This paper focuses on designing data-driven models to learn a discriminant representation space for face recognition using RGB-D data. Unlike hand-crafted representations, learned models can extract and organize the discriminant information from the data, and can automatically adapt to build new compute vision applications faster. We proposed an effective way to train Convolutional Neural Networks to learn face patch discriminant features. The proposed solution was tested and validated on state-of-the-art RGB-D datasets and showed competitive and promising results relatively to standard hand-crafted feature extractors.
@article{arxiv.1812.06829,
title = {Discriminant Patch Representation for RGB-D Face Recognition Using Convolutional Neural Networks},
author = {Nesrine Grati and Achraf Ben-Hamadou and Mohamed Hammami},
journal= {arXiv preprint arXiv:1812.06829},
year = {2018}
}
Comments
Preprint accepted for publication in Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - 2019