On multi-view face recognition using lytro images

Chiesa, Valeria; Dugelay, Jean-Luc
EUSIPCO 2018, 26th European Signal Processing Conference, 3-7 September 2018, Rome, Italy

In this work, a simple and efficient approach for recognizing faces from light field images, notably from Lytro Illum camera, is proposed. The suggested method is based on
light field images property of being rendered through a multiview representation. In the preliminary analysis, feature vectors extracted from different views of the same Lytro picture are proved different enough to provide complementary information beneficial for face recognition purpose. Starting from a set of multiple views for each data, face verification problem is tackled and results are compared with those achieved with classical 2D images simulated using a single view, i.e. the central one. Two experiments are described and, in both cases, the presented method shows superior performances than standard algorithms adopted by classical imaging sensors.

DOI
Type:
Conference
City:
Rome
Date:
2018-09-03
Department:
Digital Security
Eurecom Ref:
5647
Copyright:
© 2018 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

PERMALINK : https://www.eurecom.fr/publication/5647