ISSN: 2277-9655
[Joby Titus et al., 6(6): June, 2017] Impact Factor: 4.116
IC™ Value: 3.00 CODEN: IJESS7
http: // www.ijesrt.com © International Journal of Engineering Sciences & Research Technology
[66]
IJESRT
INTERNATIONAL JOURNAL OF ENGINEERING SCIENCES & RESEARCH
TECHNOLOGY
ANALYSIS OF IMAGE SEGMENTATION TECHNIQUES FOR TEXTURE
FEATURE EXTRACTION
G.Ravindran
1
, T.Joby Titus
2*
, V.Ganesh
3
, V.S.Sanjana Devi
4
1,2,3
Assistant Professor(Sr.Grade), Department of Electronics and Communication Engineering,
Sri Ramakrishna Institute of Technology, Coimbatore-641010, India.
4
Assistant Professor, Department of Electrical and Electronics Engineering,
Sri krishna College of Technology, Coimbatore-641010, India.
DOI: 10.5281/zenodo.802824
ABSTRACT
The pixels of an image are grouped into several regions for segmentation. In segmentation technique the texture
feature parameter is an image analysis technique in the field of Computer vision. In the Segmentation field,
there are many techniques are used to segment the images .The proposed approach is to analyze and compare
the gray level texture feature techniques, number of clusters, Fuzzy C means, and to find which algorithmic
approach provides better results in image segmentation.
KEYWORDS: Feature Extraction, Fuzzy C Means, K means, Watershed segmentation.
INTRODUCTION
Texture image consists of integration objects within a single image. In Figure 1 a variety of texture images are
represented . Despite the large variation in image pattern, humans can easily predict them for segmentation. In
Figure 2, human vision is difficult to interpret the variation in image. To Segment the images, we consider
several factors such as similarity of patterns, proximity and continuity in pattern, parallelism, closure and
familiarity and these factors are used as base parameter for image analysis technique. The clustering in computer
vision is called Segmentation in which an image is sub divided into different regions. To analyze a parameter
using image processing an image segmentation leads to a difficult task [1],[2].
(a) (b) (c)
(d) (e) (f)
Fig.1: Challenging Images for segmentation