Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

14

ICANN
2009
Springer

favoriteEmaildiscussreport

145views Neural Networks» more ICANN 2009»

Learning from Examples to Generalize over Pose and Illumination

13 years 9 months ago

Learning from Examples to Generalize over Pose and Illumination

Download ftp.neuroinformatik.rub.de

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.

Marco K. Müller, Rolf P. Würtz

Real-time Traffic

ICANN 2009 | Rank Lists | Similarity Rank Lists | Strong Variations |

claim paper

Related Content

» Learning Generalized Policies from Planning Examples Using Concept Languages

» Featureless 2D3D Pose Estimation by Minimising an IlluminationInvariant Loss

» Shape and Materials by Example A Photometric Stereo Approach

» Face Recognition from Video Using the Generic ShapeIllumination Manifold

» Building a Classification Cascade for Visual Identification from One Example

» Estimating Coloured 3D Face Models from Single Images An Example Based Approach

» Simple DFA are Polynomially Probably Exactly Learnable from Simple Examples

» Predicate Invention and Learning from Positive Examples Only

» Interactive learning of structural shape descriptions from automatically generated nearmis...

Post Info
More Details (n/a)

Added	25 Jul 2010
Updated	25 Jul 2010
Type	Conference
Year	2009
Where	ICANN
Authors	Marco K. Müller, Rolf P. Würtz

Comments (0)