Development of a real-time machine vision system for functional textile fabric defect detection using a deep YOLOv4 model

We introduce a real-time machine vision system we developed with the aim of detecting defects in functional textile fabrics with good precision at relatively fast detection speeds to assist in textile industry quality control. The system consists of image acquisition hardware and image processing software. The software we developed uses data preprocessing techniques to break down raw images to smaller suitable sizes. Filtering is employed to denoise and enhance some features. To generalize and multiply the data to create robustness, we use data augmentation, which is followed by labeling where the defects in the images are labeled and tagged. Lastly, we utilize YOLOv4 for localization where the system is trained with weights of a pretrained model. Our software is deployed with the hardware that we designed to implement the detection system. The designed system shows strong performance in defect detection with precision of [Formula: see text], and recall and [Formula: see text] scores of [Formula: see text] and [Formula: see text], respectively. The detection speed is relatively fast at [Formula: see text] fps with a prediction speed of [Formula: see text] ms. Our system can automatically locate functional textile fabric defects with high confidence in real time.

[1]  Aysin Ertüzün,et al.  An efficient method for texture defect detection: sub-band domain co-occurrence matrices , 2000, Image Vis. Comput..

[2]  Chunlei Li,et al.  Fabric defect recognition using optimized neural networks , 2019, Journal of Engineered Fibers and Fabrics.

[3]  C. J. Kuo,et al.  A Back-Propagation Neural Network for Recognizing Fabric Defects , 2003 .

[4]  Cordelia Schmid,et al.  High-dimensional data clustering , 2006, Comput. Stat. Data Anal..

[5]  Xi Chen,et al.  Defect detection on the fabric with complex texture via dual-scale over-complete dictionary , 2016 .

[6]  N. H. C. Yung,et al.  Automated fabric defect detection - A review , 2011, Image Vis. Comput..

[7]  Grantham Pang,et al.  Discriminative training approaches to fabric defect classification based on wavelet transform , 2004, Pattern Recognit..

[8]  Junfeng Jing,et al.  Supervised defect detection on textile fabrics via optimal Gabor filter , 2014 .

[9]  Bernd Scholz-Reiter,et al.  Design of deep convolutional neural network architectures for automated feature extraction in industrial inspection , 2016 .

[10]  Dandan Zhu,et al.  Yarn-Dyed Fabric Defect Detection Based On Autocorrelation Function And GLCM , 2015 .

[11]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[12]  Moncef Gabbouj,et al.  Center weighted median filters: Some properties and their applications in image processing , 1994, Signal Process..

[13]  N. H. C. Yung,et al.  Motif-based defect detection for patterned fabric , 2008, Pattern Recognit..

[14]  Chi-Ho Chan,et al.  Fabric defect detection by Fourier analysis , 1999, Conference Record of the 1999 IEEE Industry Applications Conference. Thirty-Forth IAS Annual Meeting (Cat. No.99CH36370).

[15]  Jian Sun,et al.  Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition , 2015, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Jing-Rong Li,et al.  Unsupervised fabric defect detection based on a deep convolutional generative adversarial network , 2019, Textile Research Journal.

[17]  Hichem Snoussi,et al.  A fast and robust convolutional neural network-based defect detection model in product quality control , 2017, The International Journal of Advanced Manufacturing Technology.

[18]  Ajay Kumar,et al.  Computer-Vision-Based Fabric Defect Detection: A Survey , 2008, IEEE Transactions on Industrial Electronics.

[19]  Grantham K. H. Pang,et al.  Discriminative fabric defect detection using adaptive wavelets , 2002 .

[20]  Du-Ming Tsai,et al.  Automated surface inspection for statistical textures , 2003, Image Vis. Comput..

[21]  Junfeng Jing,et al.  Fabric defect detection using the improved YOLOv3 model , 2020 .

[22]  Nadia Baaziz,et al.  Automatic Fabric Defect Detection Using Learning-Based Local Textural Distributions in the Contourlet Domain , 2018, IEEE Transactions on Automation Science and Engineering.

[23]  Errol J. Wood,et al.  Applying Fourier and Associated Transforms to Pattern Characterization in Textiles , 1990 .

[24]  Yu Zhang,et al.  Fabric defect classification using radial basis function network , 2010, Pattern Recognit. Lett..

[25]  Sung Yong Shin,et al.  Fast determination of textural periodicity using distance matching function , 1999, Pattern Recognit. Lett..

[26]  Ayush Dogra,et al.  Image Sharpening By Gaussian And Butterworth High Pass Filter , 2014 .

[27]  Michael K. Ng,et al.  Wavelet based methods on patterned fabric defect detection , 2005, Pattern Recognit..

[28]  Mohand Saïd Allili,et al.  Texture Modeling Using Contourlets and Finite Mixtures of Generalized Gaussian Distributions and Applications , 2014, IEEE Transactions on Multimedia.

[29]  Hao Ma,et al.  Automatic fabric defect detection using a deep convolutional neural network , 2019, Coloration Technology.

[30]  Chung-Feng Jeffrey Kuo,et al.  Using a Neural Network to Identify Fabric Defects in Dynamic Cloth Inspection , 2003 .

[31]  Stavros A. Koubias,et al.  Real-Time Vision-Based System for Textile Fabric Inspection , 2001, Real Time Imaging.

[32]  Huosheng Xie,et al.  A Robust Fabric Defect Detection Method Based on Improved RefineDet , 2020, Sensors.