Virtual view generation using clustering based local view transition model

Authors:
Xi Li;Tomokazu Takahashi;Daisuke Deguchi;Ichiro Ide;Hiroshi Murase
Affiliations:
Graduate School of Information Science, Nagoya University, Japan;Department of Economics and Information, Gifu Shotoku Gakuen University, Japan;Information and Communications Headquarters, Nagoya University, Japan;Graduate School of Information Science, Nagoya University, Japan;Graduate School of Information Science, Nagoya University, Japan
Venue:
ACCV'12 Proceedings of the 11th international conference on Computer Vision - Volume 2
Year:
2012

Citing 8
Cited 0

Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Hallucinating Faces

FG '00 Proceedings of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition 2000
Face recognition from one example view

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Face recognition: A literature survey

ACM Computing Surveys (CSUR)
Face Recognition Based on Frontal Views Generated from Non-Frontal Images

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Multi-View Stereo Revisited

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Frontal face generation from multiple low-resolution non-frontal faces for face recognition

ACCV'10 Proceedings of the 2010 international conference on Computer vision - Volume Part I
Locally Linear Regression for Pose-Invariant Face Recognition

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents an approach for realistic virtual view generation using appearance clustering based local view transition model, with its target application on cross-pose face recognition. Previously, the traditional global pattern based view transition model (VTM) method was extended to its local version called LVTM, which learns the linear transformation of pixel values between frontal and non-frontal image pairs using partial image in a small region for each location, rather than transforming the entire image pattern. In this paper, we show that the accuracy of the appearance transition model and the recognition rate can be further improved by better exploiting the inherent linear relationship between frontal-nonfrontal face image patch pairs. For each specific location, instead of learning a common transformation as in the LVTM, the corresponding local patches are first clustered based on appearance similarity distance metric and then the transition models are learned separately for each cluster. In the testing stage, each local patch for the input non-frontal probe image is transformed using the learned local view transition model corresponding to the most visually similar cluster. The experimental results on a real-world face dataset demonstrated the superiority of the proposed method in terms of recognition rate.