A new approach to the unsupervised detection and classification of the spliced yarn joint

• Autorzy: Issa K. , Nagahashi H.
• Języki publikacji: EN

Abstrakty

EN

This paper presents an automatic vision-based system for unsupervised detection and classification of spliced yarn joints. In the splice detection process, a competitive learning method based on an LBG algorithm is used. In the splice classification process, a dynamic time warping (DTW) algorithm is used to classify the extracted splice joint into one of three categories, based on the degree of similarity between the spliced joint and the non- spliced remaining part of the same yarn. The use of DTW in the classification makes the proposed method adaptable to different types of yarns. Consequently, this method might be universally applicable for the classification of all spliced yarn joints. The proposed method has been evaluated using three types of experiments, yielding a promising result.

Słowa kluczowe

EN

spliced yarn joint; visual inspection; VQ; DTW

PL

zaplątane połączenia przędz; inspekcja wizualna; DTW

• Wydawca: Lodz University of Technology, Faculty of Material Technologies and Textile Design
• Czasopismo: Autex Research Journal
• Rocznik: 2008
• Tom: Vol. 8, no. 1
• Strony: 6--12
• Opis fizyczny: Bibliogr. 14 poz.

Twórcy

autor

Issa K.

• Imaging Science and Engineering Laboratory, Tokyo Institute of Technology, Japan

autor

Nagahashi H.

• Imaging Science and Engineering Laboratory, Tokyo Institute of Technology, Japan

Bibliografia

• 1. Rudolf Luz, Method and apparatus for preparing yarn ends for splicing, USP 4,528,808 7/1985 57/22.
• 2. Koji Deno, Yarn end untwisting device for a pneumatic yarn splicing device, USP 4,494,366 1/1985 57/22.
• 3. Khaled Issa & Rudi Grutz, New technique for optimizing yarn-end preparation on splicer and a method for rating the quality of yarn end. Autex Research Journal, 2005, Vol.5, No.1, pp.1 19.
• 4. Cheng.K.P.S and Lam H.L.I., ‘Physical properties of pneumatically spliced cotton ring spun yarn’, Textile Res.J.,70,2000,12,1053-1057.
• 5. Cybulska M. Assessing yarn structure with image analysis method. Textile Res. J.69, 1999,05, 369-374.
• 6. Emery, N. B., and Buchanan, D. R., Yarn Package Inspection with Computer Vision and Robotics, Textile Res. J. 58, 605-614 (1988).
• 7. Stanislaw Lewandowski, Tomasz Stanczyck, ‘Identification and classification of spliced wool combed yarn joints by artificial neural networks’, Fiberes & Textile in Eastern Europe, 2005, Vol.13 No 1.(49), pp. 39-43.
• 8. Lewandowski S., Drobina R., ‘Strength and Geometric Sizes of Pneumatically Spliced Combed Wool Ring Spun Yarns’, Fibres & Textiles in Eastern Europe, 2004, Vol.12, No 2 (46), pp. 31-37.
• 9. G. B. Coleman and H. C. Andrew, ‘Image segmentation by clustering’, Proc. IEEE, 67,5, May 1979, 773-785.
• 10. J-H. Wang and C-Y. Peng, “Optimal Clustering Using Neural Networks,” IEEE International Conference on Systems, Man, and Cybernetics, Vol. 2, pp. 1625-1630, 1998.
• 11. Likas, A., Vlassis, N., & Verbeek, J. J. (2003). The global k-means clustering algorithm. Pattern Recognition, 36, 451–461.
• 12. Linde, Y., Buzo, A., & Gray, R.M. (1980). An algorithm for vector quantizer design. IEEE Transactions on Communication, COM-28, 84–95.
• 13. Keogh, E., & Pazzani, M. (2000) Scaling up dynamic time warping for datamining applications. In 6th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Boston.
• 14. William K. Pratt Digital image processing 3rd ed. (Academic press, New York, 2001) pp. 189-199.