DefinePK

Abstract

The mean-shift clustering is an efficient technique for color image segmentation by dividing an image into homogeneous regions. The main drawback of mean-shift clustering is to use a fixed scale, which directly determines to use a fixed homogeneity. Since each region could have different homogeneity, using a fixed scale has a problem to segment well. To resolve this problem, we incorporate multi-resolution search by providing different scales to regions. The proposed algorithm starts initially at lowest resolution first and then proceeds to higher resolution where the search results are only refined. The proposed algorithm is applied to skin color segmentation.