scholarly journals Fabric Defect Detection System Using Stacked Convolutional Denoising Auto-Encoders Trained with Synthetic Defect Data

2020 ◽  
Vol 10 (7) ◽  
pp. 2511
Author(s):  
Young-Joo Han ◽  
Ha-Jin Yu
Keyword(s):  
Image Segmentation ◽  
Deep Learning ◽  
Machine Vision ◽  
Image Classification ◽  
Defect Detection ◽  
Detection System ◽  
Image Detection ◽  
Fabric Defect Detection ◽  
Fabric Defect ◽  
Segmentation Image

As defect detection using machine vision is diversifying and expanding, approaches using deep learning are increasing. Recently, there have been much research for detecting and classifying defects using image segmentation, image detection, and image classification. These methods are effective but require a large number of actual defect data. However, it is very difficult to get a large amount of actual defect data in industrial areas. To overcome this problem, we propose a method for defect detection using stacked convolutional autoencoders. The autoencoders we proposed are trained by using only non-defect data and synthetic defect data generated by using the characteristics of defect based on the knowledge of the experts. A key advantage of our approach is that actual defect data is not required, and we verified that the performance is comparable to the systems trained using real defect data.

Machine Vision Window Division on Self-Adaptation

2011 ◽  
Vol 460-461 ◽  
pp. 617-620
Author(s):  
Xiu Chen Wang
Keyword(s):  
Image Analysis ◽  
Machine Vision ◽  
Defect Detection ◽  
Actual Situation ◽  
Adaptive Window ◽  
Fabric Defect Detection ◽  
Fabric Defect ◽  
Self Adaptation ◽  
Recognition Efficiency ◽  
Division Model

Aiming at time-consuming and ineffective problem of image window division in fabric defect detection, this paper proposes a new adaptive division method after a large number of experiments. This method can quickly and exactly recognize defect feature. Firstly, a division model on adaptive window is established, secondly, the formula to anticipate generally situation of fabric image is given according to the peaks and valleys change in the model, and methods to calculate the division size and position of adaptive window are given. Finally, we conclude that the algorithm in this paper can quickly and simply select the size and position of window division according to actual situation of different fabric images, and the time of image analysis is shortened and the recognition efficiency is improved.

Fabric Defect Detection System

2021 ◽  
pp. 788-800
Author(s):  
Tanjim Mahmud ◽  
Juel Sikder ◽  
Rana Jyoti Chakma ◽  
Jannat Fardoush
Keyword(s):  
Defect Detection ◽  
Detection System ◽  
Fabric Defect Detection ◽  
Fabric Defect

scholarly journals Texture defect detection by using polynomial interpolation and multilayer perceptron

2019 ◽  
Vol 14 ◽  
pp. 155892501882527
Author(s):  
Sabeur Abid
Keyword(s):  
Defect Detection ◽  
Manufacturing Industry ◽  
Polynomial Interpolation ◽  
Detection System ◽  
Labor Cost ◽  
Fabric Defect Detection ◽  
Accuracy Comparison ◽  
Comparison Results ◽  
Fabric Defect ◽  
Texture Defect Detection

This article deals with fabric defect detection. The quality control in textile manufacturing industry becomes an important task, and the investment in this field is more than economical when reduction in labor cost and associated benefits are considered. This work is developed in collaboration with “PARTNER TEXTILE” company which expressed its need to install automated defect fabric detection system around its circular knitting machines. In this article, we present a new fabric defect detection method based on a polynomial interpolation of the fabric texture. The different image areas with and without defects are approximated by appropriate interpolating polynomials. Then, the coefficients of these polynomials are used to train a neural network to detect and locate regions of defects. The efficiency of the method is shown through simulations on different kinds of fabric defects provided by the company and the evaluation of the classification accuracy. Comparison results show that the proposed method outperforms several existing ones in terms of rapidity, localization, and precision.

scholarly journals A fabric defect detection method based on deep learning

IEEE Access ◽  
2022 ◽  
pp. 1-1
Author(s):  
Qiang Liu ◽  
Chuan Wang ◽  
Yusheng Li ◽  
Mingwang Gao ◽  
Jingao Li
Keyword(s):  
Deep Learning ◽  
Defect Detection ◽  
Detection Method ◽  
Fabric Defect Detection ◽  
Fabric Defect

Fabric Defect Detection Using Wavelet-Enhanced Single-Point Photoelectric Sensing System

2012 ◽  
Vol 162 ◽  
pp. 497-504
Author(s):  
Shun Cong Zhong ◽  
Qiu Kun Zhang ◽  
Li Gang Yao ◽  
Yao Chun Shen
Keyword(s):  
Defect Detection ◽  
Light Transmission ◽  
Detection System ◽  
Single Point ◽  
Fluorescent Light ◽  
Fabric Defect Detection ◽  
Noise Rate ◽  
Fabric Defect ◽  
Negative Effect ◽  
Defect Signal

A fabric defect detection system based on single-point photoelectric sensing, was proposed and developed. The performance of the system was enhanced by using wavelet denoising algorithm to reduce the negative effect of noise and the environment disturb, such as fluorescent light in the factory. Instead of detection of light reflection from fabric, a light transmission technique with higher signal-to-noise rate was employed in the system for evaluating the fabric defect. A Si photodiode was used to record the defect signal of fabric. The signal was enhanced by stationary wavelet transform. The signal was quantitatively evaluated and finally a defect alarm was triggered. From the experimental results, the timeliness, robustness and detection precision of the system were demonstrated, therefore, it could be recommended for the applications in fabric industries.

Sign in / Sign up

Export Citation Format

Share Document