A three-level architecture for bridging the image semantic gap.
Mohammed BelkhatirPublished in: Multim. Syst. (2011)
Keyphrases
- semantic gap
- image content
- low level
- low level features
- video retrieval
- image data
- semantic information
- visual content
- image features
- semantic concepts
- visual features
- image representation
- multiscale
- image classification
- image retrieval
- higher level
- image annotation
- low level visual features
- image analysis
- image collections
- multi modal
- image regions
- high level semantics
- image segmentation
- low level features and high level
- active learning
- object recognition
- similarity measure
- high level