An Integration Strategy based on Fuzzy Clustering and Level Set Method for Cell Image Segmentation

View/ Open
Author(s)
Gharipour, A
Liew, AWC
Griffith University Author(s)
Year published
2013
Metadata
Show full item recordAbstract
In this study a new image segmentation framework which combines the Fuzzy c means clustering and the level set method is presented. Using this framework, the well-known Chan and Vese's level set technique and classical Bayes classifier are employed to obtain a prior membership value for each pixel based on region information. Next, a novel clustering model based on fuzzy c-mean clustering assisted by prior membership values is used to obtain the final segmentation. Experiments performed on high-throughput fluorescence microscopy colon cancer cell images, which are commonly utilized for the study of many normal and neoplastic ...
View more >In this study a new image segmentation framework which combines the Fuzzy c means clustering and the level set method is presented. Using this framework, the well-known Chan and Vese's level set technique and classical Bayes classifier are employed to obtain a prior membership value for each pixel based on region information. Next, a novel clustering model based on fuzzy c-mean clustering assisted by prior membership values is used to obtain the final segmentation. Experiments performed on high-throughput fluorescence microscopy colon cancer cell images, which are commonly utilized for the study of many normal and neoplastic procedures, indicate a significant improvement in accuracy when compared to several existing techniques.
View less >
View more >In this study a new image segmentation framework which combines the Fuzzy c means clustering and the level set method is presented. Using this framework, the well-known Chan and Vese's level set technique and classical Bayes classifier are employed to obtain a prior membership value for each pixel based on region information. Next, a novel clustering model based on fuzzy c-mean clustering assisted by prior membership values is used to obtain the final segmentation. Experiments performed on high-throughput fluorescence microscopy colon cancer cell images, which are commonly utilized for the study of many normal and neoplastic procedures, indicate a significant improvement in accuracy when compared to several existing techniques.
View less >
Conference Title
2013 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2013
Publisher URI
Copyright Statement
© 2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Subject
Computer vision