Color Image Segmentation using Region Growth and Merging Technique
Abstract
We propose a method of region growing and region merging used for color image segmentation. In this paper Initial seed selection is
the first stage of color image segmentation. Here we use two details; one is non-edge pixels and second is smoothness feature of the pixels. The
non-edge pixels and smoothness at pixel’s neighbor are used as criteria to determine initial seeds in the color image. Second stage is region
growing. It is used to segment the image based on seed regions. Third and last stage is region merging which is used to merge the small region.
This method is applied to many color images and experimental results show the effectiveness of the method.
Keywords: image segmentation; edge detection; smoothness; seed selection; region growing; region merging
Full Text:
PDFDOI: https://doi.org/10.26483/ijarcs.v2i2.401
Refbacks
- There are currently no refbacks.
Copyright (c) 2016 International Journal of Advanced Research in Computer Science

