|
Huge multimedia databases are getting generated on Internet. We, as individuals, also have private and public collections of images and videos. Browsing and searching these collections in an effective and intuitive manner, is becoming extremely important. Lack of approximate methods for processing multimedia data in webscale systems, has forced researchers to focus on efficient and effective solutions for indexing and retrieval in multimedia databases.
We have explored a number of related issues including (i) capturing and representing visual information (ii) data structures and database related issues (iii) scalability and algorithmic issues. (iv) incorporation of semantics in retrieval (iv) solutions for domain specific multimedia databases. Our solutions have been extensively tested and demonstrated on videos and images from broadcast videos, movies and Internet collections.
Specific activities in this area include:
* Large Scale Image and Video Retrieval
* Object and Scene Classification for Retrieval
* Learning in Retrieval and Recognition
* Modelling Semantics in Enhancing Retrieval Performance
* Document Databases.
* Efficiency and Scalability in Retrieval Systems.
Related Papers:
* Pradhee Tandon and C.V. Jawahar "A Bayesian Approach to Hybrid Image Retrieval" in Proceedings of Third International Confernece on Pattern Recognition and Machine Intelligence (PReMI'09), Dec 16-20, 2009, IIT Delhi.
* Pradhee Tandon, Piyush Nigam, Vikram Pudi, C. V. Jawahar "FISH: A Practical System for Fast Interactive Image Search in Huge Databases" in Proceedings of 7th ACM International Conference on Image and Video Retrieval (CIVR '08), July 7-9, 2008, Niagara Falls, Canada
* Shashank J, Kowshik P, Kannan Srinathan and C.V. Jawahar "Private Content Based Image Retrieval" in Proceedings of IEEE computer society conference on Computer Vision and Pattern Recognition (CVPR) 2008, Egan Convention Center, Anchorage, Alaska, June 24-26, 2008.
* Pramod Sankar K and C.V. Jawahar "Probabilistic Reverse Annotation for Large Scale Image Retrieval" in Proc of IEEE Computer Society Conference on Computer Vision and Pattern Recognition,Minneapolis, Minnesona, 18-23 June, 2007.
Related Thesis:
* A Study of Graph Based Techniques for Selected Computer Vision Tasks
Praveen Dasigi, Year of Completion : 2009
* Learning in Large Scale Image Retrieval Systems
Pradhee Tandon, Year of Completion : 2009
* Efficient Image Retrieval Methods For Large Scale Dynamic Image Databases
Suman Karthik, Year of Completion : 2009
Faculty
- C V Jawahar
- P J Narayanan
(Head)
|