Axiom - A Modular Visual Object Retrieval System
KI '02 Proceedings of the 25th Annual German Conference on AI: Advances in Artificial Intelligence
Concept-Based Browsing in Video Libraries
ADL '99 Proceedings of the IEEE Forum on Research and Technology Advances in Digital Libraries
Content-based 3D Neuroradiologic Image Retrieval: Preliminary Results
CAIVD '98 Proceedings of the 1998 International Workshop on Content-Based Access of Image and Video Databases (CAIVD '98)
MPEG-7 visual shape descriptors
IEEE Transactions on Circuits and Systems for Video Technology
Hi-index | 0.00 |
In visual object retrieval, there are always queries which cannot be processed successfully. In these cases, it is desirable to extract imprecise symbolic information. We present an architecture that extracts symbolic descriptors of the objects shown in the query image. The method is based on a combination of numeric feature extraction and classification. We describe some examples of descriptors and present first experimental results.