Personal tools
Laboratoire d'InfoRmatique en Image et Systèmes d'information

Skip to content. | Skip to navigation

Laboratoire d'InfoRmatique en Image et Systèmes d'information
UMR 5205 CNRS / INSA Lyon / Université Claude Bernard Lyon 1 / Université Lumière Lyon 2 / École Centrale de Lyon
You are here: Home > membres

Richard Marriott


PhD student

Team Feature Extraction and Identification
Institution École Centrale de Lyon
Location Ecully (Ecole Centrale de Lyon)
E-mail at
Contact details Publications Thesis
Subject 3D-based Lighting Normalization for Reliable 2D Face Recognition
Abstract The goal of this thesis is to explore the potential for exploiting 3D information to improve existing 2D facial recognition (FR) methods via normalisation of the effects of uneven lighting in images. Development of a solution to introduce illumination-invariance to FR systems would broaden the domain of their reliable application to environments with unconstrained lighting conditions where only monocular visual information is available, for example, video surveillance. Given a deformable 3D statistical face model as a prior, we hope to be able to infer 3D details from 2D images, including the 3D lighting information to be adjusted. To aid in the analysis of images, we look to make use of convolution neural networks and benefit from the recent advances made in the field of deep learning.
This research is being conducted in collaboration with IDEMIA, the world leader in trusted identity technologies.
Advisor Liming Chen

Last update : 2018-01-18 13:52:10