A ray detection image mark information character segmentation method based on edge detection

An edge detection and ray detection technology, which is used in character and pattern recognition, instruments, computer parts, etc., can solve the problems of the threshold segmentation method is no longer applicable, the image background is complex, and the contrast of the ray detection image is low, and the edge of the image can be protected. Information, good image noise, effects to resolve image blur and edge loss

Inactive Publication Date: 2019-05-17
XI AN JIAOTONG UNIV
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the low contrast of the ray detection image and the complex image background, the threshold segmentation method in the traditional character segmentation technology is no longer applicable

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 ray detection image mark information character segmentation method based on edge detection
  • A ray detection image mark information character segmentation method based on edge detection
  • A ray detection image mark information character segmentation method based on edge detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The invention provides a method for segmenting characters of ray detection image marking information based on edge detection. Firstly, the ray image is read in and converted into grayscale to obtain a grayscale image f(x, y); secondly, the improved LOG edge detection operator is used Perform edge detection on the grayscale image f(x,y) to obtain a binary image h(x,y) containing its edge information; perform edge detection on the discontinuous breakpoints in the above binary image h(x,y) Connect to obtain a binary image q(x,y) containing continuous edge information; then perform region filling operations on the binary image q(x,y) to obtain the filled image p(x,y)=imfill(q (x,y),'holes'); Finally, the region growing method is used to extract all the connected regions in the image p(x,y), and by judging the difference in the size of the connected regions between the marked information and the non-marked information, the complete ray Character segmentation of image tagging...

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 ray detection image mark information character segmentation method based on edge detection, and the method comprises the steps of reading a ray image, and carrying out the graying of the ray image, and obtaining a gray image; secondly, carrying out edge detection on the gray level image by utilizing an improved LOG edge detection operator to obtain a binary image containing edge information of the gray level image; performing edge connection on discontinuous breakpoints in the binary image to obtain a binary image containing continuous edge information; carrying out region filling operation on the binary image to obtain a filled image; and finally, extracting all connected regions in the image by adopting a region growing method, and comparing different areas between the connected regions of the mark information and the non-mark information so as to complete character segmentation of the mark information of the ray image. According to the present invention, the characters of the ray image marking information can be rapidly and effectively segmented, and a good foundation is laid for subsequent ray image marking information recognition.

Description

technical field [0001] The invention belongs to the technical field of character recognition of radiation detection image marking information, and in particular relates to a method for character segmentation of radiation detection image marking information based on edge detection. Background technique [0002] At present, in the non-destructive testing industry, the marking information on the radiographic inspection image is still entered manually, which has problems such as low efficiency and high labor intensity. This puts forward efficient and automatic identification requirements for the acquisition of radiographic inspection image marking information. [0003] Traditional character recognition technology can be roughly divided into character segmentation and character recognition. In character segmentation, threshold segmentation is often used to highlight the characters in the image. However, due to the low contrast of the ray detection image and the complex image back...

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): G06K9/34
Inventor 姜洪权高建民王晓桥王泉生夏锋社程雷贺帅李华
Owner XI AN JIAOTONG UNIV
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