SEMI SUPERVISED IMAGE SEGMENTATION USING OPTIMAL HIERARCHICAL CLUSTERING BY SELECTING INTERESTED REGION AS PRIOR INFORMATION

[摘要] Image segmentation is to be the first step in image analysis, pattern recognition and feature extraction. It is a critical but primary component of image analysis since it only determines the quality of the final result of image analysis. This paper discuss about the semi supervised image segmentation using hierarchical clustering algorithm. The prior information for the clustering process is given as an interested area selection from image using mouse. Here intensity, color and texture of the image properties are considered. The proposed idea gives more clarity of segmented regions than the existing methods using the other semi supervised method.

[关键词] semi supervised clustering;PSO algorithm;image segmentation