the preset feature vector group whose difference with the feature vector of the sub-object is less than a second preset threshold, acquiring feature parameters associated with the second preset feature vector;

Using the characteristic parameter as a characteristic label, each region to be identified is associated with the characteristic label.
4. The image scan processing method according to claim 1, wherein said obtaining an object recognition model corresponding to said feature tag, and recognizing said area to be recognized according to said object recognition model to obtain a target object, include:

If the feature tag is a text tag, obtain a text recognition model;

The region to be recognized is recognized according to the text recognition model to obtain a text recognition result.
4. The image scan processing method according to claim 1, wherein said obtaining an object recognition model corresponding to said feature tag, and recognizing said area to be recognized according to said object recognition model to obtain a target object, include:

If the feature tag is an image tag, obtain a graphic recognition model;

The region to be recognized is recognized according to the graphic recognition model to obtain a graphic recognition result.
The method for processing scanned images according to claim 1, wherein said acquiring a target combination template and generating a target file based on said target combination template and a plurality of said target objects comprises:

Generating a user interface, and displaying multiple preset combination templates on the user interface;

Acquiring a target combination template generated by a user selecting a plurality of the preset combination templates;

The target file is generated according to the target combination template and the plurality of target objects.
A device for processing scanned images, including:

The preprocessing unit is configured to preprocess the initial picture scan according to the preset image preprocessing method to generate the first picture scan;

A segmentation unit, configured to segment the scan of the first picture according to a preset image segmentation method to form multiple regions to be identified;

The acquiring unit is used to acquire the characteristic parameters of each of the regions to be identified, and set corresponding characteristic labels according to the characteristic parameters of each of the regions to be identified

A recognition unit, configured to obtain an object recognition model corresponding to the feature tag, and recognize the area to be recognized according to the object recognition model to obtain a target object;

The target file generating unit is configured to obtain a target combination template, and generate a target file according to the target combination template and multiple target objects.
8. The image scan processing device according to claim 8, wherein the preprocessing unit comprises:

A grayscale processing unit, configured to perform grayscale processing on the scan of the initial picture to generate an initial grayscale image corresponding to the scan of the initial picture;

A judging unit, configured to judge whether the initial gray image has a distortion area according to a preset image distortion detection method;

The distortion correction unit is configured to perform distortion correction on the initial grayscale image according to a preset distortion correction algorithm to generate the first image scan if it is determined that the initial grayscale image has a distortion area.
8. The image scan processing device according to claim 8, wherein the dividing unit comprises:

The object feature vector obtaining unit is configured to obtain the object feature vector of the scan of the first picture according to a preset feature vector calculation method;

The image segmentation template acquisition unit is configured to, if there is a first preset feature vector in the preset feature vector group whose difference with the feature vector of the object is less than a first preset threshold, to obtain the first preset feature vector related Joint image segmentation template;

The to-be-recognized region generating unit is configured to segment the scan of the first picture according to the image segmentation template to generate a plurality of the to-be-recognized regions.
A computer device includes a memory and a processor connected to the memory; the memory is used to store a computer program; the processor is used to run the computer program stored in the memory to perform the following steps:

Preprocess the initial scan of the image according to the preset image preprocessing method to generate the first scan of the image;

Segment the scan of the first picture according to a preset image segmentation method to form a plurality of regions to be identified;

Acquiring the characteristic parameter of each region to be identified, and setting a corresponding characteristic label according to the characteristic parameter of each region to be identified;

Obtaining an object recognition model corresponding to the feature tag, and recognizing the area to be recognized according to the object recognition model to obtain a target object;

A target combination template is obtained, and a target file is generated according to the target combination template and the plurality of target objects.
11. The computer device according to claim 11, wherein said preprocessing the initial picture scan according to a preset image processing method to generate the first picture scan comprises:

Performing grayscale processing on the scan of the initial picture to generate an initial grayscale image corresponding to the scan of the initial picture;

