Retrieval of articulate objects from images and video using invariant signatures.
Ronald-Bryan O. AlferezYuan-Fang WangPublished in: ICME (1) (2002)
Keyphrases
- image database
- video images
- image retrieval
- visual data
- image data
- multiple objects
- content based retrieval
- static images
- bounding box
- individual objects
- visual appearance
- complex scenes
- symbolic descriptions
- object motion
- image regions
- input image
- semantic labels
- image features
- low level image features
- invariant properties
- video data
- textual descriptions
- image classification
- cbir systems
- video retrieval
- spatial relationships
- image set
- video frames
- video sequences
- keypoints
- d objects
- image sequences
- target object
- surface properties
- test images
- raw image
- retrieval systems
- three dimensional
- video collections
- invariant descriptors
- retrieving images
- planar objects
- visual concepts
- viewing angle
- geometric transformations
- object recognition
- relevance feedback
- color histogram
- image quality
- image annotation
- video streams
- image matching
- segmentation method