Abstract—Many real-world and man-made objects are line symmetry. To detection the line-symmetry objects from an image, in this paper, a new cluster validity measure which adopts a non-metric distance measure based on the idea of "line symmetry" is presented. The thresholding technique is first applied to extract the objects from the original image; and the object pixels are transferred to be the data patterns. Then the fuzzy clustering algorithm is applied to label the object pixels; and the proposed validity measure is used in determining the number of objects. Simulation results are used to illustrate the performance of the proposed measure.

Index Terms—Extract object, cluster validity, clustering algorithm, line symmetry, similarity measure.

Chien-Hsing Chou and Yung-Long Chu are with the Department of Electrical Engineering, Tamkang University, Taiwan (e-mail: chchou@mail.tku.edu.tw).
Yi-Zeng Hsieh and Mu-Chun Su are with the Department of Computer Science & Information Engineering, National Central University, Taiwan.

Cite:Chien-Hsing Chou, Yi-Zeng Hsieh, Mu-Chun Su, and Yung-Long Chu, "Extracting and Labelling the Objects from an Image by Using the Fuzzy Clustering Algorithm and a New Cluster Validity," International Journal of Computer and Communication Engineering vol. 2, no. 3, pp. 281-283, 2013.