Abstract: The fabric defect identification system requires efficient and Robust Defect Detection algorithms. Due to large number of fabric defect classes, the automatic fabric inspection system is very challenging. When researchers consider reduction of labor cost and its benefits, the automatic fabric inspection system is very economical. Various techniques have been developed to detect fabric defects. Based on the features of fabric, the defect detection techniques have been characterized into three categories. They are statistical, structural and model based techniques. This study presents entropy based fabric defect detection from the images of textile industry. Textile industry needs to produce less defective textiles for minimizing production cost and time consumption. The images are acquired, preprocessed, statistical feature-entropy is extracted. The artificial neural network is used as identification model. The extracted feature is given as input to the artificial neural network, it identifies the defect. The proposed method shows a better performance when compared with the existing methods.
P. Banumathi and G.M. Nasira, 2014. Fabric Defect Identification System Using Statistical Approach and Artificial Neural Network Techniques. Research Journal of Applied Sciences, 9: 619-623.