A Novel Content Based Medical Image Retrieval using SURF Features

Abstract

Objective: Content Based Image Retrieval (CBIR) has been one of the most vivid research areas in the field of computer vision over the last 10 years. In the medical field, images especially digital images are produced in ever-increasing quantities and used for diagnostics and therapy. Content Based Medical Image Retrieval is an important tool for doctors in their daily activity. Findings: This work describes a method for medical images annotation based on the SURF (Speeded up Robust Features) features. The proposed technique effectively uses most of the information from image is backbone of an efficient Content Based Image Retrieval system for medical databases. In this work the SURF features are used to improve the retrieval accuracy. Methods: The method applies the SURF algorithm in the detection, description, extracting references images and matching feature points in the image respectively. In the process of feature point matching, the false matching points are eliminated through this algorithm. Applications: SURF is fast and robust interest point detector which is used in many computer vision applications. The experimental evaluation is carried out for lung images using SURF features and proposed method provides better outcome.