Open AccessAn Effective Texture Features Based Mammogram Mass Detection System
Author(s) -
Kavirayani R. Prasad,
T. Suneetha Rani,
S. Shanawaz Basha
Publication year - 2018
Publication title -
international journal of engineering and technology
Language(s) - English
Resource type - Journals
ISSN - 2227-524X
DOI - 10.14419/ijet.v7i3.12.16437
Subject(s) - computer science , artificial intelligence , feature (linguistics) , identification (biology) , mammography , pattern recognition (psychology) , computer vision , field (mathematics) , feature selection , texture (cosmology) , point (geometry) , breast cancer , cancer , medicine , mathematics , image (mathematics) , philosophy , linguistics , botany , pure mathematics , biology , geometry
The identification of Mammogram is a very complicated application in Bio-medical field, it has complicated tissues. Nowadays breast cancer test, Bio-medical field often miss approximately 10% - 30% of tumors because of the ambiguous margins of lesions and visual weakness ensuing from long-time identification. For these reasons, numerous computer-aided recognition systems have been residential to aid Bio-medical in detecting mammographic lesions which may point out the existence of breast cancerthis revision presents a repeated Computer detection system that uses limited and isolated quality features for mammographic mass recognition. And system segments some adaptive square regions of interest (ROIs) for apprehensive areas. This revise also proposes two tricky feature withdrawal methods based on co-occurrence environment and visual compactness alteration to illustrate restricted quality uniqueness and the isolated photometric allocation of each ROI. As a final point, this revision uses stepwise linear discriminate examination to grade typical regions by selecting and evaluating the entity presentation of each feature. Consequences demonstrate that the projected system achievesacceptable recognition concert.