Support Vector Machine Based Texture Feature Extraction Technique for Classification of Breast Cancer From Ultrasound Images

Abstract

Breast Cancers is such a ailment that has got excellent attention within many years. In breast cancer the breast lesion are differentiated into two instructions i.e. Benign and Malignant. Computer-Aided Detection (CAD) system is designed to resource radiologists in detecting lesions which could imply the presence of breast cancers. The ROI is extracted from the ultrasonic photos, the usage of imageJ software after which the unique photograph processing techniques are carried out i.e. preprocessing, feature extraction and feature classification using MATLAB. SVM classifier is significantly used for category. Classification of breast ultrasound images using Statistical and Transform domain feature extraction techniques were data is partitioned by hold-out method and classified using Support Vector Machine (SVM) classifier. SVM trains a model that assigns unseen new objects into a specific category. The best obtained result out of all the features used is calculated using Fourier Power Spectrum (FPS) feature.