Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Illumination normalization for face recognition

A comparative study of conventional vs. perception-inspired algorithms
Beleuchtungsnormierung für Gesichtserkennung: Eine Vergleichsstudie von konventionellen gegenüber wahrnehmungsinspirierten Algorithmen.
 
: Dunker, P.; Keller, M.

Encarnacao, P. ; Institute for Systems and Technologies of Information, Control and Communication -INSTICC-, Setubal; University of Madeira:
First International Conference on Bio-inspired Systems and Signal Processing 2008. Proceedings. Vol.2 : Funchal, Madeira, Portugal, January 28 - 31, 2008. Part of BIOSTEC - International Joint Conference on Biomedical Engineering Systems and Technologies
Setúbal: INSTICC Press, 2008
ISBN: 978-989-811118-0
ISBN: 978-989-8111-18-0
pp.237-243
International Conference on Bio-inspired Systems and Signal Processing (Biosignals) <1, 2008, Funchal>
International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC) <2008, Funchal>
English
Conference Paper
Fraunhofer IDMT ()
Algorithmus; Signalverarbeitung; Klassifikation; Diffusionsfilter; Gesicht; Bilderkennung; Vergleichsuntersuchung; Taxonomie

Abstract
Face recognition has been actively investigated by the scientific community and has already taken its place in modern consumer software. However, there are still major challenges remaining e.g. preventing negative influence from varying illumination, even with well known face recognition systems. To reduce the performance drop off caused by illumination, normalization methods can be applied as pre-processing step. Well known approaches are linear regression or local operations. In this publication the authors present the results of a two-step evaluation for real-world applications of a wide range of state-of-the-art illumination normalization algorithms. Further they present a new taxonomy of these methods and depict advanced algorithms motivated by the pre-eminent human abilities of illumination normalization. Additionally they introduce a recent bio-inspired algorithm based on diffusion filters that outperforms most of the known algorithms. Finally they deduce the theoretical potentials and practical applicability of the normalization methods from the evaluation results.

: http://publica.fraunhofer.de/documents/N-110406.html