Invoice date positioning method based on segmentation Hough transformation straight line detection

A positioning method and line detection technology, applied in the field of image processing, can solve problems such as noise interference and line segmentation, achieve precise positioning, good detection effect, and avoid repeated searches.

Active Publication Date: 2014-07-30
陕西通力电梯设备有限公司
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method of invoice date location based on segmented Hough transform line detection, which solves the problems of noise interference, line segmentation, precise positioning, and repeated searches in the prior art

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
  • Invoice date positioning method based on segmentation Hough transformation straight line detection
  • Invoice date positioning method based on segmentation Hough transformation straight line detection
  • Invoice date positioning method based on segmentation Hough transformation straight line detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0025] refer to figure 1 , the present invention is based on the invoice date positioning method of subsection Hough transform straight line detection, implements according to the following steps:

[0026] Step 1: Obtain the width and height of the invoice image

[0027] Before performing the following steps, pre-binarize the invoice image to obtain the horizontal line in the image, figure 2 The invoice effect picture shown is as follows image 3 as shown,

[0028] After a lot of experiments, according to the invoice date sample, set the step size Ap_Length to 50;

[0029] Then set the size of the Hough[tMax][rMax] array, the first variable tMax is the radian dimension, tMax=180; the second variable rMax is the length dimension, and its calculation formula is:

[0030] rMax=(int)sqrt((float)(width*width+Ap_Length*Ap_Length))+1;

[0031...

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 an invoice date positioning method based on segmentation Hough transformation straight line detection. The method includes the steps that firstly, the width and the height of an invoice image are acquired; secondly, the two-value image is scanned from bottom to top according to the step sizes; thirdly, the length from each point to an original point is calculated in each step size, and a Hough matrix is stored; fourthly, a straight line with most points in the Hough matrix is acquired as a main straight line in the step sizes; fifthly, the number of the points on the straight line is counted, and whether the number of the points on the straight line is larger than a quarter of the width is judged, if yes, the sixth step is executed, and if not, the step sizes are added, and the third step is executed; sixthly, the number of breakpoints of the straight line is acquired, if the straight line is not within the range of being 100 from the upper end and the number of the breakpoints is smaller than 44 or the number of the points on the straight line is larger than one third of the width, the straight line is effective, and the seventh step is executed, or else the step sizes are added, and the third step is executed; seventhly, the slope and the position where the straight line is located are displayed. The method has the good detection effect on lines similar to horizontal straight lines.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to an invoice date positioning method based on segmented Hough transform line detection. Background technique [0002] In computer recognition, it is often necessary to find the region of interest from the image, and line detection, as an important link in image processing, is widely used by people. At present, the commonly used line detection algorithms include horizontal projection method, heuristic connection, Radon transform, chain code detection method and Hough transform and so on. [0003] The horizontal projection method is the simplest, but it interferes a lot with images with complex text information, and it must be rotated to find a straight line. The heuristic connection algorithm is relatively simple, but it is more sensitive to the edge detection results, and it is easy to produce broken short lines. The Radon transformation is simple and fast, but there is a ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00
Inventor 金海燕席倩王彬王晓帆黑新宏王磊叶晓辉
Owner 陕西通力电梯设备有限公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap