A Time Efficient Clustering Algorithm for Gray Scale Image Segmentation

A Time Efficient Clustering Algorithm for Gray Scale Image Segmentation

Nihar Ranjan Nayak, Bikram Keshari Mishra, Amiya Kumar Rath, Sagarika Swain
Copyright: © 2013 |Pages: 11
DOI: 10.4018/ijcvip.2013010102
(Individual Articles)
No Current Special Offers


The goal of image segmentation is to assign every image pixels into their respective sections that share a common visual characteristic. In this paper, the authors have evaluated the performances of three different clustering algorithms – the classical K-Means, a modified Watershed segmentation as proposed by A. R. Kavitha et al., (2010) and their proposed Improved Clustering method normally used for gray scale image segmentation. The authors have analyzed the performance measure which affects the result of gray scale segmentation by considering three very important quality measures that is – Structural Content (SC) and Root Mean Square Error (RMSE) and Peak Signal to Noise Ratio (PSNR) as suggested by Jaskirat et al., (2012). Experimental result shows that, the proposed method gives remarkable consequence for the computed values of SC, RMSE and PSNR as compared to K-Means and modified Watershed segmentation. In addition to this, the end result of segmentation by means of the Proposed technique reduces the computational time as compared to the other two approaches irrespective of any input images.
Article Preview

Performance Measures

Determining the fineness of segmentation results, minimizing the noise factor present in the segmented image and performing the segmentation in a least amount of time are some of the factors that affect the outcome of segmentation. In this section, we discuss briefly the following quality measures we have used in our work that affect the performance of gray scale image segmentation using clustering approach.

Structural Content (SC)

The value of SC (Jaskirat et al., 2012) to a great extent influences the quality of a segmented image. SC measure is given by:

where in(i, j) is the input image and seg(i, j) is the target segmented image and m & n are image matrix rows and columns respectively.

A smaller value of SC means that the image is of better quality.

Root Mean Square Error (RMSE)

Generally speaking, RMSE (Jaskirat et al., 2012) gives the difference between the values predicted by a model and the values actually present in that model. In term of image processing, it corresponds to the amount of deviation present in the output segmented image as compared to that in the original input image. RMSE measure is given by:


A smaller value calculated for RMSE means that the image is of good quality.

Complete Article List

Search this Journal:
Volume 13: 1 Issue (2023): Forthcoming, Available for Pre-Order
Volume 12: 4 Issues (2022): 1 Released, 3 Forthcoming
Volume 11: 4 Issues (2021)
Volume 10: 4 Issues (2020)
Volume 9: 4 Issues (2019)
Volume 8: 4 Issues (2018)
Volume 7: 4 Issues (2017)
Volume 6: 2 Issues (2016)
Volume 5: 2 Issues (2015)
Volume 4: 2 Issues (2014)
Volume 3: 4 Issues (2013)
Volume 2: 4 Issues (2012)
Volume 1: 4 Issues (2011)
View Complete Journal Contents Listing