A table frame line detection method based on region growth

A technology of region growth and detection method, which is applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve problems such as easy negligence, poor quality of tables and pictures, blurring, etc., and achieve the effect of improving enterprise efficiency and saving labor costs

Inactive Publication Date: 2019-05-24
上海眼控科技股份有限公司
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

This technology helps detect if an outside part or header on one sheet has been copied onto another piece of paper without affecting their content being counted by counting them automatically. It also saves time when managing multiple checks manually.

Problems solved by technology

This patented problem addressed in this patents relates to improving the accuracy and speed at identifying forms or documents from images captured through an image capturing device such as cameras used for scanning them during financial transactions. Existing methods have limitations due to factors like low resolution caused by camera lens distortion, lack of ability to automatically recognize irregularities around tables, insufficiently accurate identification results when there may occur partial blockage between different parts of the document being analyzed (such as if multiple pages were taken together), and damage to the surface texture of the sheet material causing streaks overlapping areas where two sheets meet each other without any overlap.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A table frame line detection method based on region growth

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention is mainly based on processing methods such as image tilt correction, image preprocessing, adaptive binarization processing and line search based on region generation.

[0037] For a picture of a financial statement downloaded from the server, specifically:

[0038] First of all, it is necessary to perform image tilt correction processing on the obtained financial statement picture, as follows:

[0039] S2-1. In order to reduce the amount of calculation for searching for a straight line, use the canny edge detection algorithm to perform edge detection on the financial statement picture to obtain an edge detection map;

[0040] S2-2, using hough transform to detect straight lines on the edge detection map;

[0041] S2-3. Screen the straight lines that meet the conditions, and record their inclination angles;

[0042] S2-4. Use a voting mechanism to determine the tilt angle with the most votes as the tilt angle of the image;

[0043] S2-5. Using affin

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a table frame line detection method based on region growth. The method comprises the following steps: downloading a table picture from a server; performing image inclination correction processing on the table picture; performing image preprocessing on the table picture; carrying out self-adaptive binarization processing on the table picture; determining an initial run section of a straight line on the binary processing graph of the table picture; Growing the direction of the whole straight line for each run section according to a certain regular area; and carrying out post-processing on the table picture, including straight line connection and screening. According to the method, the table outer frame can be effectively detected, and good robustness can be kept for interference such as wrinkles and unclearness of the table receipt.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Owner 上海眼控科技股份有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products