Publication

Abstract : The aim of this work is to classify images related to social events. With advances in digital image processing, automated classification of event related images over large categories of dataset is possible only if the name of the event is known. The purpose of the paper is to identify different events in a given set of images with the help of visual content. We compare the performance of Global (GIST) as well as Local Descriptors (SIFT) which is helpful in achieving this classification and retrieval of images. The performances of both the approaches are assessed. © Research India Publications.