Cloth defect classification method based on LBP features and convolutional neural network

A convolutional neural network and defect classification technology, applied in the field of fabric defect classification based on LBP features and convolutional neural network, can solve the problems of high false detection rate and missed detection rate, detection efficiency of detection algorithm and low detection accuracy, etc. Achieve the effect of improving accuracy, high defect detection accuracy, and simple algorithm implementation

Pending Publication Date: 2020-02-21
YANSHAN UNIV
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The detection efficiency and detection accuracy of the traditional detection algorithm are not high, and under the conditions of complex background and uneven illumination, the traditional detection algorithm has a high false detection rate and missed detection rate

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
  • Cloth defect classification method based on LBP features and convolutional neural network
  • Cloth defect classification method based on LBP features and convolutional neural network
  • Cloth defect classification method based on LBP features and convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] In order to make the technical solutions and advantages of the present invention more clear, the technical solutions in the embodiments of the present invention are clearly and completely described below in conjunction with the drawings in the embodiments of the present invention:

[0031] A cloth defect classification method based on LBP features and convolutional neural network of the present invention, figure 1 It is a flow chart of the defect classification method of the present invention, figure 2 The flow chart of the steps for defect classification, the specific implementation steps are as follows:

[0032] Step 1: Collect multiple images of cloth samples;

[0033] Step 2: In order for the support vector machine model to be able to finally classify the defects, it is divided into three folders: normal image, hole hole image and plasma spot image, and store the image name and the corresponding number 0-3; the label type is: normal is the number 0, the hole is 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

The invention discloses a cloth defect classification method based on LBP features and a convolutional neural network, and belongs to a defect classification method. According to the method, collectedsample images are randomly divided into a training set, a verification set and a test set in proportion; image preprocessing is carried out, weight fusion is carried out on the optimal feature vectorautomatically extracted from the sample image by using the convolutional neural model and the LBP feature vector calculated by the image; a final support vector is provided for the support vector machine classification model; the support vector machine optimizes hyper-parameters in the model by using a magnetotactic bacterium algorithm with an elitist strategy; the LBP features of the image are considered; after extraction, only weight addition of the feature vectors automatically extracted by the convolutional neural network needs to be carried out, interference of the cloth background is obviously reduced, the method has no requirement for the design and color of the cloth, the method can be used for solving the cloth defect detection problem of different designs and colors and single colors, and the method has the advantages of simple algorithm implementation, high classification accuracy and high operation efficiency.

Description

technical field [0001] The invention relates to a defect classification method, in particular to a cloth defect classification method based on LBP features and a convolutional neural network. Background technique [0002] Artificial intelligence is a national strategic emerging industry. With the continuous improvement of the information construction of the manufacturing industry, and the relatively complete industrial layout, and the textile industry is a traditional light industry pillar industry in my country, the final grading of textiles depends on the quality of the cloth. Cloth defect inspection is an important link in the production and quality management of the textile industry, and cloth defect intelligent detection is a technical bottleneck that has plagued the industry for many years. At present, almost all inspections are done manually, which is easily affected by subjective factors and lacks consistency; and the long-term work of inspectors under strong light ...

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): G06T7/00G06T7/11G06T7/187G06T7/194G06T5/00G06T5/40G06K9/62G06N3/04G06N3/08G06N3/00
CPCG06T7/0004G06T7/11G06T7/187G06T7/194G06T5/40G06N3/084G06N3/006G06T2207/10004G06T2207/20024G06T2207/20081G06T2207/20084G06T2207/30124G06N3/045G06F18/241G06F18/2411G06T5/70Y02P90/30
Inventor 郭保苏庄集超章钦李锦瑞
Owner YANSHAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products