Denoising of Microarray Images using the Markov Random Field Model in the Spatial Domain
Conference: Creative Trends in Engineering and Technology
DNA Microarray technology is a very useful area in bioinformatics research. Microarray gene expression data\nallow us to quantitatively and simultaneously monitor the expression of thousands of genes under different conditions.\nDenoising is one of the major pre-processing steps in microarray image analysis. This paper presents a new spatial domain\ntechnique for denoising a DNA microarray image. The proposed method uses Markov Random Field model to reduce the\nnoise in the microarray image. The probability mass function for the Markov Random Field uses Quadratic Energy Function.\nMaximum-a-Posteriori method is used to estimate the noiseless pixel values followed by Quasi-Newton method to solve the\nunconstrained non-linear optimization problem. Experimental results and analysis illustrate the performance of the proposed\nmethod with contemporary methods.
CTET - 2016