According to a preset image distortion detection method, determine whether the initial gray image has a distortion area;

If it is determined that the initial gray-scale image has a distortion area, perform distortion correction on the initial gray-scale image according to a preset distortion correction algorithm to generate the first picture scan.
11. The computer device according to claim 11, wherein the segmenting the scan of the first picture according to a preset image segmentation method to form a plurality of regions to be identified comprises:

Acquiring the object feature vector of the first image scan according to a preset feature vector calculation method;

If there is a first preset feature vector in the preset feature vector group whose difference with the object feature vector is less than a first preset threshold, acquiring an image segmentation template associated with the first preset feature vector;

The first image scan is segmented according to the image segmentation template to generate a plurality of regions to be identified.
11. The computer device according to claim 11, wherein said acquiring the characteristic parameters of each of the regions to be identified, and setting corresponding characteristic labels according to the characteristic parameters of each of the regions to be identified comprises:

Acquiring the sub-object feature vector of each region to be identified according to the preset feature vector calculation method;

If there is a second preset feature vector in the preset feature vector group whose difference with the feature vector of the sub-object is less than a second preset threshold, acquiring feature parameters associated with the second preset feature vector;

Using the characteristic parameter as a characteristic label, each region to be identified is associated with the characteristic label.
11. The computer device according to claim 11, wherein said obtaining an object recognition model corresponding to said feature tag, and recognizing said region to be recognized according to said object recognition model to obtain a target object comprises:

If the feature tag is a text tag, obtain a text recognition model;

The region to be recognized is recognized according to the text recognition model to obtain a text recognition result.
11. The computer device according to claim 11, wherein said obtaining an object recognition model corresponding to said feature tag, and recognizing said region to be recognized according to said object recognition model to obtain a target object comprises:

If the feature tag is an image tag, obtain a graphic recognition model;

The region to be recognized is recognized according to the graphic recognition model to obtain a graphic recognition result.
11. The computer device according to claim 11, wherein said acquiring a target combination template and generating a target file according to said target combination template and a plurality of said target objects comprises:

Generating a user interface, and displaying multiple preset combination templates on the user interface;

Acquiring a target combination template generated by a user selecting a plurality of the preset combination templates;

The target file is generated according to the target combination template and the plurality of target objects.
A computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the processor executes the following steps:

Preprocess the initial scan of the image according to the preset image preprocessing method to generate the first scan of the image;

Segment the scan of the first picture according to a preset image segmentation method to form a plurality of regions to be identified;

Acquiring the characteristic parameter of each region to be identified, and setting a corresponding characteristic label according to the characteristic parameter of each region to be identified;

Obtaining an object recognition model corresponding to the feature tag, and recognizing the area to be recognized according to the object recognition model to obtain a target object;

A target combination template is acquired, and a target file is generated according to the target combination template and the plurality of target objects.
18. The computer-readable storage medium according to claim 18, wherein the step of preprocessing the initial picture scan according to a preset image processing method to generate the first picture scan comprises:

Performing grayscale processing on the scan of the initial picture to generate an initial grayscale image corresponding to the scan of the initial picture;

According to a preset image distortion detection method, determine whether the initial gray image has a distortion area;

If it is determined that the initial gray-scale image has a distortion area, perform distortion correction on the initial gray-scale image according to a preset distortion correction algorithm to generate the first picture scan.
18. The computer-readable storage medium of claim 18, wherein the step of segmenting the scan of the first picture according to a preset image segmentation method to form a plurality of regions to be identified comprises:

Acquiring the object feature vector of the first image scan according to a preset feature vector calculation method;

If there is a first preset feature vector in the preset feature vector group whose difference with the object feature vector is less than a first preset threshold, acquiring an image segmentation template associated with the first preset feature vector;

The first image scan is segmented according to the image segmentation template to generate a plurality of regions to be identified.