Study of Image Quantization Technology Based on FCM Clustering Algorithm
Di-lan YANG, Zhang Ju-wu · 2010
Aiming at a defect on randomness of the initial clustering center choosing and sensitivity of initial value in tradition FCM, a clustering algorithm about FCM of weighted Characteristic is proposed. It compensates the color's inhomogeneous by interposing weighted matrix in RGB color space, and uses a statistics clustering algorithm of minimal maximal distance in class to initiate clustering center. The results indicates the algorithm can decrease effectively the mean square deviation of color quantization, keep overall arrangement of ideas and part characteristic detail in image reconstruction and is helpful for the study of the image process technology.