Unlock instant, AI-driven research and patent intelligence for your innovation.

A cloth defect detection method based on regional fusion characteristics

A defect detection and region fusion technology, applied in the field of machine learning, can solve problems such as unstable evaluation standards, missed and false detections, and susceptibility to subjective factors

Pending Publication Date: 2019-04-26
JIANGSU UNIV
View PDF1 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The accuracy and speed of manual detection depend on the experience and proficiency of the operator, and the evaluation standard is unstable and easily affected by subjective factors, resulting in missed and false detections

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 cloth defect detection method based on regional fusion characteristics
  • A cloth defect detection method based on regional fusion characteristics
  • A cloth defect detection method based on regional fusion characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0063] Such as figure 1 As shown, the present invention proposes a cloth defect detection method and device based on the fusion of LBP features, and adopts the following technical solutions:

[0064] Step 1, obtain the real-time image information of the cloth through the industrial camera, and then send it to the microcomputer for processing; the microcomputer is a raspberry pie, figure 2 As shown, the real-time image information of the cloth is obtained; according to the prior knowledge, the cloth surface part is selected; for the single-layer smooth cloth, the white light source on the back is ...

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 real-time flaw detection method in a single-layer plain cloth production process. According to the method, firstly, an industrial camera is used for collecting video images of cloth produced by a loom in real time, noise information is filtered out through Fourier transform, secondly, an LBP and HOG fusion feature of a cloth candidate area is extracted through a sliding window method, and finally flaws are finely classified through multiple types of support vector machines. The device comprises an industrial camera for collecting cloth defects, a light source, a mechanical fixing device and a raspberry pi platform for algorithm operation. The defects of flaw classification and positioning in a traditional method can be overcome, accurate positioning and real-timedetection of flaws such as broken yarns, jumpers and greasy dirt appearing in a smooth single-layer plain cloth cover are achieved, and unmanned cloth flaw monitoring is achieved.

Description

technical field [0001] The invention relates to the field of machine learning, and proposes a method for detecting cloth defects by fusing HOG-LBP regional features. Background technique [0002] With the development of technology, the scale of the textile industry has grown rapidly, and it has become an important economic pillar of my country's basic industry. In the production process of textiles, surface defects of cloth are the main factors affecting the quality of cloth. Cloth surface defects directly affect the cloth surface grade, and the price of second-class products is generally only half of that of first-class products. Defects caused by jumpers and other reasons will directly lead to waste products and unnecessary losses. Therefore, cloth defect detection is particularly important in the quality inspection of textiles. [0003] For a long time, cloth quality inspection has always been done manually. The accuracy and speed of manual detection depend on the exp...

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): G06T7/00G06T5/00G06T5/10G06K9/46G06K9/62
CPCG06T5/10G06T7/0008G06T2207/30124G06T2207/20056G06V10/50G06V10/467G06F18/253G06T5/70Y02P90/30
Inventor 何永贵沈继锋刘冰沙骁骅
Owner JIANGSU UNIV