Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.14279/1952
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 
metadata.dc.contributor.other: Λανίτης, Ανδρέας
Major Field of Science: Social Sciences
Keywords: Point distribution modelling;Multi-layer perceptron;Shape variation
Issue Date: Jun-1997
Source: Image and Vision Computing,1997, vol. 15, no. 6, pp. 457-463
Volume: 15
Issue: 6
Start page: 457
End page: 463
Journal: Image and Vision Computing 
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: https://hdl.handle.net/20.500.14279/1952
ISSN: 02628856
DOI: 10.1016/S0262-8856(96)00001-7
Rights: © Elsevier
Type: Article
Affiliation : University College London 
The University of Manchester 
Cyprus College 
Appears in Collections:Άρθρα/Articles

CORE Recommender
Sorry the service is unavailable at the moment. Please try again later.
Show full item record

SCOPUSTM   
Citations

12
checked on Mar 21, 2021

WEB OF SCIENCETM
Citations

10
Last Week
0
Last month
0
checked on Oct 29, 2023

Page view(s)

506
Last Week
0
Last month
1
checked on Jan 30, 2025

Google ScholarTM

Check

Altmetric


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