An Efficient Agglomerative Clustering Algorithm for Region Growing.
Takio Kurita · 1994
This paper proposes an efficient agglomerative clustering algorithm for region growing. To speed up the search of the best pair of segments which is merged into one segment, dissimilarity values of all possible pairs of segments are stored in a heap. Then the best pair can be found as the element of the root node of the binary tree corresponding to the heap. Since the only adjacent pairs of segments are possible to be merged in image segmentation, this constraints of neighboring relations are represented by sorted linked lists. Then we can reduce the computation for updating the dissimilarity values and neighboring relations which are influenced by the merging of the best pair. The proposed algorithm is applied to the segmentations of a monochrome image and range images. 1. Introduction Image segmentation is the one of the most fundamental and important techniques in image processing and pattern recognition. There are three approaches, (1) characteristic feature thresholding or cluste...