Head Pose Estimation Using Multi-scale Gaussian Derivatives - Archive ouverte HAL Access content directly
Conference Papers Year : 2013

Head Pose Estimation Using Multi-scale Gaussian Derivatives

(1) , (1)
1

Abstract

In this paper we approach the problem of head pose estimation by combining Multi-scale Gaussian Derivatives with Support Vector Machines. We evaluate the approach on the Pointing04 and CMU-PIE data sets and to estimate the pan and tilt of the head from facial images. We achieved a mean absolute error of 6.9 degrees for pan and 8.0 degrees for tilt on the Pointing04 data set.
Fichier principal
Vignette du fichier
79440319.pdf (363.99 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00839527 , version 1 (28-06-2013)

Identifiers

Cite

Varun Jain, James L. Crowley. Head Pose Estimation Using Multi-scale Gaussian Derivatives. 18th Scandinavian Conference on Image Analysis, Jun 2013, Espoo, Finland. ⟨10.1007/978-3-642-38886-6_31⟩. ⟨hal-00839527⟩
260 View
523 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More