A new classification method for animal fibers

Scale pattern of cashmere and fine wool is different and that is a major reference distinguishing them from each other. A technique commonly used consists of analyzing their SEM image for detecting cuticle scale edge height (CSH) of fiber. However, the method is expensive and only a small quantity of fiber samples is detected, which make the average error approach 8 percent. In this paper, a new method is presented. The fiber images captured by CCD camera are transformed into skeletonized binary images only having one pixel wide and showing only fiber and scale edge details. Four basic shape parameters of fiber scale are measured and a database composed of numerical data of four relative indexes, which are fiber diameter, scale interval, normalized scale perimeter and normalized scale area, is established. Finally, a multi-parameter Bayes classification model based on them is developed. The numerical experiment results show that through the new model is based on light microscopy, its classification performance is similar to that of those model based on scanning electronic microscopy when distinguishing cashmere from fine wool (70 s) and the accuracy rate approaches 90 percent.