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：2017
卷号：5
期号：4
页码：7627
DOI：10.15680/IJIRCCE.2017.05040200
出版社：S&S Publications
摘要：Color Image Segmentation separates the image into distinct regions of similar pixels based on pixelproperty. It is the high level image description in terms of objects, scenes, and features. The success of image analysisdepends on segmentation reliability. This article presents a novel approach for color image segmentation using twodifferent algorithms with respect to color features. Here presented an adaptive masking method based on fuzzymembership functions and a thresholding mechanism over each color channel to overcome over segmentation problem,before combining the segmentation from each channel into the final one. Our proposed method ensures accuracy andquality of different kinds of color images. Consequently, the proposed modified fuzzy approach can enhance the imagesegmentation performance by use of its membership functions. Similarly, it is worth noticing that our proposedapproach is faster than many other segmentation algorithms, which makes it appropriate for real-time application.According to the visual and quantitative verification, the proposed algorithm is performing better than existingalgorithms.
关键词：Color Segmentation; Fuzzy Membership Functions; Edge Detection; Region Growing
