Abstract
Face recognition in real-world conditions requires the ability to deal with a number
of conditions, such as variations in pose, illumination and expression. In this paper, we
focus on variations in head pose and use a computationally efficient regression-based
approach for synthesising face images in different poses, which are used to extend the
face recognition training set. In this data-driven approach, the correspondences between
facial landmark points in frontal and non-frontal views are learnt offline from manually
annotated training data via Gaussian Process Regression. We then use this learner to
synthesise non-frontal face images from any unseen frontal image. To demonstrate the
utility of this approach, two frontal face recognition systems (the commonly used PCA
and the recent Multi-Region Histograms) are augmented with synthesised non-frontal
views for each person. This synthesis and augmentation approach is experimentally
validated on the FERET dataset, showing a considerable improvement in recognition
rates for ±40◦ and ±60◦ views, while maintaining high recognition rates for ±15◦
and ±25◦ views.
of conditions, such as variations in pose, illumination and expression. In this paper, we
focus on variations in head pose and use a computationally efficient regression-based
approach for synthesising face images in different poses, which are used to extend the
face recognition training set. In this data-driven approach, the correspondences between
facial landmark points in frontal and non-frontal views are learnt offline from manually
annotated training data via Gaussian Process Regression. We then use this learner to
synthesise non-frontal face images from any unseen frontal image. To demonstrate the
utility of this approach, two frontal face recognition systems (the commonly used PCA
and the recent Multi-Region Histograms) are augmented with synthesised non-frontal
views for each person. This synthesis and augmentation approach is experimentally
validated on the FERET dataset, showing a considerable improvement in recognition
rates for ±40◦ and ±60◦ views, while maintaining high recognition rates for ±15◦
and ±25◦ views.
Original language | English |
---|---|
Title of host publication | British Machine Vision Conference 2009 |
Editors | Andrea Cavallaro, Simon Prince, Daniel Alexander |
Place of Publication | London, UK |
Publisher | British Machine Vision Association |
Pages | 1-10 |
Number of pages | 10 |
DOIs | |
Publication status | Published - 2009 |
Event | British Machine Vision Conference 2009 - London, United Kingdom Duration: 7 Sept 2009 → 10 Sept 2009 |
Conference
Conference | British Machine Vision Conference 2009 |
---|---|
Country/Territory | United Kingdom |
City | London |
Period | 7/09/09 → 10/09/09 |