Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.14279/29346
Title: | A general non-linear method for modelling shape and locating image objects | Authors: | Lanitis, Andreas Sozou, Peter D. Taylor, Chris J. Cootes, Timothy F. Di Mauro, E. C. |
Major Field of Science: | Engineering and Technology;Social Sciences | Field Category: | Computer and Information Sciences;SOCIAL SCIENCES;Design | Keywords: | Shape;Principal component analysis;Biomedical imaging;Deformable models;Multilayer perceptrons;Tellurium;Biophysics;Educational institutions;Ear;Face recognition | Issue Date: | 25-Aug-1996 | Source: | Proceedings of 13th International Conference on Pattern Recognition, 1996, pp. 266-270 | Start page: | 266 | End page: | 270 | Conference: | 13th International Conference on Pattern Recognition | Abstract: | Objects of the same class often 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. Here we present a new form of PDM, which uses a multilayer perceptron (MLP) to carry out nonlinear principal component analysis. We demonstrate that MLP-PDMs can model the shape variability in classes of object for which the linear model fails. We describe the use of MLP-PDMs in image search and present quantitative results for a practical application (face recognition), demonstrating the ability to locate image structures accurately starting from a very poor initial approximation to their pose and shape. © 1996 IEEE. | URI: | https://hdl.handle.net/20.500.14279/29346 | DOI: | 10.1109/ICPR.1996.547428 | Rights: | © Copyright IEEE | Type: | Conference Papers | Affiliation : | University College London The University of Manchester |
Appears in Collections: | Δημοσιεύσεις σε συνέδρια /Conference papers or poster or presentation |
CORE Recommender
SCOPUSTM
Citations
10
5
checked on Mar 14, 2024
Page view(s) 10
152
Last Week
0
0
Last month
6
6
checked on Nov 12, 2024
Google ScholarTM
Check
Altmetric
This item is licensed under a Creative Commons License