Improving Query Effectiveness for Large Image Databases with Multiple Visual Feature Combination
Conference Proceeding Article
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.
Multiple database, Probabilistic approach, Neural network, Distortion, Human, Classification, Texture, Multimedia, Indexing, Visual databases, Distributed database, Multiple image, Image databank, Database query
Databases and Information Systems | Numerical Analysis and Scientific Computing
Data Management and Analytics
9th International Conference on Database Systems for Advanced Applications (DASFAA '04)
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). Research Collection School Of Information Systems.
Available at: http://ink.library.smu.edu.sg/sis_research/1238