Share Email Print
cover

Proceedings Paper

Using Bayesian neural networks to classify forest scenes
Author(s): Aki Vehtari; Jukka Heikkonen; Jouko Lampinen; Jouni Juujarvi
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

We present results that compare the performance of Bayesian learning methods for neural networks on the task of classifying forest scenes into trees and background. Classification task is demanding due to the texture richness of the trees, occlusions of the forest scene objects and diverse lighting conditions under operation. This makes it difficult to determine which are optimal image features for the classification. A natural way to proceed is to extract many different types of potentially suitable features, and to evaluate their usefulness in later processing stages. One approach to cope with large number of features is to use Bayesian methods to control the model complexity. Bayesian learning uses a prior on model parameters, combines this with evidence from a training data, and the integrates over the resulting posterior to make predictions. With this method, we can use large networks and many features without fear of overfitting. For this classification task we compare two Bayesian learning methods for multi-layer perceptron (MLP) neural networks: (1) The evidence framework of MacKay uses a Gaussian approximation to the posterior weight distribution and maximizes with respect to hyperparameters. (2) In a Markov Chain Monte Carlo (MCMC) method due to Neal, the posterior distribution of the network parameters is numerically integrated using the MCMC method. As baseline classifiers for comparison we use (3) MLP early stop committee, (4) K-nearest-neighbor and (5) Classification And Regression Tree.

Paper Details

Date Published: 6 October 1998
PDF: 8 pages
Proc. SPIE 3522, Intelligent Robots and Computer Vision XVII: Algorithms, Techniques, and Active Vision, (6 October 1998); doi: 10.1117/12.325800
Show Author Affiliations
Aki Vehtari, Helsinki Univ. of Technology (Finland)
Jukka Heikkonen, Helsinki Univ. of Technology (Finland)
Jouko Lampinen, Helsinki Univ. of Technology (Finland)
Jouni Juujarvi, Helsinki Univ. of Technology (Finland)


Published in SPIE Proceedings Vol. 3522:
Intelligent Robots and Computer Vision XVII: Algorithms, Techniques, and Active Vision
David P. Casasent, Editor(s)

© SPIE. Terms of Use
Back to Top