SVM-based Harris corner detection for breast mammogram image normal/abnormal classification

Authors:
Hyun I. Kim;Sung Shin;Wei Wang;Soon I. Jeon
Affiliations:
South Dakota State University, Brookings, SD;South Dakota State University, Brookings, SD;South Dakota State University, Brookings, SD;Telecommunications Research Institute (ETRI), DaeJeon, South Korea
Venue:
Proceedings of the 2013 Research in Adaptive and Convergent Systems
Year:
2013

Citing 10
Cited 0

Geometry from visual motion

Active vision
The nature of statistical learning theory

The nature of statistical learning theory
Information Retrieval

Information Retrieval
A Tutorial on Support Vector Machines for Pattern Recognition

Data Mining and Knowledge Discovery
Approaches for automated detection and classification of masses in mammograms

Pattern Recognition
Agglomerated feature extractionin medical images for breast cancer and its characteristic pattern generation

Proceedings of the 2011 ACM Symposium on Research in Applied Computation
Image matching by multiscale oriented corner correlation

ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part I
Fuzzy support vector machines

IEEE Transactions on Neural Networks
A new histogram-based breast cancer image classifier using Gaussian mixture model

Proceedings of the 2012 ACM Research in Applied Computation Symposium
A new Fourier-based approach to measure irregularity of breast masses in mammograms

Proceedings of the 2012 ACM Research in Applied Computation Symposium

Quantified Score

Hi-index	0.00

Visualization

Abstract

The breast mammogram image is one of the most important materials of the Computer-Aided Diagnosis (CAD) system to support diagnosis of breast cancer. In the CAD system, intensity value is a widely used feature for medical image processing. In this paper, we propose develop improved Harris Corner Detection with improved input training data set for Support Vector Machine (SVM) to classify a breast mammogram image as normal or abnormal. In the proposed approach, corner pixels from improved Harris Corner Detection are used as a training input feature for SVM. The results demonstrate that the proposed approach can significantly improve both the accuracy and the performance of computational speed to classify the breast mammogram image as normal or abnormal, when compared with the data set from traditional methods.