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

Fiber identification and segmentation method

A fiber identification, single fiber technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve problems such as many interference lines, single fiber extraction is not considered, and transparent fiber grayscale changes are not obvious.

Active Publication Date: 2018-06-29
ZHEJIANG UNIV OF TECH
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] To sum up, the main problems in the single-fiber segmentation scheme of the strip fiber image under the microscope are: (1) In the strip fiber image, the gray level changes obviously for the part where the fibers overlap, while for the transparent fiber image The change of fiber gray level is not obvious, and the traditional threshold method and watershed are difficult to achieve segmentation; (2) the strip fiber outline is closed and long, and there are bending, multiple overlapping and multiple crossing phenomena in the image, In the process of segmentation with edge detection, there are many interference lines, and it is difficult to match and cluster the contours of the same root fiber; (3) only is a single-pixel fiber and does not consider the specific accuracy of the extraction of a single fiber

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
  • Fiber identification and segmentation method
  • Fiber identification and segmentation method
  • Fiber identification and segmentation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The present invention is described in detail below in conjunction with examples and pictures.

[0046] Step 1: If figure 1 It is the fiber image under the microscope, read in the image, grayscale, use the 3*3 kernel for noise reduction, use the Canny operator to detect the edge, and get the edge figure 2 ;

[0047] Step 2: Right figure 2 Perform traversal and disconnection operations, and store the coordinate set of each curve after disconnection into the curve set lines. The specific steps are:

[0048] Step 2.1: Find figure 2 If the white pixel in is not found, it will end; otherwise, the found white pixel will be used as the head node p 1 (x 1 ,y 1 ), put p 1 Stored in the curve line;

[0049] Step 2.2: Pass p 1 Find the next white pixel point p in the eight-neighborhood of the point 2 (x 2 ,y 2 ), put p 2 Add to line, record p 2 in p 1 The position in the eight-neighborhood, such as image 3 , the red arrow indicates the direction to obtain the wh...

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 fiber identification and segmentation method. The fiber identification and segmentation method can automatically segment a single curve in a picture. Compared with manual segmentation, the fiber identification and segmentation method disclosed by the invention greatly improves efficiency, and a curve head slope, a tail slope, length and an interval variance are used for determining the rough contour of a fiber edge so as to realize the single segmentation of the fiber.

Description

technical field [0001] The invention relates to the field of image recognition and segmentation, in particular to a fiber segmentation method for matching and clustering fiber outer contours through edge detection. Background technique [0002] With the continuous development of digital image processing technology and deep learning, the identification and detection technology of fiber types has advanced by leaps and bounds, but there has been no universally applicable method for automatic segmentation of fiber images by computer, and the existing segmentation technologies generally have limitations. For different morphological fibers, different segmentation methods are required to extract them. [0003] For the identification and detection of strip fibers, it is necessary to provide a large number of single strip fiber samples, and to obtain these samples, it is necessary to first intercept a single strip fiber sample from an image containing multiple strip fibers, but The ...

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): G06K9/40G06K9/46
CPCG06V10/30G06V10/44
Inventor 高飞林俊辉刘浩然卢书芳张元鸣肖刚
Owner ZHEJIANG UNIV OF TECH
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