Denoising Based Clustering Algorithm for Segmentation of Microarray Image

J. Harikiran; M. l. Phanendra; P. Naga Srinivasu; Dr. P. V. Lakshmi; Dr. R. Kiran Kumar

A Deoxyribonucleic Acid (DNA) microarray is a collection of microscopic DNA spots attached to a solid surface, such as glass, plastic or silicon chip forming an array. The analysis of DNA microarray images allows the identification of gene expressions to draw biological conclusions for applications ranging from genetic profiling to diagnosis of cancer. The DNA microarray image analysis includes three tasks: gridding, segmentation and feature extraction. Clustering algorithms have been applied for segmenting the microarray image. However, noises are introduced into the images during acquisition or transmission process, affecting the segmentation results. Noise reduction is a prerequisite step prior to feature extraction attempts from microarray images. In order to overcome this drawback, this paper presents a new clustering based segmentation technique that can be used in segmenting noise microarray images. We call this method as Denoising Fuzzy Moving K-means Clustering algorithm (DFMK). The proposed algorithm is able to minimize the effect of Salt-and-Pepper noise during the segmentation process without degrading the fine details of the images. The method incorporates a noise detection stage to the clustering algorithm, producing an adaptive segmentation technique specifically for segmenting the noise microarray images. The results obtained from the proposed algorithm are more quantitative and qualitative than the conventional clustering algorithm such as K-means in segmenting the noise microarray images.

Select Volume / Issues:

• Volume 3 Issue 6, Nov. 2012

Year:

2012

Type of Publication:

Article

Keywords:

Microarray; Salt and Pepper Noise; Image Segmentation; Image Processing

Journal:

IJECCE

Volume:

3

Number:

6

Pages:

1608-1612

Month:

November