Low-code form generation method and device based on image recognition

The form image is preprocessed and optical character recognition through image recognition technology, and automatically extracts and converts it into low-code form configuration information, solving the problem of low-code development platform inefficient when creating complex or large quantities of forms, and achieving efficient and flexible Form generation reduces development costs.

CN119065656AInactive Publication Date: 2024-12-03INSPUR SOFTWARE TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202411554558.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-04
Publication Date
2024-12-03
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Existing low-code development platforms are inefficient when creating complex forms or large numbers of forms, and image recognition technology has limited applications in this field.

Method used

Image recognition technology is used to preprocess and optical character recognition for form images, extract table style description information, and automatically convert it into low-code form configuration information, and display and adjust it through a visual designer.

Benefits of technology

It improves form creation efficiency, reduces development costs, and has the advantages of high flexibility and wide application scope.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119065656A_ABST
    Figure CN119065656A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of graphic image processing, in particular to a low-code form generation method and device based on image recognition. According to the low-code form generation method based on image recognition, after a form image is recognized and preprocessed by using an image recognition technology, text information in a form is recognized by using an optical character recognition (OCR) technology, and form style description information is extracted; automatically converting the extracted structured form text information and form style description information into low-code form configuration information, and establishing a corresponding relationship between the form text information and low-code form elements; and rendering and displaying the converted low-code form configuration information in a visual form designer for further development and adjustment by a user. According to the low-code form generation method and device based on image recognition, the low-code form configuration information can be automatically generated, so that the form creation efficiency is improved, the development cost is reduced, and the method and device have the advantages of being high in flexibility, wide in application range and the like.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of graphic and image processing technology, and in particular to a low-code form generation method and device based on image recognition. Background Art

[0002] With the rapid development of information technology, low-code development platforms are increasingly favored by enterprises and developers. Low-code development platforms can quickly build applications in a visual way, greatly improving development efficiency. However, in existing technologies, the creation of forms usually requires manual input or selection from templates, which is still inefficient for some complex forms or when a large number of forms need to be created quickly.

[0003] At the same time, image recognition technology has made significant progress in recent years, but its application in low-code development platforms is still relatively limited. In order to meet the needs of rapid development, the present invention proposes a low-code form generation method and device based on image recognition. Summary of the invention

[0004] In order to remedy the deficiencies of the prior art, the present invention provides a simple and efficient low-code form generation method and device based on image recognition.

[0005] The present invention is achieved through the following technical solutions: A low-code form generation method based on image recognition includes the following steps: Step S1, using image recognition technology to identify the form image, the form image includes a screenshot and a photographed picture; performing image preprocessing operations on the form image, including geometric correction, enhancement, denoising and binarization; Step S2, using optical character recognition (OCR) technology to identify text information in the form, and extracting table style description information through an image analysis algorithm, wherein the table style description information includes width, height, border style, background color and text style; Step S3: automatically convert the extracted structured form text information and table style description information into low-code form configuration information, establish a corresponding relationship between the form text information and the low-code form elements, and generate the style configuration parameters of the low-code form according to the table style description information; Step S4: Render and display the converted low-code form configuration information in the visual form designer for users to further develop and adjust.

[0006] In step S1, the specific implementation steps are: S101. Given an affine transformation matrix , where the linear transformation matrix , the translation matrix , read the form image to get the image representation matrix X, , where (x1, y1), (x2, y2) represent the image coordinates, and the form image is transformed to Y=R T X+t, get the geometric correction image matrix Y; S102, select the sharpening intensity coefficient , perform sharpening and enhancement processing on the geometric correction image matrix Y to obtain the sharpening and enhanced image Z: ; S103, reading the pixel value I(x, y) of any pixel point (x, y) in the sharpening enhanced image Z, selecting an area with m*n pixels in the surrounding neighborhood, performing filtering and noise reduction processing, and obtaining a noise reduction processed image F; The denoising process at least includes mean denoising. The pixel value F(x, y) of the denoised image F at the pixel point (x, y) obtained by the mean denoising process is: ; S104, further performing binarization processing on the denoised image F, converting the denoised image F from a grayscale image into a binary image B; The global threshold s is calculated using the big law: ; Wherein, N is the total number of pixels of the denoised image F, w is the grayscale value, ranging from 0 to 255; q(w) is the number of pixels in the image with a grayscale value less than w; g(w) is the number of pixels in the image with a grayscale value greater than w.

