PBIR: perception-based image retrieval-a system that can quickly capture subjective image query concepts.
Edward Y. ChangKwang-Ting ChengWei-Cheng LaiChing-Tung WuChengwei ChangYi-Leh WuPublished in: ACM Multimedia (2001)
Keyphrases
- image retrieval
- image similarity
- relevance feedback
- object retrieval
- target images
- image features
- image content
- image data
- input image
- visual concepts
- similarity matching
- single image
- million images
- high resolution
- image classification
- retrieving images
- response time
- multiscale
- image database
- edge detection
- retrieval method
- human perception
- query processing
- database
- similarity measure
- low level image features
- retrieved images
- street view
- visual perception
- web images
- web image search
- segmentation method
- keywords
- query expansion
- image search
- image set
- image collections
- test images
- image matching
- textual descriptions
- image regions
- semantic gap
- image representation
- feature points
- image quality
- information retrieval systems
- low level
- object recognition