Extracting Shape Features in JPEG-2000 Compressed Images
ADVIS '02 Proceedings of the Second International Conference on Advances in Information Systems
Multimodal interface for human-machine communication
Design of a two-stage content-based image retrieval system using texture similarity
Information Processing and Management: an International Journal
Image Database Design Based on 9D-SPA Representation for Spatial Relations
IEEE Transactions on Knowledge and Data Engineering
Image retrieval and perceptual similarity
ACM Transactions on Applied Perception (TAP)
Robust Visual Content Representation Using Compression Modes Driven Low-level Visual Descriptors
MMM '09 Proceedings of the 15th International Multimedia Modeling Conference on Advances in Multimedia Modeling
CIARP'05 Proceedings of the 10th Iberoamerican Congress conference on Progress in Pattern Recognition, Image Analysis and Applications
An approach to compressed image retrieval based on JPEG2000 framework
ADMA'05 Proceedings of the First international conference on Advanced Data Mining and Applications
Hi-index | 0.01 |
Data representation and content description are two basic components required by the management of any image database. A wavelet based system, called the WaveGuide, which integrates these two components in a unified framework, is proposed in this work. In the WaveGuide system, images are compressed with the state-of-the-art wavelet coding technique and indexed with color, texture, and object shape descriptors generated in the wavelet domain during the encoding process. All the content descriptors are extracted by machines automatically with a low computational complexity and stored with a low memory space. Extensive experiments are performed to demonstrate the performance of the new approach