A computer vision approach for textile quality control

Textile manufacturers have to monitor tire quality of their products in ord er to maintain the high-quality standards established for the clothing indu stry. Thus, textile quality control is a key factor for the increase of com petitiveness of their companies. Textile faults have traditionally been det ected by human visual inspection. However, human inspection is time consumi ng and does not achieve a high level of accuracy. Therefore, industrial vis ion units are of strategic interest for the textile industry as they could form the basis of a system achieving a high degree of accuracy on textile i nspection. This work describes the software core of a system designed for f abric inspection on the basis of simple image-processing operations as well as its efficiency on defection of usual textile defects. The prerequisites of the over all system are then discussed analytically, as well as the lim itations and the restrictions imposed due to the nature of the problem. The software algorithm and the evaluation of the first results are also presen ted in. details. Copyright (C) 2001 John Wiley & Sons, Ltd.