Algorithm on detection and identification of foreign fibers in raw cotton

Foreign fibers accounted for a small proportion in cotton, but there is serious impact on the quality of textile. Foreign fibers are removed by hand, which is low efficiency. To meet the requirements of accuracy and real-time, the identification of foreign fibers base on machine vision is proposed. The traditional algorithm of identification is generally complex and large amount of calculation, so real-time is bad. In this paper, according to the character of image gray of foreign fibers, and mathematical model is established. Further, important image features are enhanced by image processing, foreign fibers´ characters are drawn. At last, foreign fibers in cotton are identified by algorithm, and algorithm is simple and efficient.