Welcome to the InfoSci Platform
Reference Hub2
Image Segmentation Utilizing Color-Space Feature

Image Segmentation Utilizing Color-Space Feature

Mohammad A. Al-Jarrah
Copyright: © 2015 |Volume: 6 |Issue: 1 |Pages: 15
ISSN: 1947-8534|EISSN: 1947-8542|EISBN13: 9781466677135|DOI: 10.4018/ijmdem.2015010103
Cite Article Cite Article

MLA

Al-Jarrah, Mohammad A. "Image Segmentation Utilizing Color-Space Feature." IJMDEM vol.6, no.1 2015: pp.39-53. http://doi.org/10.4018/ijmdem.2015010103

APA

Al-Jarrah, M. A. (2015). Image Segmentation Utilizing Color-Space Feature. International Journal of Multimedia Data Engineering and Management (IJMDEM), 6(1), 39-53. http://doi.org/10.4018/ijmdem.2015010103

Chicago

Al-Jarrah, Mohammad A. "Image Segmentation Utilizing Color-Space Feature," International Journal of Multimedia Data Engineering and Management (IJMDEM) 6, no.1: 39-53. http://doi.org/10.4018/ijmdem.2015010103

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

In this paper, the authors introduced a stochastic model for color images. Utilizing this model, they proposed a new method for color image segmentation. The proposed method consists of three stages; the first stage considers the red, green, and blue color component of the image as a gray image. One of the known gray image Thresholding algorithm is applied on the three color components. The second stage segments the image based on the results of first stage. This stage produces eight color segments. The third stage identifies the segments through color-space correlation. Color-space correlation algorithm assumes that a set of pixels are considered to belong to one region if and only if they belong to the same color cluster and all connected using neighborhood filters. The last stage may produce very small segments. These small segments are merged with their closed neighbors based on color features. Finally, Conducted experiments achieved perceptually accepted segments and compare favorably to other segmentation methods.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.