Learning from Examples to Generalize over Pose and Illumination

Authors:
Marco K. Müller;Rolf P. Würtz
Affiliations:
Institute für Neural Computation, Ruhr-University, Bochum, Germany 44780;Institute für Neural Computation, Ruhr-University, Bochum, Germany 44780
Venue:
ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part II
Year:
2009

Citing 9
Cited 1

Learning translation invariant recognition in massively parallel networks

Volume I: Parallel architectures on PARLE: Parallel Architectures and Languages Europe
Learning invariance from transformation sequences

Neural Computation
Face Recognition by Elastic Bunch Graph Matching

IEEE Transactions on Pattern Analysis and Machine Intelligence
Distortion Invariant Object Recognition in the Dynamic Link Architecture

IEEE Transactions on Computers
Slow feature analysis: unsupervised learning of invariances

Neural Computation
Rapid convergence to feature layer correspondences

Neural Computation
Head Pose Estimation in Computer Vision: A Survey

IEEE Transactions on Pattern Analysis and Machine Intelligence
The CAS-PEAL Large-Scale Chinese Face Database and Baseline Evaluations

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
Similarity rank correlation for face recognition under unenrolled pose

ICB'07 Proceedings of the 2007 international conference on Advances in Biometrics

2013 Special Issue: Learning invariant face recognition from examples

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a neural system that recognizes faces under strong variations in pose and illumination. The generalization is learnt completely on the basis of examples of a subset of persons (the model database) in frontal and rotated view and under different illuminations. Similarities in identical pose/illumination are calculated by bunch graph matching, identity is coded by similarity rank lists. A neural network based on spike timing decodes these rank lists. We show that identity decisions can be made on the basis of few spikes. Recognition results on a large database of Chinese faces show that the transformations were successfully learnt.