Automated Vision System for Recognising Lycra Spandex Defects
Research and development
Author:
- Su Te-Li
Department of Cosmetic Application and Management, St. Mary’s Medicine, Nursing and Management Collage, Yilan, Taiwan R. O. C.
 Full text | Abstract: Fabric defect detection and classification plays a very important role in the automatic detection process for fabrics. This paper refers to the seven commonly seen defects of lycra spandex: laddering, end-out, hole, oil spot, dye stain, snag, and crease mark. First of all, thegray level co-occurrence matrix was used to collect the features of the fabric image texture, and then the back-propagation neural network was used to establish flaw classifications of the fabric. In addition, by using the Taguchi method combined with BPNN, the BPNN drawback was improved upon, which requires overly time consuming trial-and-error to find the learning parameters, and could therefore converge even faster with an even smaller convergence error and better recognition rate. The experimental results proved that the final root-mean-square error convergence of the Taguchi-based BPNN was 0.000104, and that the recognition rate can reach 97.14%. |
Tags: lycra spandex defects, automated vision recognition, Taguchi method, neural network.
Citation: Su T.-L. Lu C.-F.; Automated Vision System for Recognising Lycra Spandex Defects. FIBRES & TEXTILES in Eastern Europe 2011, Vol. 19, No. 1 (84) pp. 43-46.