Check patentability & draft patents in minutes with Patsnap Eureka AI!

Mathematic morphology-based rapid small target image threshold value segmentation method

A technique of mathematical morphology and threshold segmentation, which is applied in image analysis, image data processing, instruments, etc., and can solve problems such as real-time detection of small objects.

Active Publication Date: 2018-03-13
TIANJIN POLYTECHNIC UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the real-time problem of small target detection in images, and provide a threshold segmentation method based on mathematical morphology for small target detection in images

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
  • Mathematic morphology-based rapid small target image threshold value segmentation method
  • Mathematic morphology-based rapid small target image threshold value segmentation method
  • Mathematic morphology-based rapid small target image threshold value segmentation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] figure 2 (a) is an image containing a small target in this embodiment, from figure 2 It can be seen from (a) that the target in the image accounts for a small proportion of the background, figure 2 (b) is the image processed by morphological opening operation, image 3 It is a comparison chart of the histogram before and after the morphological opening operation. The black thick line indicates the histogram before the morphological opening operation, and the blue thin line indicates the histogram after the morphological opening operation. It can be seen that the histogram before and after the processing has occurred Variety. Figure 4 is the rate of change of the gray histogram before and after the morphological opening operation, and the threshold T can be set according to the principle of maximum value, that is, determined according to the gray level corresponding to the maximum value of the rate of change of the histogram. The threshold T=176 in this embodiment...

Embodiment 2

[0043] Figure 7 (a) is an image containing a small object in this embodiment, wherein the small object is a lotus. Figure 7 (b) is a binary image segmented by the method of the present invention, wherein the morphological processing adopts the open operation, The value is 10. Depend on Figure 7 It can be seen that the lotus information is well preserved in the segmentation result of the method of the present invention.

Embodiment 3

[0045] Figure 8(a) is an image containing a small target in this embodiment, where the small target is a tree trunk. Figure 8 (b) is a binary image segmented by the method of the present invention, wherein the morphological processing adopts a closed operation, The value is 10. Depend on Figure 8 It can be seen that although the segmented image has a little noise, the method of the present invention basically retains the entire small target information.

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 mathematic morphology-based rapid small target image threshold value segmentation method. The method comprises the following steps of: firstly graying and denoising a to-be-detected image to improve the image quality; strengthening a target by utilizing mathematic morphological processing; and setting a threshold value through change of a grey level histogram function ofthe image before and after the morphological processing, so as to segment the image and then segment to-be-detected small targets in the image. The method is capable of self-adaptively segment the small targets from the image, has the characteristics of being simple and efficient, and is suitable for the online detection of the small targets in the image.

Description

technical field [0001] The invention relates to a fast threshold segmentation method for detecting small targets in images, in particular to a mathematical morphology-based fast threshold segmentation method for small target images, which belongs to the field of digital image processing. Background technique [0002] Image segmentation is used to extract meaningful target parts in the image, which is the basis of high-level computer vision processing. So far, there have been many image segmentation methods, which can be roughly divided into three categories: edge-based segmentation, region-based segmentation, and threshold-based segmentation. Threshold-based segmentation is simple and efficient, and is suitable for unsupervised decision-making in pattern recognition because it does not require prior knowledge of images. Appropriate threshold is the key to threshold segmentation, and improper threshold will affect target recognition. [0003] In the field of image processin...

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): G06T7/11G06T7/187G06T7/136
Inventor 杨彦利赵燕飞
Owner TIANJIN POLYTECHNIC UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com