Abstract:

For rapid identification and inspection of wool and cashmere, this paper suggests an identifacation method based on the characteristics of spectral line. First, the images of wool and cashmere are taken using optical microscope. Secondly, the surface information of the wool and cashmere is obtained from the images by image processing. Thirdly, the spectral lines of the wool and cashmere are extracted by a local projection method with feature segmentation. The features of each spectral line such as unit width, unit peak value and coefficient of discretion, and peak width are extracted according to the different characteristics of the surface. We finally differentiate wool and cashmere based on the analysis of the features of these spectral lines. Experimental results demonstrate that this method works quickly and effectively which has remarkable advantages in comparison with the previous methods.