Automatic Technique for Skew Correction and Denoising of Microarray Images

Abstract

DNA microarray technology has promised a very accelerating research inclination in recent years. There are numerous applications of this technology, including clinical diagnosis and treatment, drug design and discovery, tumour detection, and in the environmental health research. Skew correction and Denoising are the major pre-processing steps in microarray image analysis. Microarray images when corrupted with noise may drastically affect the subsequent stages of image analysis and finally affects gene expression profile. In this paper a fully automatic skew correction
algorithm based on corner spots detection to detect and correct any skew in the subgrid and morphological approach with adaptive threshold to denoise microarray images is presented. The morphological operators like dilation, erosion and adaptive threshold are used in the filtering process. Experiments on Stanford and TBDB illustrate robustness of the proposed approach in the presence of noise, artifacts and weakly expressed spots. Experimental results and analysis illustrates the performance of the proposed method with the contemporary methods.