Learning multiview face subspaces and facial pose estimation using independent component analysis

Authors:
S. Z. Li;XiaoGuang Lu;Xinwen Hou;Xianhua Peng;Qiansheng Cheng
Affiliations:
Microsoft Res. Asia, Beijing, China;-;-;-;-
Venue:
IEEE Transactions on Image Processing
Year:
2005

Citing 0
Cited 13

Two-stage optimal component analysis

Computer Vision and Image Understanding
Independent component analysis-based defect detection in patterned liquid crystal display surfaces

Image and Vision Computing
Saliency model-based face segmentation and tracking in head-and-shoulder video sequences

Journal of Visual Communication and Image Representation
Learning a Person-Independent Representation for Precise 3D Pose Estimation

Multimodal Technologies for Perception of Humans
Head Pose Estimation Based on Tensor Factorization

Neural Information Processing
3-D head pose estimation in monocular video sequences using deformable surfaces and radial basis functions

IEEE Transactions on Circuits and Systems for Video Technology
Using mutual information to indicate facial poses in video sequences

Proceedings of the ACM International Conference on Image and Video Retrieval
Synchronized submanifold embedding for person-independent pose estimation and beyond

IEEE Transactions on Image Processing
Independent components extraction from image matrix

Pattern Recognition Letters
Effects of finite register length on fast ICA, bacterial foraging optimization based ICA and constrained genetic algorithm based ICA algorithm

Digital Signal Processing
Classification of 3-D objects and faces employing view-based clusters

Computers and Electrical Engineering
3D face pose estimation based on multi-template AAM

CCBR'12 Proceedings of the 7th Chinese conference on Biometric Recognition
Robust frontal view search using extended manifold learning

Journal of Visual Communication and Image Representation

Quantified Score

Hi-index	0.01

Visualization

Abstract

An independent component analysis (ICA) based approach is presented for learning view-specific subspace representations of the face object from multiview face examples. ICA, its variants, namely independent subspace analysis (ISA) and topographic independent component analysis (TICA), take into account higher order statistics needed for object view characterization. In contrast, principal component analysis (PCA), which de-correlates the second order moments, can hardly reveal good features for characterizing different views, when the training data comprises a mixture of multiview examples and the learning is done in an unsupervised way with view-unlabeled data. We demonstrate that ICA, TICA, and ISA are able to learn view-specific basis components unsupervisedly from the mixture data. We investigate results learned by ISA in an unsupervised way closely and reveal some surprising findings and thereby explain underlying reasons for the emergent formation of view subspaces. Extensive experimental results are presented.