[0007] In the step S2, in the process of using optical character recognition (OCR) technology to recognize the text information in the form, the recognition result is verified and corrected to improve the accuracy of recognition; The image analysis algorithm includes an edge detection algorithm and a color analysis algorithm. The edge detection algorithm is used to detect the border of the table and calculate the width and style of the border. The color analysis algorithm is used to extract the background color and text style of the table.

[0008] A low-code form generation device based on image recognition, comprising an image recognition module, an information conversion module and a visual form designer; The image recognition module is responsible for using image recognition technology to recognize form images, which include screenshots and photographs; and preprocessing the form images, which includes image geometric correction, enhancement, denoising and binarization operations; at the same time, it is responsible for using optical character recognition (OCR) technology to recognize text information in the form, and extracting table style description information through image analysis algorithms, which includes width, height, border style, background color and text style; The information conversion module is responsible for automatically converting the extracted structured form text information and table style description information into low-code form configuration information, establishing the correspondence between form text information and low-code form elements, and generating style configuration parameters of the low-code form based on the table style description information; The visual form designer is responsible for rendering and displaying the converted low-code form configuration information for users to further develop and adjust.

[0009] The image recognition module adopts the mean denoising method, and the calculation method is as follows: ; Wherein, F(x, y) is the pixel value of the denoised image F at the pixel point (x, y) obtained by the mean denoising process; The global threshold s is calculated using the big law: ; Wherein, N is the total number of pixels of the denoised image F, w is the grayscale value, ranging from 0 to 255; q(w) is the number of pixels in the image with a grayscale value less than w; g(w) is the number of pixels in the image with a grayscale value greater than w.

[0010] In the image recognition module, the image analysis algorithm includes an edge detection algorithm and a color analysis algorithm; the edge detection algorithm is used to detect the border of the table and calculate the width and style of the border, and the color analysis algorithm is used to extract the background color and text style of the table.

[0011] In the process of recognizing text information in the form using the optical character recognition (OCR) technology, the image recognition module verifies and corrects the recognition result to improve the recognition accuracy.

[0012] A low-code form generation computing device based on image recognition, characterized in that it includes: One or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and are configured to be executed by the one or more processors, and the one or more programs include instructions for executing any of the above methods.

[0013] A computer-readable storage medium storing one or more programs, characterized in that: the one or more programs include instructions, which, when executed by a low-code form generation computing device based on image recognition, enable the low-code form generation computing device based on image recognition to perform any of the above methods.

[0014] The beneficial effect of the present invention is that the low-code form generation method and device based on image recognition can automatically identify form images, extract structured form text information and table style description information, and automatically convert them into low-code form configuration information, thereby improving form creation efficiency and reducing development costs. It has the advantages of high flexibility and a wide range of applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Attached Figure 1 This is a schematic diagram of the low-code form generation method based on image recognition of the present invention. DETAILED DESCRIPTION

[0017] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0018] The low-code form generation method based on image recognition includes the following steps: Step S1, using image recognition technology to identify the form image, the form image includes a screenshot and a photographed picture; performing image preprocessing operations on the form image, including geometric correction, enhancement, denoising and binarization; Step S2, using optical character recognition (OCR) technology to identify text information in the form, and extracting table style description information through an image analysis algorithm, wherein the table style description information includes width, height, border style, background color and text style; Step S3: automatically convert the extracted structured form text information and table style description information into low-code form configuration information, establish a corresponding relationship between the form text information and the low-code form elements, and generate the style configuration parameters of the low-code form according to the table style description information; Step S4. Render and display the converted low-code form configuration information (such as {"meta":{"column_format":"DOUBLE","max_length":50,...},"options":{"defaultValue":0,"required":false,...},"name":"Quantization bits","type":"number",...}) in the visual form designer for users to further develop and adjust.

