Open AccessEffective Texture Features for Segmented Mammogram Images
Author(s) -
P. Anjaiah,
Kavirayani R. Prasad,
C. G. Raghavendra
Publication year - 2018
Publication title -
international journal of engineering and technology
Language(s) - English
Resource type - Journals
ISSN - 2227-524X
DOI - 10.14419/ijet.v7i3.12.16450
Subject(s) - artificial intelligence , segmentation , computer science , computer vision , region of interest , mammography , texture (cosmology) , image segmentation , region growing , pattern recognition (psychology) , image texture , breast cancer , image (mathematics) , cancer , medicine
Textures of mammogram images are useful for finding masses or cancer cases in mammography, which has been used by radiologist. Textures are greatly succeed for segmented images rather than normal images. It is necessary to perform segmentation for exclusive specification of cancer and non-cancer regions separately. Region of interest (ROI) in most commonly used technique for mammogram segmentation. Limitation of this method is that it unable to explore segmentation for large collection of mammogram images. Therefore, this paper is proposed multi-ROI segmentation for addressing the above limitation. It supports greatly for finding best texture features of mammogram images. Experimental study demonstrates the effectiveness of proposed work using benchmarked images.