Segmentation of Defects in Textile Images Based on Adaptive Sparse Domain Selection Method

Abstract

Generalized fabric inspection system needs perfect and efficient pattern recognition to detect and identify different types of defects in various kinds of fabrics. The inspection system needs on good environment for managing the fabric manufacturing unit and inspection unit with better results. In real time production environment, it is difficult to detect defects automatically for whole fabrics, although fabrics may be characterized by color, pattern, texture, and material quality. Human visual system is labor prone, costly, less accuracy and time consuming system. These drawbacks are overcome by automated fabric inspection system which provides warning to manufacturing unit to stop and recover the production, if it detects abnormalities in the process.