by C. P. Town, D. Sinclair
http://www.uk.research.att.com/pub/docs/att/tr.2000.14.ps.gz
Add To MetaCart
Abstract:
This paper demonstrates an approach to content based image retrieval founded on the semantically meaningful labelling of images by high level visual categories. The image labelling is achieved by means of a set of trained neural network classifiers which map segmented image region descriptors onto semantic class membership terms. It is argued that the semantic terms give a good estimate of the salient features which are important for discrimination in image retrieval. Furthermore, it is shown that the choice of visual categories such as grass or sky which mirror high level human perception allows the implementation of intuitive and versatile query composition interfaces and a variety of image similarity metrics for content based retrieval.
Citations
|
3052
|
Neural Networks for Pattern Recognition
– Bishop
- 1995
|
|
718
|
Pattern recognition and neural networks
– Ripley
- 1996
|
|
354
|
Photobook: Tools for content-based manipulation of image databases
– Pentland, Picard, et al.
- 1994
|
|
195
|
Blobworld: A system for region-based image indexing and retrieval
– Carson, Thomas, et al.
- 1999
|
|
104
|
Neural networks and related methods for classification
– Ripley
- 1994
|
|
43
|
Interpreting image databases by region classification
– Campbell, Mackeown, et al.
- 1997
|
|
11
|
Voronoi seeded colour image segmentation
– Sinclair
- 1999
|
|
9
|
Learnable visual keywords for image classification
– Lim
- 1999
|
|
5
|
The qbic project: querying images by color, texture and shape
– Niblack
- 1993
|
|
5
|
Smooth region structure: folds, domes, bowls, ridges, valleys and slopes
– Sinclair
- 2000
|
|
3
|
Primitives, perceptual organisation and object recognition
– Forsyth, Malik, et al.
- 1997
|
|
2
|
Automatic classification of objects in captioned descriptive photographs for retrieval, chapter 4
– Rowe, Frew
- 1997
|
|
1
|
Model-based classification of visual informaton for content-based retrieval
– Jaimes, Chang
- 1999
|
|
1
|
SNNS user manual, version 4.2. Technical report, Eberhard-Karls-Universitat Tubingen, WilhelmSchickard -Institut fur Informatik
– Zell, Mache, et al.
- 1998
|
