Title :
A Recognition Method for Wool and Cashmere Fiber Based on the Feature of the Spectral Line
Author :
Jiang Gaoping ; Zhong Yueqi ; Wang Rongwu
Author_Institution :
Donghua Univ., Shanghai, China
Abstract :
This paper provides a recognition method for wool and cashmere fiber based on the feature of the spectral line. In this study, the morphology of the wool and cashmere fibers are determined by optical microscope. Then from the images, a great number of fiber surface information are obtained. And through a local projection method and segmented into unit, the spectral line of the wool/cashmere fiber are extracted. The features of each spectral line, such as unit width, unit peak value and coefficient of dispersion, are extracted according to the characteristics of the surface morphology. Hence, the difference helped to identify wool from cashmere based on the analysis of the features of such spectral lines.
Keywords :
feature extraction; image recognition; image segmentation; optical microscopes; wool; fiber surface information; local projection method; optical microscope; recognition method; spectral line; surface morphology; unit peak value; wool-cashmere fibers; Axles; Data mining; Feature extraction; Image analysis; Image processing; Image segmentation; Optical microscopy; Scanning electron microscopy; Surface morphology; Wool;
Conference_Titel :
Information Science and Engineering (ICISE), 2009 1st International Conference on
Conference_Location :
Nanjing
Print_ISBN :
978-1-4244-4909-5
DOI :
10.1109/ICISE.2009.144
