Fuzzy Classification of Animal Fibers Using Neuro-Fuzzy Classifier

Structure of cashmere and fine wool fiber is similar. It has been difficult to classify them accurately. Scale pattern is a major reference distinguishing them from each other. At present, the procedure is completed by experts of this field by analyzing SEM or LM image of fiber, which is tedious, time-consumed and subjective. In this paper, an objective approach based on neuro-fuzzy classification tool is presented to classify these two types of fiber. Firstly, the color light microscope images of fiber captured by CCD camera are transformed into skelrtonzied binary images only having one pixel wide and showing only fiber and scale edge details. Then four basic shape parameters of fiber scale are measured and a database composed of numerical data of four comparable indexes, which are fiber diameter, scale interval, normalized scale perimeter and normalized scale area, is established. A neuro-fuzzy classifier is developed based on them. The simulation results show that whether on training set or testing set, the model can always distinguish cashmere from fine wool (70s) effectively and the average classification accuracy are higher than 90 percent.