Name
Abstract | ||
|---|---|---|
In this letter we present a fully automatic and computationally efficient algorithmbased on the Minimum Description Length Principle (MDL) for optimizing multilayer perceptronclassifiers. We demonstrate our method on the problem of multispectral Landsatimage classification. We compare our results with a hand designed multi-layer perceptronand a Gaussian maximum likelihood classifier where our method produces betterclassification accuracy with a smaller number of hidden units.1... |
Year | DOI | Venue |
|---|---|---|
1998 | 10.1109/36.655348 | IEEE T. Geoscience and Remote Sensing |
Keywords | Field | DocType |
geophysical signal processing,geophysical techniques,geophysics computing,image classification,multilayer perceptrons,optimisation,remote sensing,accuracy,classifier,computationally efficient algorithm,geophysical measurement technique,image classification,land surface,land use,minimum description length,multidimensional image processing,multilayer perceptron,multispectral Landsat image,multispectral remote sensing,neural net,optimal neural network,optimization,terrain mapping | Computer vision,Remote sensing,Minimum description length,Multispectral image,Gaussian,Multilayer perceptron,Artificial intelligence,Multispectral pattern recognition,Classifier (linguistics),Artificial neural network,Contextual image classification,Mathematics | Journal |
Volume | Issue | ISSN |
36 | 1 | 0196-2892 |
Citations | PageRank | References |
11 | 2.20 | 10 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Horst Bischof | 1 | 8751 | 541.43 |
| Ales Leonardis | 2 | 1636 | 147.33 |