Please use this identifier to cite or link to this item: http://ktisis.cut.ac.cy/handle/10488/246
Title: Non-linear point distribution modelling using a multi-layer perceptron
Authors: Sozou, Peter D.
Cootes, Timothy F.
Taylor, Chris J.
Di Mauro, E. C.
Lanitis, Andreas 
Keywords: Point distribution modelling
Multi-layer perceptron
Shape variation
Issue Date: 1997
Publisher: ELsevier B. V.
Source: Image and Vision Computing,Vol. 15, no. 6, 1997, pp. 457-463
Abstract: Objects of the same class sometimes exhibit variation in shape. This shape variation has previously been modelled by means of point distribution models (PDMs) in which there is a linear relationship between a set of shape parameters and the positions of points on the shape. A polynomial regression generalization of PDMs, which succeeds in capturing certain forms of non-linear shape variability, has also been described. Here we present a new form of PDM, which uses a multi-layer perceptron to carry out non-linear principal component analysis. We compare the performance of the new model with that of the existing models on two classes of variable shape: one exhibits bending, and the other exhibits complete rotation. The linear PDM fails on both classes of shape; the polynomial regression model succeeds for the first class of shapes but fails for the second; the new multi-layer perceptron model performs well for both classes of shape. The new model is the most general formulation for PDMs which has been proposed to date.
URI: http://ktisis.cut.ac.cy/handle/10488/246
ISSN: 0262-8856
DOI: 10.1016/S0262-8856(96)00001-7
Rights: Copyright © 1997 Published by Elsevier Science B.V.
Appears in Collections:Άρθρα/Articles

Show full item record

WEB OF SCIENCETM
Citations 20

4
checked on Dec 22, 2016

Page view(s) 20

4
checked on Jan 23, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.