An image-based method for the automatic recognition of cashmere and wool fibers

Abstract

Due to the similarity of the morphological and textural structure between cashmere and wool fibers, it is a great challenge to identify these two animal fibers automatically. In this paper, one set of image-based method using the gray level co-occurrence matrix algorithm, the interactive measurement algorithm and the k-means clustering algorithm were proposed to identify cashmere and wool fibers quickly and accurately. Firstly, thousands of fiber images were observed by optical microscope and captured by digital camera and two different preprocessing methods were used to obtain the input images for the different feature extraction algorithm. Then the texture features were extracted by the gray level co-occurrence matrix and the diameter of fibers was measured by the interactive measurement algorithm. Finally, the extracted features were fed into the fiber identification system based on k-means algorithm for classification. The experimental results indicated that the proposed method was feasible for the recognition of cashmere and wool fibers with a high recognition of 94.29%.