Development Of Micro Fiber Edge Detection System Based On Grey System Theory

With the development of economy and technology,fiber has important application in all fields of society.The composition and quality of fiber determines its performance and price,and testing the integrity and continuity of the edge of the fiber has a direct impact on subsequent fiber image separation,feature extraction,pattern recognition and blending ratio calculation accuracy.Therefore,the fiber image edge detection is an important part of the fiber automatic recognition system.Because of the influence of illumination unevenness,background noise and focusing during embedding,slicing and image acquisition,fiber micrographs inevitably have poor fiber quality,no obvious difference between target and background,adhesion and contour fracture and so on.And the traditional edge detection algorithm to obtain the edge of the micro fibers appears false,discontinuous edge and can not effectively extract the edge of the adhesion of the problem.At the same time,the Shanghai entry exit inspection and Quarantine Bureau as the quality of import and export of the legal supervision organs,faces the import and export of the composition of the identification of blended fabrics in long-term.The current means of identification,is through the manual observation of the fabric slices of microscopic images to make subjective judgments.This traditional method of identification can not guarantee the accuracy of identification results while consumes a lot of human resources.So it is a very important subject to study the edge detection of micro fiber based on the computer digital image processing technology and the scientific grey system theory.This subject comes from National Natural Science Foundation of China,"Non-negative Matrix Factorization Algorithm Based on Constraints and Its Application in Automatic Fiber Recognition"(61472075).Our college is a university where textile and clothing and other areas in the country's leading place for a long time and has identification of cotton chemical fabrics with rich achievements.So how to use the existing digital image processing technology and the gray system theory introduced in image edge detection in recent years to extract the complete,continuous and accurate fiber edge information becomes the key of this paper.Based on the gray system theory,NIBLACK algorithm and the hole filling algorithm,an edge detection algorithm of micro fiber based on the gray system theory is proposed,and an automatic detection system of micro fiber edge is developed.For each pixel in the image of micro fiber as the research object,the edge detection method based on gray system theory combines the GM(1,1)model and NIBLACK algorithm to obtain the strong and weak edge information of micro-fiber and realizes the strong and weak edge connection effectively and then uses the hole filling algorithm to deal with false edges to extract the complete edge information.According to the design of micro fiber edge detection system based on grey system theory,this paper plays the advantage that "less data poor information modeling" of grey system theory,introduces the idea of system design and implementation and displays the results of the design by starting from the principle of the algorithm and making full use of grey system theory in the system of academic research in China in a strong position and advanced level.Experimental results show that the proposed design can extract the complete and accurate edge information of micro fibers.