|
Perceptually-relevant Retrieval of Figurative Images
In this collaborative project we aim to invent and develop new techniques
for the retrieval of figurative images (such as clip art, logos, signs) from
large databases. Our techniques will be based on the extraction and matching
of perceptually relevant shape features, thereby overcoming many of the
limitations of existing methods.
This project will develop new algorithms and systems for:
- Perceptual segmentation of raw images, and grouping of shape elements.
(Responsible partner: University of York.)
- Matching of geometrical patterns representing shape features.
(Responsible partner: Free University Berlin.)
- Indexing shape features in huge databases of figurative images.
(Responsible partner: Utrecht University.)
- Indexing the relative spatial layout of shape features within these
images. (Responsible partner: Utrecht University.)
- Experimentally verification in a prototype system, and performing
rigorous evaluations on databases with an independently validated ground
truth. (Responsible partner: Aktor Knowledge Technology.)
The Profi project is funded by the European Commission FP6 research program,
meeting the objectives of the Future and Emerging Technologies programme:
- The proposed research is inherently innovative, high-risk and
long-term.
- It is embryonic research, showing proof-of concept.
- It holds out the promise of major advances at a foundational level.
For more information see the project description
[html]
[pdf]
or contact the coordinator:
Remco Veltkamp,
Utrecht Universtiy |