An Approach for Segmentation of Colored Images with Seeded Spatial Enhancement

Abstract

In the image analysis, image segmentation is the operation that divides image into set of different segments. The work deals about common color image segmentation techniques and methods. Image enhancement is done using four connected approach for seed selection of the image. An algorithm is implemented on the basis of manual seed selection. It select a seed point in an image an then check for its four neighbor pixels connected to that particular seed point. And segment that image in foreground and background framing. At the end, the evaluation criterion will be introduced and applied on the algorithms results. Five most used image segmentation algorithms, namely, efficient graph based, K means, Mean shift, Expectation maximization and hybrid method are compared with implemented algorithm.