Improving Query Effectiveness for Large Image Databases with Multiple Visual Feature Combination
Publication Type
Conference Proceeding Article
Publication Date
2004
Abstract
This paper describes CMVF, a new framework for indexing multimedia data using multiple data properties combined with a neural network. The goal of this system is to allow straightforward incorporation of multiple image feature vectors, based on properties such as colour, texture and shape, into a single low-dimensioned vector that is more effective for retrieval than the larger individual feature vectors. CMVF is not constrained to visual properties, and can also incorporate human classification criteria to further strengthen image retrieval process. The analysis in this paper concentrates on CMVF's performance on images, examining how the incorporation of extra features into the indexing affects both efficiency and effectiveness, and demonstrating that CMVF's effectiveness is robust against various kinds of common image distortions and initial(random) configuration of neural network.
Keywords
Multiple database, Probabilistic approach, Neural network, Distortion, Human, Classification, Texture, Multimedia, Indexing, Visual databases, Distributed database, Multiple image, Image databank, Database query
Discipline
Databases and Information Systems | Numerical Analysis and Scientific Computing
Publication
9th International Conference on Database Systems for Advanced Applications (DASFAA '04)
Identifier
10.1007/978-3-540-24571-1_75
Publisher
Springer Verlag
Citation
SHEN, Jialie; Shepherd, John; Ngu, AHH; and Huynh, Du Q..
Improving Query Effectiveness for Large Image Databases with Multiple Visual Feature Combination. (2004). 9th International Conference on Database Systems for Advanced Applications (DASFAA '04).
Available at: https://ink.library.smu.edu.sg/sis_research/1238
Additional URL
http://www.springerlink.com/content/te12xgmkj9bttq4r/