Multilayer Dynamic Link Networks for Establishing Image Point Correspondences and Visual Object Recognition

by Rolf P. Würtz

Abstract

The major tasks for automatic object recognition are segmentation of the image and solving the correspondence problem, i.e. reliably finding the points in the image that belong to points in a given model. Once these correspondences are found, the local similarities can be used to assign one model out of a set of known ones to the image.

This work defines a suitable representation for models and images based on a multiresolution transform with Gabor wavelets.The properties of such transforms are discussed in detail.

Then a neural network with dynamic links and short-term activity correlations is presented that estimates these correspondences in several layers coarse-to-fine. It is formalized into a nonlinear dynamical system. Simulations show its capabilities that extend earlier systems by background invariance and faster convergence.

Finally, the central procedures of the network are put into an algorithmic form, which allows fast implementation on conventional hardware and uses the correspondences for the successful recognition of human faces out of a gallery of 83 independent of their hairstyle. This demonstrates the potential for the recognition of objects independently of the background, which was not possible with earlier systems.

Keywords

Neural network, dynamic link architecture, correspondence problem, object recognition, face recognition, coarse-to-fine strategy, wavelet transform, image representation


Abstract..........................................1

Preface...........................................3

Acknowledgements..................................5

Contents..........................................7

1. Introduction..................................13

2. Wavelet Preprocessing.........................25

3. Representation of Images and Models...........49

4. Hierarchical Dynamic Link Matching............65

5. Algorithmic Pyramid Matching..................89

6. Hierarchical Object Recognition..............109

7. Discussion...................................119

8. Bibliography.................................127

9. Anhang in deutscher Sprache..................141

Index...........................................153

Hardcopies available

The book is no longer available from the publisher. If find that you can not use the Postscript file (or if you are a hardcore bibliophile) email me at rolf.wuertz@neuroinformatik.ruhr-uni-bochum.de.

Like to look at the Postscript file?

If you wish to get the whole document (1.6MB compressed postscript), then click here.

This document is being maintained by Rolf P. Würtz, rolf.wuertz@neuroinformatik.ruhr-uni-bochum.de

Last modification on: 2007-03-01