상세정보
학술대회
SVM-Based Harris Corner Detection for Breast Mammogram Image Normal/Abnormal Classification
- 저자
- Hyun I. Kim, Sung Shin, Wei Wang, 전순익
- 발행일
- 201310
- 출처
- Research in Adaptive and Convergent Systems (RACS) 2013, pp.187-191
- 협약과제
- 13PR2600, 전자파 이용 조기진단 고정밀 MT 시스템 개발, 전순익
- 초록
- 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. © 2013 ACM.
- KSP 제안 키워드
- Breast Cancer(BC), CAD system, Computational Speed, Data sets, Harris corner Detection, Mammogram Images, Medical Image Processing, Support VectorMachine(SVM), Support diagnosis, Traditional methods, computer-aided diagnosis(CAD)