Image Classification And Segmentation on Complicated Colonies

Abstract

This paper presents a methodology for colony image classification and segmentation. For the delineation of both colonies and plaques, there are a large number of applications. The main problem is how to delineate complicated colonies. To avoid the problem, it is usual that the existing systems are semi-automatic systems. In this study, we used two blocks to accomplish the complicated colony delineation. The one is image classification, and the other is image segmentation. In order to speed up the image segmentation process of the large images, we classify the images first by using a low resolution image, then, segment them by a fast segmentation algorithm. The algorithm is studied mainly based on multi-resolution technique and the fusion of edge detection result and similarity segmentation result. By use this methodology, the whole image segmentation process time is reduced by tens' times than traditional segmentation methods. And the accuracy of the image segmentation is not decreased