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

Otsu algorithm based on local adaptation

A local self-adaptive and algorithmic technology, applied in computing, image data processing, instruments, etc., can solve problems such as difficult to obtain segmentation results, high time overhead, and difficult to obtain the best threshold

Inactive Publication Date: 2018-12-25
LIAONING UNIVERSITY OF TECHNOLOGY
View PDF7 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the algorithm is relatively simple, it needs to traverse all the pixels in the image when calculating the variance, resulting in a large time overhead, so it is difficult to apply it to a real-time image processing system
In addition, if only the grayscale histogram of the image is used to select the threshold for image segmentation, it is often difficult to obtain the optimal threshold, so it is difficult to obtain better segmentation results

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
  • Otsu algorithm based on local adaptation
  • Otsu algorithm based on local adaptation
  • Otsu algorithm based on local adaptation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] Otsu algorithm based on local adaptation:

[0018] The principle of one-dimensional Otsu algorithm can be expressed as follows: Suppose the image has L gray levels, the total number of pixels with gray value i is n, and the total number of pixels in the entire image is N, then the proportion of gray value i in the image is for and have Set the threshold as T, and divide the image gray level into 2 categories, namely the so-called foreground and background. Let foreground A=(1,2,...,T), background B=(T+1,T+2,...,L-1), T∈(0,L-1), we can get The proportions of A and B in the image are respectively:

[0019]

[0020] Then it can be concluded that the average gray value of A and B is:

[0021]

[0022] Then the average gray value of the image is

[0023]

[0024] Finally, the variance between image classes is obtained as:

[0025] σ 2 =p A (w A -w 0 ) 2 +p B (w B -w 0 ) 2 (1).

[0026] From formula (1), we can see that σ 2 The larger the value, t...

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

Based on the locally adaptive Otsu algorithm, the specific method is to use sliding windows to traverse the entire image, Otsu threshold segmentation is performed on each window to get each local binary image, and then using image mosaic technology, these binary images are spliced to get the whole image segmentation results. Experimental results show that the segmentation effect of the proposed algorithm is better than that of the original Otsu algorithm, and the time overhead is significantly reduced. By using the technical scheme, the real-time requirement of image segmentation can be achieved.

Description

technical field [0001] The invention belongs to the field of computer image processing, in particular to Otsu algorithm based on local self-adaptation. Background technique [0002] Because it is not affected by image contrast and brightness changes, the Otsu algorithm is often used in image segmentation problems. Although the algorithm is relatively simple, it needs to traverse all the pixels in the image when calculating the variance, resulting in a large time cost, so it is difficult to apply to a real-time image processing system. In addition, if only the gray histogram of the image is used to select the threshold for image segmentation, it is often difficult to obtain the optimal threshold, so it is difficult to obtain better segmentation results. Contents of the invention [0003] The object of the present invention is to provide a locally adaptive Otsu algorithm. In order to improve the image segmentation effect, a locally adaptive threshold segmentation method is ...

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
CPCG06T7/136
Inventor 孙福明蔡希彪贾旭
Owner LIAONING UNIVERSITY OF TECHNOLOGY
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