Evaluation of Object Based Video Retrieval Using SIFT
Shradha Gupta1, Neetesh Gupta2, Shiv Kumar3
1Shradha Gupta, Information Technology, RGPV TIT, Bhopal, India.
2Prof. Neetesh Gupta, Head & Professor, Department of Information Technology, RGPV TIT, Bhopal, India.
3Prof. Shiv Kumar, Professor, Department of Information Technology, RGPV TIT, Bhopal, India.
Manuscript received on April 08, 2011. | Revised Manuscript received on April 22, 2011. | Manuscript published on May 05, 2011. | PP: 1-6 | Volume-1 Issue-2, May 2011. | Retrieval Number: A019031111
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In Video Retrieval system, each video that is stored in the database has its features extracted and compared to the features of the query image. The local invariant features are obtained for all frames in a sequence and tracked throughout the shot to extract stable features. Proposed work is to retrieve video from the database by giving query as an object. Video is firstly converted into frames, these frames are then segmented and an object is separated from the image. Then features are extracted from object image by using SIFT features. Features of the video database obtained by the segmentation and feature extraction using SIFT feature are matched by Nearest Neighbor Search (NNS). In this paper we have evaluated the proposed video retrieval system. The proposed method is better than previous video retrieval methods because it is invariant to illumination changes.
Keywords: Video retrieval, segmentation, SIFT, Nearest-neighbor search.