A general non-linear method for modelling shape and locating image objects

Research output: Chapter in Book/Report/Conference proceedingConference contribution


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.

Bibliographical metadata

Original languageEnglish
Title of host publicationProceedings - International Conference on Pattern Recognition|Proc. Int. Conf. Pattern Recognit.
Number of pages4
ISBN (Print)081867282X, 9780818672828
Publication statusPublished - 1996
Event13th International Conference on Pattern Recognition, ICPR 1996 - Vienna
Event duration: 1 Jul 1996 → …


Conference13th International Conference on Pattern Recognition, ICPR 1996
Period1/07/96 → …
Internet address