Colour invariants for machine face recognition

Ognjen Arandjelovíc*, Roberto Cipolla

*Corresponding author for this work

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

4 Citations (Scopus)

Abstract

Illumination invariance remains the most researched, yet the most challenging aspect of automatic face recognition. In this paper we investigate the discriminative power of colour-based invariants in the presence of large illumination changes between training and test data, when appearance changes due to cast shadows and non-Lambertian effects are significant. Specifically, there are three main contributions: (i) we employ a more sophisticated photometric model of the camera and show how its parameters can be estimated, (ii) we derive several novel colour-based face invariants, and (iii) on a large database of video sequences we examine and evaluate the largest number of colourbased representations in the literature. Our results suggest that colour invariants do have a substantial discriminative power which may increase the robustness and accuracy of recognition from low resolution images.

Original languageEnglish
Title of host publication2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008
DOIs
Publication statusPublished - 2008
Event2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008 - Amsterdam, Netherlands
Duration: 17 Sept 200819 Sept 2008

Conference

Conference2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008
Country/TerritoryNetherlands
CityAmsterdam
Period17/09/0819/09/08

Fingerprint

Dive into the research topics of 'Colour invariants for machine face recognition'. Together they form a unique fingerprint.

Cite this