Continuous Head Pose Estimation Using Manifold Subspace Embedding and Multivariate Regression

In this paper, a continuous head pose estimation system is proposed to estimate yaw and pitch head angles from raw facial images. Our approach is based on manifold learning-based methods, due to their promising generalization properties shown for face modeling from images. The method combines histog...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2018-01, Vol.6, p.18325-18334
Main Authors: Diaz-Chito, Katerine, Martinez Del Rincon, Jesus, Hernandez-Sabate, Aura, Gil, Debora
Format: Article
Language:English
Subjects:
B-splines
Face
Feature extraction
generalized discriminative common vectors
Head
Head pose estimation
Histograms
HOG features
Machine learning
Manifolds
Manifolds (mathematics)
multiple linear regression
Pitch (inclination)
Pose estimation
Training
Yaw
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, a continuous head pose estimation system is proposed to estimate yaw and pitch head angles from raw facial images. Our approach is based on manifold learning-based methods, due to their promising generalization properties shown for face modeling from images. The method combines histograms of oriented gradients, generalized discriminative common vectors, and continuous local regression to achieve successful performance. Our proposal was tested on multiple standard face data sets, as well as in a realistic scenario. Results show a considerable performance improvement and a higher consistence of our model in comparison with other state-of-the-art methods, with angular errors varying between 9° and 17°.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2018.2817252