Title

Learning affine transformations

Authors

Authors

G. Bebis; M. Georgiopoulos; N. D. Lobo;M. Shah

Comments

Authors: contact us about adding a copy of your work at STARS@ucf.edu

Abbreviated Journal Title

Pattern Recognit.

Keywords

object recognition; artificial neural networks; ALGEBRAIC-FUNCTIONS; RECOGNITION; REPRESENTATION; Computer Science, Artificial Intelligence; Engineering, Electrical &; Electronic

Abstract

Under the assumption of weak perspective, two views of the same planar object are related through an affine transformation. In this paper, we consider the problem of training a simple neural network to learn to predict the parameters of the affine transformation. Although the proposed scheme has similarities with other neural network schemes, its practical advantages are more profound. First of all, the views used to train the neural network are not obtained by taking pictures of the object from different viewpoints. Instead, the training views are obtained by sampling the space of affine transformed views of the object. This space is constructed using a single view of the object. Fundamental to this procedure is a methodology, based on singular-value decomposition (SVD) and interval arithmetic (IA), for estimating the ranges of values that the parameters of affine transformation can assume. Second, the accuracy of the proposed scheme is very close to that of a traditional least squares approach with slightly better space and time requirements. A front-end stage to the neural network, based on principal components analysis (PCA), shows to increase its noise tolerance dramatically and also to guides us in deciding how many training views are necessary in order for the network to learn a good, noise tolerant, mapping. The proposed approach has been tested using both artificial and real data. (C) 1999 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.

Journal Title

Pattern Recognition

Volume

32

Issue/Number

10

Publication Date

1-1-1999

Document Type

Article

Language

English

First Page

1783

Last Page

1799

WOS Identifier

WOS:000081589800008

ISSN

0031-3203

Share

COinS