Comparison of fuzzy C means and K means clustering technique using color segmentation for prostate cancer cell images / Nuratiqah Mohd Zahari

Segmentation of an image entails the division or separation of the image into regions of similar attribute. The most basic attribute for segmentation of an image is its color components for a color image. Clustering is one of the methods used for segmentation. The aim of the project is to investigat...

Full description

Saved in:
Bibliographic Details
Main Author: Mohd Zahari, Nuratiqah
Format: Thesis
Language:English
Published: 2012
Online Access:https://ir.uitm.edu.my/id/eprint/87116/1/87116.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Segmentation of an image entails the division or separation of the image into regions of similar attribute. The most basic attribute for segmentation of an image is its color components for a color image. Clustering is one of the methods used for segmentation. The aim of the project is to investigate two methods of segmentation based on accuracy and efficiency. Twenty color images of prostate cancer cell are converted into L*a*b*color space and are segmented using Fuzzy C-Means clustering and K-Means clustering. Accuracy of segmentation are judged by visually inspecting the abnormal cell area, which is brown in color. Segmentation time is also measured to determine which clustering technique is faster. Results showed that Fuzzy C-Means clustering produced better segmentation results. However, K-Means clustering technique is faster compared to Fuzzy C-Means clustering.