A neural-network-based machine-learning model for fabric defect detection and classification using fused global features.

Detecting defects and classifying them is a primary requirement for textile industries. Manual methods of defect identification and classification happens in most cases for which the accuracy could not exceed more than 70%. A real time, fast and automated system for defect detection and classification is required for textile industries. This paper addresses this challenge and explores the use of different machine-learning models for the global features such as GLCM and Tamura extracted from checked pattern fabrics. In the training phase, machine-learning models produce an accuracy of > 90% and testing with new fabric images provides a maximum accuracy of 65%. To improve the accuracy of the classification system, an artificial neural network-based machine-learning model with features fusing has been proposed. Using the proposed approach, a testing accuracy of 80% is observed, and an accuracy of 96.1% is achieved in the training phase. [ABSTRACT FROM AUTHOR]