Segmentation of Microscopy images using Multi-Scale Retinex with Chromacity Preservation and Otsu Thresholding

Abstract

Bacteria play a significant role in our environment by being helpful or harmful; hence, it is crucial to identify the various bacterial species. The microscopic image captured by camera with microscope is not reliable due to the poor quality of image, making bacterial counting a difficult and time-consuming task. This paper proposes improved and enhanced Multi-Scale Retinex with Chromacity Preservation and Otsu Thresholding techniques for increasing the quality of images of bacterial cells for segmentation and contrast enhancement. A combinative procedure of image enhancement and segmentation is illustrated in this paper. The parameters for Image Quality Assessment (IQA) used are Enhancement Measure Estimation and Standard Deviation of the upgraded images. The proposed approach gives better segmentation results, as proven by the incremental changes in the IQA parameters.