An Efficient Features Extraction of Bone Fracture Detection Using SVM

Abstract

The main problem in human beings is Bone Fracture. The main reason behind this pain is due to high pressure applied on the bone. It occurs not only because of high pressure but also because of osteoporosis and bone cancer. Hence for bone fracture an accurate diagnosis is very important. In this paper the design of efficient features extraction of bone fraction detection using SVM is implemented.  This will analyze the fracture in effective way. The main theme of this project is to develop an image processing efficiently for a quick and accurate classification of bone fractures based on the given information which we got from the x-ray / CT images. We get the Images of the fractured bone are from hospital. Total number of features are extracted using the SIFT Watershed transform based on gradient and homotopy modification to segment X-ray fracture images. Then the features consisted of region number, region area, region centroid and protuberant polygon of fracture image are extracted by marker processing and region props function. Finally this can be performed very accurately with effective output.