Abstract
|
Due to tremendous technological advancements, need of image information systems has became an important issue, since visual media requires large amounts of memory and computing power for processing and storage, there is a need to efficiently index and retrieve visual information from image database. In recent years, the digital document image has become an important means of enhancing information management. Content-Based Image Retrieval (CBIR) is a challenging task which retrieves the similar images from the large database. Most of the CBIR system uses the low-level features such as color, texture and shape to extract the features from the images. In so many works available, interest points are used to extract the similar images with different view and accuracy. In this paper, the same is tried to retrieve with the use of SURF and fed into Support Vector Machine (SVM) for further classification. SURF is fast and robust interest points detector which is used in many computer vision applications and other methodologies available for the same have been discussed, followed by an experimental simulation and evaluation over a set of test images in MATLAB simulation environment
|