期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2018
卷号：6
期号：10
页码：8195-8202
DOI：10.15680/IJIRCCE.2018. 0610040
出版社：S&S Publications
摘要：Image processing is a method to perform some operations on an image, in order to get an enhanced
image or to extract some useful information from it. The techniques that are used to find the objects of interest are
usually referred to as segmentation techniques. Segmentation partitions an image into distinct regions containing each
pixel with similar attributes. To be meaningful and useful for image processing and interpretation, the regions should
strongly relate to depicted objects or features of interest. There is no universally applicable segmentation technique that
will work for all images and no segmentation technique is perfect. Problem is how to choose the color representation
for segmentation. Each color representation has its advantages and disadvantages. There are two critical issues for color
image segmentation, 1. What segmentation method should be utilized and 2. What color space should be adopted?
Most of color image segmentation methods are generally extended from monochrome segmentation approaches. In this
paper, I want to present a review of the state of the art color image segmentation methods along with different color
spaces. Different image segmentation methods I would like to use are SLIC, Felzenswalb, Quick Shift, Watershed and
Normalized Cut. Whereas some color spaces used are l*a*b*, YCbCr, HSV. Executed the considered segmentation
techniques along with different color spaces, and have traced the best combinations of segmentation and color space.
关键词：Segmentation; Color Space; RGB; Lab; YCbCr; HSV
