Abstract:
Inspection of fabrics is a major consideration in fabric manufacture, as well as in the manufacture of garments and other fabric-based goods. In the Sri Lankan industry almost all fabric inspection is carried out by manual methods, and is therefore subjective and prone to human error. Various automated fabric inspection systems have been developed in various parts of the world. These systems are, however, rather costly. The purpose of this research is to design a cost-effective fabric inspection system for the objective assessment of fabric defects. This system is being designed with special relevance to the Sri Lankan industry, and should be capable of giving consistent results irrespective of user. Image processing techniques are used to scan images of the test fabric, compare it with an ideal sample with which the system has been calibrated before the commencement of inspection, and identify defects, according to pre-learnt rules. The information gathered would then be used to grade the fabric, either by giving the frequency of occurrence of defects or by assigning points. A new classification method for common defects has been designed, that will facilitate easy grading according to commonly used grading systems. A coding system for defects has also been designed, which will help in the reporting of defects to the user.