ETFA'09 Proceedings of the 14th IEEE international conference on Emerging technologies & factory automation
Yarn periodical errors determination using three signal processing approaches
Digital Signal Processing
Hi-index | 0.00 |
In this paper, a new method of automatic recognition of yarn count based on digital image processing is presented. In order to eliminate the influence of hairiness of yarn and improve the measurement precision, Fuzzy C-Means Clustering algorithm is proposed. Then get the ratio between yarn and interstice. Finally ascertain the projected diameter of yarn automatically and calculate the count of yarn. Experimental results show that the precision can be improved by selecting different threshold of membership degree for the yarn with different extent of hairiness.