CONTENT BASED IMAGE RETRIEVAL FOR MRI BRAIN IMAGES USING SVM CLASSIFIER

E. Sandhiya¹, Mr. G. Raghuraman^2
1Master of Computer Science and Engineering Department of Computer Science and Engineering SSN College of Engineering,Chennai, India.
²Assistant Professor Department of Computer Science and Engineering SSN College Engineering,Chennai, India.

     Content-based image retrieval might help the radiologists throughout medical diagnosis involving human brain tumor by simply searching and retrieving the similar images through a medical image repository. It makes use of image features, such as color, shape and texture, to index images with minimal human intervention. Among many retrieval features associated with CBIR, texture retrieval is one of the most powerful. As a way to tackle this concern , proposed a new method for medical image retrieval using a supervised classifier which concentrates on extracted features. We have obtained the texture based features such as GLCM (Gray Level Co-occurrence Matrix) of MRI images that contains information about the position of pixels having similar gray level values. SVM classifier is performed to classify the affected images into two categories such as normal and abnormal. The query image is classified by the classifier to a particular class and the relevant images are retrieved from the database. This will help the physician or radiologist to perform the diagnosis in a faster and non invasive way and help to increase the response time and also gives the accuracy of retrieval results.