Use of weighted visual terms and machine learning techniques for image content recognition relying on mpeg-7 visual descriptors.
Giuseppe AmatoPasquale SavinoVanessa MagionamiPublished in: MS (2008)
Keyphrases
- visual descriptors
- visual content
- image content
- mpeg standard
- visual features
- image retrieval
- visual information
- image database
- image collections
- visual concepts
- content based retrieval
- semantic gap
- visual similarity
- image representation
- spatial relationships
- semantic content
- image annotation
- image data
- image features
- video retrieval
- visual data
- automatic image annotation
- image regions
- object recognition
- semantic concepts
- low level
- image matching
- co occurrence
- computer vision
- cbir systems
- image search
- multimedia content
- machine learning
- image classification
- multimedia databases
- keypoints
- multimedia documents
- key frames
- video sequences
- visual words