基于自适应FCM聚类的彩色图像区域分割算法

Region-based color image segmentation algorithm with adaptive FCM clustering

传统的基于聚类的图像分割方法大都存在聚类数目难以确定、过度分割等缺点。针对这些问题,提出一种新的彩色图像区域分割算法。首先将彩色图像划分为3×3的图像子块,然后在RGB色彩空间中抽取子块的颜色特征和位置特征共同组成子块的特征向量,最后运用自适应的FCM算法进行聚类,进而分割图像成区域。实验结果表明,这种分割方法具有比较理想的分割效果。

Traditional clustering-based image segmentation methods often have some disadvantages, such as difficult to determine the number of clusters, image over-segmentation etc. To resolve these problems, a new region-based color image segmentation algorithm is introduced in this paper, which divides an image to 3 x 3 sub-blocks firstly. Then, the color and position features of every sub-block are extracted to form feature vectors. Finally, an adaptive FCM （Fuzzy c-means Clustering Method） algorithm is used to cluster, thus the image is divided into regions. The experimental results show that this segmentation method has an ideal segmentation effect.