3D curvature analysis with a novel one-shot technique
Resumen:
In this work we will show that it is possible to perform three-dimensional (3D) analysis and extract features without performing a 3D surface reconstruction. We propose a novel approach that consists in acquiring the scene under the projection of structured light (plus the natural ambient illumination), which allows us to obtain the depth gradient map using a simple processing step with very low hardware requirements.
2014 | |
Face curvatures 3D feature extraction HK classification Nose location Procesamiento de Señales |
|
Inglés | |
Universidad de la República | |
COLIBRI | |
https://hdl.handle.net/20.500.12008/41796 | |
Acceso abierto | |
Licencia Creative Commons Atribución - No Comercial - Sin Derivadas (CC - By-NC-ND 4.0) |
Resultados similares
-
One-shot 3D-gradient method applied to face recognition
Autor(es):: Di Martino, Matías
Fecha de publicación:: (2015) -
A study of deep learning and its applications to face recognition techniques
Autor(es):: Suzacq, Fernando
Fecha de publicación:: (2021) -
Automatic eyes and nose detection using curvature analysis
Autor(es):: Di Martino, Matías
Fecha de publicación:: (2015) -
Evaluation of a face recognition system performances variation on a citizen passports database
Autor(es):: Preciozzi, Javier
Fecha de publicación:: (2014) -
Not afraid of the dark : NIR-VIS face recognition via cross-spectral hallucination and low-rank embedding
Autor(es):: Sapiro, Guillermo
Fecha de publicación:: (2017)