Seminar Details
| Date |
25-5-2009 |
| Time |
9:30 |
| Room/Location |
DISI-Sala conferenze 3° piano |
| Title |
Evolutionary Algorithms for Protein Ligand Docking |
| Speaker |
Prof. Ashish Ghosh |
| Affiliation |
Indian Statistical Institute, Kolkata, India |
| Link |
https://www.disi.unige.it/index.php?eventsandseminars/seminars
|
| Abstract |
In remote sensing applications, change-detection is the process of
identifying differences in the state of an object or phenomenon by analyzing
a pair of images acquired on the same geographical area at different times.
In this lecture, we will propose a few unsupervised context-sensitive
techniques for change-detection in multitemporal remote sensing images using
modified versions of Hopfield"s neural network, a modified self-organizing
feature map neural network and a multi-layer perceptron. Each spatial
position of the input image corresponds to a neuron. The network is updated
depending on some learning rule and when the network converges, status of
output neurons depict a change-detection map. Experimental results, carried
out on two multispectral and multitemporal remote sensing images, confirm
the effectiveness of the proposed approaches. The approaaches are found to
be robust and does not require any a'priori knowledge of distribution of
input images. |
|
|
 |
