Concept detection and keyframe extraction using a visual thesaurus
Multimedia Tools and Applications
Using visual context and region semantics for high-level concept detection
IEEE Transactions on Multimedia - Special issue on integration of context and content
| Hi-index | 0.00 |
This paper presents an approach on high-level feature detection within video documents, using a Region Thesaurus and Latent Semantic Analysis. A video shot is represented by a single keyframe. MPEG-7 features are extracted from coarse regions of it. A clustering algorithm is applied on all extracted regions and a region thesaurus is constructed. Its use is to assist to the mapping of low- to high-level features by a model vector representation. Latent Semantic Analysis is then applied on the model vectors to exploitthe latent relations among region types aiming to improvedetection performance. The proposed approach is thoroughlyexamined using TRECVID 2007 development data.