No abstract

Digital image processing is important for image information extraction. One of the image processing methods is morphological image processing. This technique uses erosion and dilation operations to enhance and improve the image quality by shrinking and enlarging the image foreground. However, morphological image processing performance depends on the characteristics of structuring elements and their foreground image that need to be extracted. This paper studies how the structuring elements affect the performance of morphological erosion and dilation on binary images. The experimental result shows that choosing the right structuring element for morphological erosion and dilation can significantly influence the foreground and background structure of the output image.

Normalization is a process of removing systematic variation that affects measured gene expression levels in the microarray experiment. The purpose is to get more accurate DNA microarray result by deleting the systematic errors that may have occurred during the making of DNA microarray Image. In this paper, five normalization methods of Global, Lowess, House-keeping, Quantile and Print-tip are discussed. The Print Tip normalization was chosen for its high accuracy (32.89 dB and its final MA graph shape was well normalized. Print tip normalization with PSNR value of 33.15dB has been chosen as a new normalization method. The results were validated using four images from the formal database for DNA microarray data. The new proposed method showed more accurate results than the existing methods in term of four parameters: MSE, PSNR, RMSE and MAE.

A deoxyribonucleic acid (DNA) microarray image requires a three-stage process to enhance and preserve the image’s important information. These are gridding, segmentation, and intensity extraction. Of these three processes, segmentation is considered the most difficult, as its function is to differentiate between features in the foreground and background. The elements in the foreground form the object or the vital information of the image, while the background features less critical information for DNA microarray image analysis. This paper presents a study that utilises the Markov random field (MRF) segmentation algorithm on a DNA microarray image. The MRF algorithm evaluates the current pixel depends on its neighbouring pixels. The experimental results show that the MRF algorithm works effectively in the segmentation process for a DNA microarray image.