An improved SVM method for cDNA microarray image segmentation

Microarray technology, as a revolutionary tool for biomedical research, has been widely used to analyze the gene expression level. Image segmentation is an important step of microarray technology. In this paper, we have presented an improved SVM method, which combined the SVM with the canny algorithm, the morphological algorithm and the fixed circle method, to obtain a better segmentation result. In addition, the initial image was preprocessed by using the image contrast enhancement and median filtering. Intensive experiments on the Stanford Microarray Database (SMD) and the Gene Expression Omnibus (GEO) database indicate that the proposed method is superior to the K-means method and the GenePix.Pro.