CORTINA: Searching a 10 Million + Images Database

Elisa Drelie Gelasca
Pratim Ghosh
Emily Moxley
Joriz De Guzman
JieJun Xu
Zhiqiang Bi
Steffen Gauglitz
Amir M. Rahimi
B. S. Manjunath

Vision Research Lab., Electrical and Computer Engineering Department, mailto: drelie [at] ece.ucsb.edu
University of Santa Barbara, California 931069560

Abstract

We present an image search and retrieval system, Cortina, that indexes over 10 Million images using image content, text and annotations. This large collection of image data, gathered from the World Wide Web (WWW), poses significant challenges to automated image analysis, pattern recognition and database indexing. At the systems level, the components of Cortina include building image collections using a Web crawler, collecting category information and keywords, and processing images to compute content descriptors. Functionalities of Cortina include duplicate image detection, category and image content based search, face detection and relevance feedback. A MySql database is used for storing textual annotations and keywords, whereas the image features are stored in flat file structures. This combination appears to be effective and scalable for large collection of image/video data and is easily parallelizable.
[PDF] [BibTex]
Elisa Drelie Gelasca, Joriz De Guzman, Steffen Gauglitz, Pratim Ghosh, JieJun Xu, Emily Moxley, Amir M. Rahimi, Zhiqiang Bi and B. S. Manjunath,
VRL, ECE, University of California, Santa Barbara, Sep. 2007.
Node ID: 470 , DB ID: 275 , Lab: VRL , Target: Technical Report
Subject: [Managing Multimedia Databases] « Look up more