Image Segmentation using Entropy: A Review
Amanjot Kaur1, Sukhwinder Bir2, Harjasdeep Singh3
1Amanjot Kaur Computer Science and Engineering, Malout Institute of Management and Information Technology, Malout, India.
2Sukhwinder Bir, Computer Science and Engineering , Beant College of Engineering and Technology, Gurdaspur, India.
3Harjasdeep Singh, Computer Science and Engineering, Malout Institute of Management and Information Technology, Malout, India.
Manuscript received on December 11, 2013. | Revised Manuscript received on December 15, 2013. | Manuscript published on December 25, 2013. | PP:7-9 | Volume-2 Issue-2, December 2013. | Retrieval Number: B0587122213/2013©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The main objective of Image Segmentation is to partition an image into different parts. Image segmentation basically used to detect the edges and boundaries. This is done to simplify and/or change the representation of an image in a more meaningful and easier way. Many image segmentation techniques are available in the literature. Some of them used gray level histograms, some used spatial and some used thresholding techniques. Under thresholding techniques there are different methods. One of those methods is entropy. Entropy is a measure of unpredictability. A good segmentation will be one that maximize the uniformity of pixels within the regions and minimize the uniformity across the regions. So we can say that entropy is a natural characteristic to be incorporated in evaluation function. This paper attempts to provide a brief review for image segmentation using entropy.
Keywords: 2D and 3D images, entropy, image segmentation, thresholding.