The Implementation Of Feature Parameters Extraction Algorithms Of Fibers Based On N Chain Code

This paper is a part of the research sponsored by the Foundation of National Excellent Doctoral Dissertation of China and the Scientific Research Foundation for the Returned Overseas Chinese Scholars, State Education Ministry. The research is also sponsored by the Shanghai Entry-Exit Inspection and Quarantine Bureau of P R China. The research mainly deals with the algorithms for automatic recognition of the nature cellulose fiber and the classification of shaped fiber. The automated fiber recognition system consists of image collection, image preprocessing, feature extraction and pattern recognition. It is designed to implement the automated fiber recognition. The process is executed without operator's interference.The input of the proposed algorithm in this paper is separated fiber, the output of the image segmentation. Fiber's feature parameters are calculated and the recognition model is developed.In the paper, the research background for fiber feature parameter calculation is reviewed briefly. Some related theory and algorithms are studied with comparison. The shortcomings of conventional algorithms are analyzed for the application of feature parameter calculation and fiber recognition. The algorithms are proposed to deal such shortcomings.Feature parameter calculation is an important pre-processing in pattern recognition. The recognition performance is largely depended on the proper selection of the feature parameters. By studying the relations of the n chain code to the feature parameters, the effect of the n chain code on the contour of fibers is studied for different n. The error is studied for six kinds of common shapes. Three models, area-error, perimeter-error and code-error, are used for the study of the relation between the different n and the smoothing of contour shape. The optimization for the value of n is proposed. A fast algorithm to calculate the local maximum for a discrete pixel set is presented. Fiber's feature calculation algorithms are proposed to deal with the corner location, straight line calculation, and contour classification for the shape of fibers in cross-sectional images. A feature calculation algorithm based on n chain code is developed.A pattern recognition system should be able to learn from the task and abstracting the decision rules. The theory of support vector machine (SVM) is an effective learning algorithm for small sample prediction. With kernel functions, SVM can constitute a high dimensional model with limited samples. It aims at the minimization rule for structural risk. Thereby it can achieve a good balance between empirical risk and classifier capacity. Therefore, SVM is applied for fiber recognition and the performance of the proposed algorithm is improved prominently.