Unsupervised Image Segmentation using ROR

Main Article Content

Dr B.L. Shivakumar
B.Suresh Kumar


Image segmentation is a process of segmenting an image into groups of pixels based on some criterions. Image segmentation is the process of partitioning a digital image into multiple segments. The purpose of image segmentation is to partition an image into meaningful regions with respect to particular application. Image segmentation is typically used to locate objects and boundaries (lines, curves, etc.) in images. Previously Adaptive Fuzzy-K-Means (AFKM) clustering for image segmentation which could be applied on general images and/or specific images. The FCM segments images based on the membership value and objective function used in it. Both of these methods work well for images with vast variations in its Pixel values but fails for pixels with slight variations. In order to overcome the disadvantages of various segmentation processes a new method of unsupervised segmentation is proposed using ROR (Robust Outlyingness Ratio). The advantages of proposed method accuracy is more, time is less and the number of iterations always being one.


Keywords: Adaptive Fuzzy-K- Means (AFKM); Fuzzy- K-Means (FKM); Silhouette Measure; Unsupervised Clustering; Threshold; Inter Cluster; Intra Cluster; Tolerance Limit(TL).


Download data is not yet available.

Article Details