[0019] In step S1, the specific implementation steps are: S101. Given an affine transformation matrix , where the linear transformation matrix , the translation matrix , read the form image to get the image representation matrix X, , where (x1, y1), (x2, y2) represent the image coordinates, and the form image is transformed to Y=R T X+t, get the geometric correction image matrix Y; S102, select the sharpening intensity coefficient , perform sharpening and enhancement processing on the geometric correction image matrix Y to obtain the sharpening and enhanced image Z: ; S103, reading the pixel value I(x, y) of any pixel point (x, y) in the sharpening enhanced image Z, selecting an area with m*n pixels in the surrounding neighborhood, performing filtering and noise reduction processing, and obtaining a noise reduction processed image F; The denoising process at least includes mean denoising. The pixel value F(x, y) of the denoised image F at the pixel point (x, y) obtained by the mean denoising process is: ; S104, further performing binarization processing on the denoised image F, converting the denoised image F from a grayscale image into a binary image B; The global threshold s is calculated using the big law: ; Wherein, N is the total number of pixels of the denoised image F, w is the grayscale value, ranging from 0 to 255; q(w) is the number of pixels in the image with a grayscale value less than w; g(w) is the number of pixels in the image with a grayscale value greater than w.

[0020] In the step S2, in the process of using optical character recognition (OCR) technology to recognize the text information in the form, the recognition result is verified and corrected to improve the accuracy of recognition; The image analysis algorithm includes an edge detection algorithm and a color analysis algorithm. The edge detection algorithm is used to detect the border of the table and calculate the width and style of the border. The color analysis algorithm is used to extract the background color and text style of the table.

[0021] The low-code form generation device based on image recognition includes an image recognition module, an information conversion module and a visual form designer; The image recognition module is responsible for using image recognition technology to recognize form images, which include screenshots and photographs; and preprocessing the form images, which includes image geometric correction, enhancement, denoising and binarization operations; at the same time, it is responsible for using optical character recognition (OCR) technology to recognize text information in the form, and extracting table style description information through image analysis algorithms, which includes width, height, border style, background color and text style; The information conversion module is responsible for automatically converting the extracted structured form text information and table style description information into low-code form configuration information, establishing the correspondence between form text information and low-code form elements, and generating style configuration parameters of the low-code form based on the table style description information; The visual form designer is responsible for rendering and displaying the converted low-code form configuration information for users to further develop and adjust.

[0022] The image recognition module adopts the mean denoising method, and the calculation method is as follows: ; Wherein, F(x, y) is the pixel value of the denoised image F at the pixel point (x, y) obtained by the mean denoising process; The global threshold s is calculated using the big law: ; Wherein, N is the total number of pixels of the denoised image F, w is the grayscale value, ranging from 0 to 255; q(w) is the number of pixels in the image with a grayscale value less than w; g(w) is the number of pixels in the image with a grayscale value greater than w.

[0023] In the image recognition module, the image analysis algorithm includes an edge detection algorithm and a color analysis algorithm; the edge detection algorithm is used to detect the border of the table and calculate the width and style of the border, and the color analysis algorithm is used to extract the background color and text style of the table.

[0024] In the process of recognizing text information in the form using the optical character recognition (OCR) technology, the image recognition module verifies and corrects the recognition result to improve the recognition accuracy.

[0025] The low-code form generation computing device based on image recognition includes: One or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and are configured to be executed by the one or more processors, and the one or more programs include instructions for executing any of the above methods.

[0026] A computer-readable storage medium storing one or more programs, characterized in that: the one or more programs include instructions, which, when executed by a low-code form generation computing device based on image recognition, enable the low-code form generation computing device based on image recognition to perform any of the above methods.

[0027] Compared with the prior art, the low-code form generation method and device based on image recognition has the following characteristics: Improved form creation efficiency: Form information is automatically extracted through image recognition technology and converted into low-code form configuration information, which greatly reduces the workload of manual input and improves the efficiency of form creation.

[0028] Reduced development costs: No need for professional developers to design complex forms, ordinary users can also quickly create forms through this method and device, reducing development costs.

[0029] High flexibility: Users can further develop and adjust the automatically generated forms in the visual form designer to meet different business needs.

[0030] Wide range of applications: The method and device are applicable to various types of form images, including screenshots, photographic images, etc., and have wide applicability.

[0031] The above is a detailed introduction to a low-code form generation method and device based on image recognition in an example of the present invention. This section uses specific examples to illustrate the principles and implementation methods of the invention. The above examples are only used to help understand the core ideas of the present invention. Without departing from the principles of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

Claims

1. A low-code form generation method based on image recognition, characterized in that: The following steps are involved: Step S1, using image recognition technology to identify the form image, the form image includes a screenshot and a photograph; Performing image preprocessing operations on the form image, including geometric correction, enhancement, denoising and binarization; Step S2, using optical character recognition (OCR) technology to identify text information in the form, and extracting table style description information through an image analysis algorithm, wherein the table style description information includes width, height, border style, background color and text style; Step S3: automatically convert the extracted structured form text information and table style description information into low-code form configuration information, establish a corresponding relationship between the form text information and the low-code form elements, and generate the style configuration parameters of the low-code form according to the table style description information; Step S4: Render and display the converted low-code form configuration information in the visual form designer for users to further develop and adjust.

