We propose an appearance manifold with view-dependent covariance matrix for face recognition from video sequences in two learning frameworks: the supervised-learning and the incremental unsupervised-learning. The advantages of this method are, first, the appearance manifold with view-dependent covariance matrix model is robust to pose changes and is also noise invariant, since the embedded covariance matrices are calculated based on their poses in order to learn the samples' distributions along the manifold. Moreover, the proposed incremental unsupervised-learning framework is more realistic for real-world face recognition applications. It is obvious that it is difficult to collect large amounts of face sequences under complete poses (from left sideview to right sideview) for training. Here, an incremental unsupervised-learning framework allows us to train the system with the available initial sequences, and later update the system's knowledge incrementally every time an unlabelled sequence is input. In addition, we also integrate the appearance manifold with view-dependent covariance matrix model with a pose estimation system for improving the classification accuracy and easily detecting sequences with overlapped poses for merging process in the incremental unsupervised-learning framework. The experimental results showed that, in both frameworks, the proposed appearance manifold with view-dependent covariance matrix method could recognize faces from video sequences accurately.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Lina, Tomokazu TAKAHASHI, Ichiro IDE, Hiroshi MURASE, "Incremental Unsupervised-Learning of Appearance Manifold with View-Dependent Covariance Matrix for Face Recognition from Video Sequences" in IEICE TRANSACTIONS on Information,
vol. E92-D, no. 4, pp. 642-652, April 2009, doi: 10.1587/transinf.E92.D.642.
Abstract: We propose an appearance manifold with view-dependent covariance matrix for face recognition from video sequences in two learning frameworks: the supervised-learning and the incremental unsupervised-learning. The advantages of this method are, first, the appearance manifold with view-dependent covariance matrix model is robust to pose changes and is also noise invariant, since the embedded covariance matrices are calculated based on their poses in order to learn the samples' distributions along the manifold. Moreover, the proposed incremental unsupervised-learning framework is more realistic for real-world face recognition applications. It is obvious that it is difficult to collect large amounts of face sequences under complete poses (from left sideview to right sideview) for training. Here, an incremental unsupervised-learning framework allows us to train the system with the available initial sequences, and later update the system's knowledge incrementally every time an unlabelled sequence is input. In addition, we also integrate the appearance manifold with view-dependent covariance matrix model with a pose estimation system for improving the classification accuracy and easily detecting sequences with overlapped poses for merging process in the incremental unsupervised-learning framework. The experimental results showed that, in both frameworks, the proposed appearance manifold with view-dependent covariance matrix method could recognize faces from video sequences accurately.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E92.D.642/_p
Copy
@ARTICLE{e92-d_4_642,
author={Lina, Tomokazu TAKAHASHI, Ichiro IDE, Hiroshi MURASE, },
journal={IEICE TRANSACTIONS on Information},
title={Incremental Unsupervised-Learning of Appearance Manifold with View-Dependent Covariance Matrix for Face Recognition from Video Sequences},
year={2009},
volume={E92-D},
number={4},
pages={642-652},
abstract={We propose an appearance manifold with view-dependent covariance matrix for face recognition from video sequences in two learning frameworks: the supervised-learning and the incremental unsupervised-learning. The advantages of this method are, first, the appearance manifold with view-dependent covariance matrix model is robust to pose changes and is also noise invariant, since the embedded covariance matrices are calculated based on their poses in order to learn the samples' distributions along the manifold. Moreover, the proposed incremental unsupervised-learning framework is more realistic for real-world face recognition applications. It is obvious that it is difficult to collect large amounts of face sequences under complete poses (from left sideview to right sideview) for training. Here, an incremental unsupervised-learning framework allows us to train the system with the available initial sequences, and later update the system's knowledge incrementally every time an unlabelled sequence is input. In addition, we also integrate the appearance manifold with view-dependent covariance matrix model with a pose estimation system for improving the classification accuracy and easily detecting sequences with overlapped poses for merging process in the incremental unsupervised-learning framework. The experimental results showed that, in both frameworks, the proposed appearance manifold with view-dependent covariance matrix method could recognize faces from video sequences accurately.},
keywords={},
doi={10.1587/transinf.E92.D.642},
ISSN={1745-1361},
month={April},}
Copy
TY - JOUR
TI - Incremental Unsupervised-Learning of Appearance Manifold with View-Dependent Covariance Matrix for Face Recognition from Video Sequences
T2 - IEICE TRANSACTIONS on Information
SP - 642
EP - 652
AU - Lina
AU - Tomokazu TAKAHASHI
AU - Ichiro IDE
AU - Hiroshi MURASE
PY - 2009
DO - 10.1587/transinf.E92.D.642
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E92-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2009
AB - We propose an appearance manifold with view-dependent covariance matrix for face recognition from video sequences in two learning frameworks: the supervised-learning and the incremental unsupervised-learning. The advantages of this method are, first, the appearance manifold with view-dependent covariance matrix model is robust to pose changes and is also noise invariant, since the embedded covariance matrices are calculated based on their poses in order to learn the samples' distributions along the manifold. Moreover, the proposed incremental unsupervised-learning framework is more realistic for real-world face recognition applications. It is obvious that it is difficult to collect large amounts of face sequences under complete poses (from left sideview to right sideview) for training. Here, an incremental unsupervised-learning framework allows us to train the system with the available initial sequences, and later update the system's knowledge incrementally every time an unlabelled sequence is input. In addition, we also integrate the appearance manifold with view-dependent covariance matrix model with a pose estimation system for improving the classification accuracy and easily detecting sequences with overlapped poses for merging process in the incremental unsupervised-learning framework. The experimental results showed that, in both frameworks, the proposed appearance manifold with view-dependent covariance matrix method could recognize faces from video sequences accurately.
ER -