Image stitching of microscopic wastewater images

Abstract

In this paper, image stitching strategy is proposed to prepare a virtual slide image of the sample of activated sludge obtained from the wastewater treatment plant. The bright-field microscopic images have inherent problem of vignetting and less contrast, which result into failed image registration by conventional methods. Our method involves illumination correction, image segmentation, image registration and finally, image stitching. First, flat-field correction method is applied to all the acquired field of views (FOVs) to balance the illumination on each FOV. In the second step, adaptive thresholding method is employed to segment all the acquired FOVs to convert into binary images. This step is meant to increase the accuracy of finding the overlapping region during image registration. Then, phase correlation is used to find the overlapping region between images in horizontal direction during image stitching for each row of the microscopy slide, and in vertical direction subsequently for image stitching between the rows. The proposed method has been compared with the state-of-the-art algorithms using subjective inspection, and no reference evaluation indices of entropy and clarity. From the evaluation, we had observed that the proposed method performs better.