Applying New Method for Computing Initial Centers of k-Means Clustering with Color Image Segmentation

Abstract

As a classic clustering method, the traditional k-Means algorithm has been widely used in
image processing and computer vision, pattern recognition and machine learning. It is known that
the performance of the k-means clustering algorithm depends highly on initial cluster centers.
Generally initial cluster centers are selected randomly, so the algorithm could not lead to the
unique result. In this paper, we present a method to compute initial centers for
k-means clustering. Our method based on an efficient technique for estimating the modes of a
distribution. We apply the new method in segmentation phase of color images. The experimental
results appeared quite satisfactory.