Real time fabric defect detection system on Matlab and C++/Opencv platforms

Author(s):  
Kazim Hanbay ◽  
Sedat Golgiyaz ◽  
Muhammed Fatih Talu
Optik ◽  
2013 ◽  
Vol 124 (21) ◽  
pp. 5280-5284 ◽  
Author(s):  
Jagdish Lal Raheja ◽  
Bandla Ajay ◽  
Ankit Chaudhary

2020 ◽  
Vol 10 (7) ◽  
pp. 2511
Author(s):  
Young-Joo Han ◽  
Ha-Jin Yu

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.


Author(s):  
Tanjim Mahmud ◽  
Juel Sikder ◽  
Rana Jyoti Chakma ◽  
Jannat Fardoush

2019 ◽  
Vol 14 ◽  
pp. 155892501882527
Author(s):  
Sabeur Abid

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.


Author(s):  
Khaled Ragab

Automating fabric defect detection has a significant role in fabric industries. However, the existing fabric defect detection algorithms lack the real-time performance that is required in real applications due to their high demanding computation. To ensure real time, high accuracy and reliable fabric defect detection this paper developed a fast and parallel normalized cross-correlation algorithm based on summed-area table technique called PFDD-SAT. To meet real-time requirements, extensive use of the NVIDIA CUDA framework for Graphical Processing Unit (GPU) computing is made. The detailed implementation steps of the PFDD-SAT are illustrated in this paper. Several experiments have been carried out to evaluate the detection time and accuracy and then the robustness to illumination and Gaussian noises. The results show that the PFDD-SAT has robustness to noise and speeds the defect detection process more than 200 times than normal required time and that greatly met the needs for real-time automatic fabric defect detection.


2012 ◽  
Vol 162 ◽  
pp. 497-504
Author(s):  
Shun Cong Zhong ◽  
Qiu Kun Zhang ◽  
Li Gang Yao ◽  
Yao Chun Shen

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.


10.5772/62058 ◽  
2016 ◽  
Vol 13 (1) ◽  
pp. 1 ◽  
Author(s):  
Tianpeng Feng ◽  
Lian Zou ◽  
Jia Yan ◽  
Wenxuan Shi ◽  
Yifeng Liu ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document