Title :
A survey of thresholding algorithms on yarn images
Author_Institution :
Computer Engineering Department, Technical University of Lodz, 18/22 Stefanowskiego Str., Lodz, 90-924, POLAND
Abstract :
The problem of image segmentation is considered. Popular thresholding methods are reviewed and tested on images presenting yarn of different hairiness. Results of image segmentation provided by the regarded thresholding approaches are presented, compared and analyzed. Especially their capabilities of extracting single fibers protruding from the yarn core are examined. Outcomes of the analysis are presented and discussed.
Keywords :
"Yarn","Image segmentation","Machine vision","Data mining","Textile fibers","Spatial resolution","Computer vision","Inspection","Testing","Image analysis"
Conference_Titel :
Perspective Technologies and Methods in MEMS Design (MEMSTECH), 2010 Proceedings of VIth International Conference on
Print_ISBN :
978-1-4244-7325-0
