Investigation on novel metaheuristic algorithms based classifier and multipath cnn for detection of defects in fabric

Abstract

Today, the textile business is one of the most popular businesses worldwide, especially in developing countries like India, Bangladesh etc. The defect in the fabric is one of the significant factors which affect the quality of fabrics. Therefore detecting defects in the fabric is essential for quality control in textile products. In most of the garment industries, second quality fabrics are the result of non-detected fabric defects. The price of this second quality product is reduced by 45% - 65% of the first quality fabrics. Still, there is a need to identify the best method to inspect fabric quality efficiently, though there are quality materials and improved technologies. In defective fabric, the weave pattern of the fabric may differ from the original design due to the wrong mechanical movement or breakage of thread on a loom. The fabric quality inspection process is carried out in online and offline mode. But in most industries, the fabric inspection process is still carried out in offline mode with the help of skilled staff with a maximum accuracy of 60%-75%. However manual inspection process fails due to lack of concentration, human fatigue, and time consumption. Therefore, Computer vision-based automatic fabric defect detection system is developed to address the limitations of the manual fabric inspection process. In textile manufacturing and quality inspection process, digital image processing techniques are very much useful. It is confirmed to be the most capable, speed and reliable result for the future enhancement of automatic fabric defect detection systems. In most existing systems, a learning-based approach is implemented for defect detection in simple patterned fabrics. In this research, novel metaheuristic algorithms based classifier is proposed to select newline