Fabric defects detection using convolution neural network and multispectral imaging
Abstract : Manual inspection of textiles is a long, tedious, and costly method. Technology has solved this problem by developing automatic systems for textile inspection. However, Jacquard fabrics present a challenge because patterns can be complex and seemingly random to systems. Only a few in-depth studies have been conducted on jacquard fabrics despite their important and intriguing nature. Previous studies on jacquard fabrics are of simple patterns. This paper introduces a new and novel field in fabrics defect detection. Complex-patterned jacquard fabrics are much more challenging. In this paper, novel defect detection models for jacquard-patterned fabrics are presented. Owing to the lack of available databases for jacquard fabrics, we compiled and experimented on our own novel dataset. Our dataset was collected from plain, undyed jacquard fabrics with different complex patterns. In this study, we used and tested several deep learning models with image pre-processing and convolutional neural networks (CNNs) for unsupervised detection of defects. We also used multispectral imaging, combining normal (RGB) and near-infrared (NIR) imaging to improve our system and increase its accuracy. We propose two systems: a semi-manual system using a simple CNN network for operation on separate patterns and an integrated automated system that uses state-of-the-art CNN architectures to run on the entire dataset without prior pattern specification. The images are preprocessed using contrast-limited adaptive Histogram Equalization (CLAHE) to enhance their features. We concluded that deep learning is efficient and can be used for defect detection in complex patterns. Proposed method of EfficientNet CNN gave high accuracy reaching 99% approximately. We also found that multispectral imaging is more advantageous and yields higher accuracy.
? In order to further verify the effectiveness of the proposed model for defect classification, its classification performance is compared with the other three existing approaches.
? This paper also compares the CNN with three existing methods with the same defect type.
? It can be seen from the experimental results that the proposed CS-CNN method outperforms the other four existing methods on this dataset.
? The development of a flexible, efficient, reliable, and integrated real-time vision system for industrial applications is an essential issue in quality control processes in various industries.
? However, these methods do not consider the problem of fabric defect classification in small sample sizes.
? The CNN cannot handle the small sample sizes problem very well in classification, a new algorithm for fabric defect classification has been developed by combining compressive sensing and the CNN (CS-CNN).
• The general hardware and software platform, developed for solving this problem, is presented while a powerful novel method for defect detection after multi resolution decomposition of the fabric images is proposed.
• In this paper a real-time pilot system for defect detection and classification has been proposed and demonstrated.
• This paper proposes a real-time pilot system for defect detection and classification of web textile fabric based on standard, low price, hardware components and supported by very fast and effective software solutions.
? The most popular CNNs simply stack convolution layers deeper and deeper, hoping to achieve better performance.
? The purpose of this study is to introduce an automatic inspection system for jacquard-patterned fabrics to efficiently detect defects.
? The advantage of multispectral imaging was tested using this simple CNN model across 10 different patterns.
? We also found that multispectral imaging is more advantageous and yields a higher accuracy.
|