Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Inter-class relative uniformity-based image adaptive thresholding method and apparatus

A uniformity and image technology, applied in the field of image processing, can solve problems such as difficulty in obtaining expected results, threshold deviation, etc., to achieve the effect of complete target, clear edge, and improved applicability

Inactive Publication Date: 2017-05-31
XIAN UNIV OF POSTS & TELECOMM
View PDF1 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Although many applications and improvement methods based on the Otsu threshold method emerge in an endless stream, in the actual application process, the limitations of this method are found
The main aspect is that there are deficiencies in considering the comprehensive factors of target and background class cohesion and inter-class discreteness, especially for images with large differences in foreground and background uniformity, the obtained threshold will deviate greatly, and it is difficult to obtain expected result

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
  • Inter-class relative uniformity-based image adaptive thresholding method and apparatus
  • Inter-class relative uniformity-based image adaptive thresholding method and apparatus
  • Inter-class relative uniformity-based image adaptive thresholding method and apparatus

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] Now in conjunction with the accompanying drawings, the preferred embodiments of the present invention will be described in detail.

[0018] The invention proposes an image self-adaptive thresholding method based on the relative uniformity between classes. First, based on the idea of ​​the Otsu threshold method focused on the target, the histogram information of the image is introduced to obtain a thresholding criterion function combined with the image distribution information; in view of the relativity of the existing Otsu threshold method to the uniform distribution of the target (background) Insufficient, the present invention reforms it, and proposes the Otsu threshold method based on the relative uniformity between classes, that is, the situation before the method of the present invention is optimized. Secondly, in order to have better adaptability to images of different distribution types, the present invention introduces weight coefficients for adjustment to obtai...

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 inter-class relative uniformity-based image adaptive thresholding method and apparatus. The method comprises the following steps of reading a grayscale image; calculating a probability, a mean value and a variance of grayscale distribution; calculating relative uniformity information of two types of to-be-segmented grayscale distribution, wherein two types of grayscales are a target grayscale and a background grayscale respectively; and based on relative probability distribution and relative uniformity information of the two types, establishing a thresholding criterion function of inter-class relative uniformity. According to the method and the apparatus, a target obtained by segmentation is completer, and the edge is clearer, so that the applicability can be improved.

Description

technical field [0001] The present invention relates to image processing, in particular to the processing of grayscale images. Background technique [0002] In image preprocessing, thresholding segmentation algorithm has been widely researched and applied due to its simplicity, efficiency, and ease of understanding. The Otsu threshold method based on the principle of separation between classes occupies an important position in the thresholding algorithm. It has become a widely used and popularized thresholding method because of its simple execution and good effect. There are countless improvements and popularization methods based on this method. . [0003] Based on the correction method of image histogram distribution information, the deviation problem of Otsu method in threshold selection is improved, and the adaptability to images is improved. The two-dimensional Otsu method based on "gray-mean" has a remarkable effect in anti-noise. In order to improve the calculation ...

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
IPC IPC(8): G06T7/136
Inventor 张弘
Owner XIAN UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com