A Suitable Neural Network to Detect Textile Defects

摘要: 25% of the total revenue earning is achieved from Textile exports for some countries like Bangladesh. It thus important to produce defect free high quality garment products. Inspection processes done on fabric industries are mostly manual hence time consuming. To reduce error identifying defects requires automotive and accurate inspection process. Considering this lacking, research implements a Defect detector. A multi-layer neural network determined that best classifies specific problems. feed digital images taken by camera converts RGB first converted into binary restoration process local threshold techniques, then three different features actual input network, which area defects, number objects in image finally shape factor. The develop system able identify two very commonly such as Holes Scratches other types minor defects. developed suitable Least Developed Countries, identifies within economical cost produces less prone real time.