Study of Image Segmentation Techniques on Microscopic Cell Images of Section of Rat Brain for Identification of Cell Body and Dendrite

摘要

Present paper illustrates the study and comparison of different image segmentation techniques on microscopic cell images-a part of computerization for cell image analysis. The process of segmentation is highly required for analysis and to study the behavior of live cell structure. The error is less in the computerized system of cell image analysis as compared to the manual system. Region growing, region split and merging, FCM, k-mean, and hybrid clustering segmentation technique are used for comparison. Hybrid clustering gives better results than other techniques in terms of accuracy and time, while region spit and merging and FCM give poor results. For performance evaluation, some parameters are used.