| |
|
Project: Learning Similarity Measures Using Neural Network
PEOPLE
OBJECTIVE
We have proposed a hybrid neural network algorithm for learning similarity measures in the texture feature space.
It achieves the objective of maintaining the topology while reducing the dimensionality, and groups perceptually
similar patterns into the same cluster. With Learning similarity, the performance of similar pattern retrievals
improves significantly.
EXAMPLE
The following examples show the retrieval performance before (left) and after (right) learning similarity measures.
As we can see, the retrieval results better match the human visual perception in terms of texture similarity.
|
|
Example 1:
 |
|
Note: the left block is before learning similarity measures, and the right block is after learning similarity measures |
|
Example 2: 
|
|
Example 3:
PUBLICATIONS
These materials are presented to ensure timely
dissemination of scholarly and technical work. Copyright and all rights
therein are retained by authors or by other copyright holders. All persons
copying this information are expected to adhere to the terms and
constraints invoked by each authors copyright. In most cases, these works
may not be reposted without the explicit permission of the copyright
holder.
-
W.Y.Ma and B.S.Manjunath, “Texture features
and learning similarity,”
Proc.
IEEE International Conference on Computer Vision and Pattern Recognition,
San Francisco, CA, pp. 425-430, June 1996.
back to ADL |
|
