DCSFPSS assisted morphological approach for grey twill fabric defect detection and defect area measurement for fabric grading

This paper proposes a new optimal morphological filter design using DC suppressed Fourier power spectrum sum (DCSFPSS) plot as a major technique to extract the texture periodicity features of textile fabrics. Periodicity is further used to assist the selection of size of structuring element(SE) for morphological operation(MO) to detect grey twill fabric defects. The performance of the scheme is evaluated on number of homogeneous twill grey fabric images with loose weft and stitch type of defects. Computation of number of defects, area of each defect and total defect area in a given fabric image is estimated. Then a simple binary based defect search algorithm is adopted to determine the presence of defects. The performance parameter of the proposed algorithm is firstly obtained in terms of accuracy of correct defect detection (ACD) which is found to be 98% for stitch and 94.7% for loose weft defect samples of two twill grey fabric classes. Secondly, the recognition of defect area less than 1mm², which has not been reported in the literature yet, was possible using this algorithm. Further we propose to use this method to grade the fabric based on standard systems adopted for classifying the fabric. The details of the experimentation and the results thereof are presented in this paper.