ANNOTION TOGETHER WITH REVIVAL OF VIDEOS THROUGH THE FEATURES OF HOG AS WELL AS SHIFT

Abstract

As the amount of information uploaded in internet is increasing day by day, in order to get the required
information the huge database of information are needed to be analyzed properly. One of the widely used methods to
analyze and retrieve these huge video data is video annotation. Video annotation process requires a large amount of
processing to analyze the contents in the video as the process is complicated. This paper introduces a video annotation
and retrieval system using SIFT and HOG features, in that SIFT given for training the classifiers. The SIFT and
HOG features of the images are extracted and used for training the classifiers for doing a comparison on
performance of the classifiers. An analysis of the results is done to find which feature is better to train the classifier
for getting more prominent annotated video database. Based on objects from the annotated video database, retrieval of
the videos is also done.