2. The low-code form generation method based on image recognition according to claim 1 is characterized in that: In step S1, the specific implementation steps are: S101. Given an affine transformation matrix , where the linear transformation matrix , the translation matrix , read the form image to get the image representation matrix X, , where (x1, y1), (x2, y2) represent the image coordinates, and the form image is transformed to Y=R T X+t, get the geometric correction image matrix Y; S102, select the sharpening intensity coefficient , perform sharpening and enhancement processing on the geometric correction image matrix Y to obtain the sharpening and enhanced image Z: ; S103, reading the pixel value I(x, y) of any pixel point (x, y) in the sharpening enhanced image Z, selecting an area with m*n pixels in the surrounding neighborhood, performing filtering and noise reduction processing, and obtaining a noise reduction processed image F; S104 , further performing binarization processing on the denoised image F, and converting the denoised image F from a grayscale image into a binary image B.

3. The low-code form generation method based on image recognition according to claim 2 is characterized in that: In step S103, the noise reduction process adopts mean noise reduction process, and the calculation method is as follows: ; Wherein, F(x, y) is the pixel value of the denoised image F obtained by using mean denoising at the pixel point (x, y).

4. The low-code form generation method based on image recognition according to claim 2 is characterized in that: In step S104, the global threshold s is calculated using the big law method: ; Wherein, N is the total number of pixels of the denoised image F, w is the grayscale value, ranging from 0 to 255; q(w) is the number of pixels in the image with a grayscale value less than w; g(w) is the number of pixels in the image with a grayscale value greater than w.

5. The low-code form generation method based on image recognition according to claim 1 is characterized in that: In the step S2, in the process of using optical character recognition (OCR) technology to recognize the text information in the form, the recognition result is verified and corrected to improve the accuracy of recognition; The image analysis algorithm includes an edge detection algorithm and a color analysis algorithm. The edge detection algorithm is used to detect the border of the table and calculate the width and style of the border. The color analysis algorithm is used to extract the background color and text style of the table.

6. A low-code form generation device based on image recognition, characterized in that: Includes image recognition module, information conversion module and visual form designer; The image recognition module is responsible for recognizing the form image using image recognition technology, and the form image includes a screenshot and a photograph; The form image is preprocessed, including image geometry correction, enhancement, denoising and binarization operations; at the same time, the optical character recognition (OCR) technology is used to identify the text information in the form, and the form style description information is extracted through the image analysis algorithm, including width, height, border style, background color and text style; The information conversion module is responsible for automatically converting the extracted structured form text information and table style description information into low-code form configuration information, establishing the correspondence between form text information and low-code form elements, and generating style configuration parameters of the low-code form based on the table style description information; The visual form designer is responsible for rendering and displaying the converted low-code form configuration information for users to further develop and adjust.

7. The low-code form generation device based on image recognition according to claim 6 is characterized in that: The image recognition module adopts the mean denoising method, and the calculation method is as follows: ; Wherein, F(x, y) is the pixel value of the denoised image F at the pixel point (x, y) obtained by the mean denoising process; The global threshold s is calculated using the big law: ; Wherein, N is the total number of pixels of the denoised image F, w is the grayscale value, ranging from 0 to 255; q(w) is the number of pixels in the image with a grayscale value less than w; g(w) is the number of pixels in the image with a grayscale value greater than w.

8. The low-code form generation device based on image recognition according to claim 6 is characterized in that: The image recognition module uses optical character recognition (OCR) technology to recognize text information in the form, and performs verification and error correction on the recognition result to improve the accuracy of recognition; In the image recognition module, the image analysis algorithm includes an edge detection algorithm and a color analysis algorithm; The edge detection algorithm is used to detect the border of the table and calculate the width and style of the border, and the color analysis algorithm is used to extract the background color and text style of the table.

Citation Information

Patent Citations

  • Form rapid construction method based on OCR identification technology

    CN115600564A

  • Low-code application generation method and device, electronic equipment and storage medium

    CN118428336A