Results 1 - 10
of
51
Face recognition by independent component analysis
- IEEE Transactions on Neural Networks
, 2002
"... Abstract—A number of current face recognition algorithms use face representations found by unsupervised statistical methods. Typically these methods find a set of basis images and represent faces as a linear combination of those images. Principal component analysis (PCA) is a popular example of such ..."
Abstract
-
Cited by 348 (5 self)
- Add to MetaCart
(Show Context)
Abstract—A number of current face recognition algorithms use face representations found by unsupervised statistical methods. Typically these methods find a set of basis images and represent faces as a linear combination of those images. Principal component analysis (PCA) is a popular example of such methods. The basis images found by PCA depend only on pairwise relationships between pixels in the image database. In a task such as face recognition, in which important information may be contained in the high-order relationships among pixels, it seems reasonable to expect that better basis images may be found by methods sensitive to these high-order statistics. Independent component analysis (ICA), a generalization of PCA, is one such method. We used a version of ICA derived from the principle of optimal information transfer through sigmoidal neurons. ICA was performed on face images in the FERET database under two different architectures, one which treated the images as random variables and the pixels as outcomes, and a second which treated the pixels as random variables and the images as outcomes. The first architecture found spatially local basis images for the faces. The second architecture produced a factorial face code. Both ICA representations were superior to representations based on PCA for recognizing faces across days and changes in expression. A classifier that combined the two ICA representations gave the best performance. Index Terms—Eigenfaces, face recognition, independent component analysis (ICA), principal component analysis (PCA), unsupervised learning. I.
Robust Parameterized Component Analysis: Theory and Applications to 2D Facial Modeling
- Computer Vision and Image Understanding, 91:53 – 71
, 2002
"... Principal Component Analysis (PCA) has been successfully applied to construct linear models of shape, graylevel, and motion. In particular, PCA has been widely used to model the variation in the appearance of people's faces. We extend previous work on facial modeling for tracking faces in video ..."
Abstract
-
Cited by 53 (12 self)
- Add to MetaCart
(Show Context)
Principal Component Analysis (PCA) has been successfully applied to construct linear models of shape, graylevel, and motion. In particular, PCA has been widely used to model the variation in the appearance of people's faces. We extend previous work on facial modeling for tracking faces in video sequences as they undergo significant changes due to facial expressions. Here we develop person-specific facial appearance models (PSFAM), which use modular PCA to model complex intra-person appearance changes. Such models require aligned visual training data; in previous work, this has involved a time consuming and errorprone hand alignment and cropping process. Instead, we introduce parameterized component analysis to learn a subspace that is invariant to affine (or higher order) geometric transformations. The automatic learning of a PSFAM given a training image sequence is posed as a continuous optimization problem and is solved with a mixture of stochastic and deterministic techniques achieving sub-pixel accuracy.
Face Recognition in Subspaces
- IN: S.Z. LI, A.K. JAIN (EDS.), HANDBOOK OF FACE RECOGNITION
, 2004
"... Images of faces, represented as high-dimensional pixel arrays, often belong to a manifold of intrinsically low dimension. Face recognition, and computer vision research in general, has witnessed a growing interest in techniques that capitalize on this observation, and apply algebraic and statisti ..."
Abstract
-
Cited by 44 (0 self)
- Add to MetaCart
Images of faces, represented as high-dimensional pixel arrays, often belong to a manifold of intrinsically low dimension. Face recognition, and computer vision research in general, has witnessed a growing interest in techniques that capitalize on this observation, and apply algebraic and statistical tools for extraction and analysis of the underlying manifold. In this chapter we describe in roughly chronological order techniques that identify, parameterize and analyze linear and nonlinear subspaces, from the original Eigenfaces technique to the recently introduced Bayesian method for probabilistic similarity analysis, and discuss comparative experimental evaluation of some of these techniques. We also discuss practical issues related to the application of subspace methods for varying pose, illumination and expression.
PCA vs. ICA: a comparison on the FERET data set
- in Proc. of the 4th International Conference on Computer Vision, ICCV’02
, 2002
"... Over the last ten years, face recognition has become a specialized applications area within the field of computer vision. Sophisticated commercial systems have been developed that achieve high recognition rates. Although elaborate, many of these systems include a subspace projection step and a neare ..."
Abstract
-
Cited by 34 (5 self)
- Add to MetaCart
(Show Context)
Over the last ten years, face recognition has become a specialized applications area within the field of computer vision. Sophisticated commercial systems have been developed that achieve high recognition rates. Although elaborate, many of these systems include a subspace projection step and a nearest neighbor classifier. The goal of this paper is to rigorously compare two subspace projection techniques within the context of a baseline system on the face recognition task. The first technique is principal component analysis (PCA), a well-known “baseline ” for projection techniques. The second technique is independent component analysis (ICA), a newer method that produces spatially localized and statistically independent basis vectors. Testing on the FERET data set (and using standard partitions), we find that, when a proper distance metric is used, PCA significantly outperforms ICA on a human face recognition task. This is contrary to previously published results. 1.
Face Recognition Using Kernel Methods
, 2001
"... Principal Component Analysis and Fisher Linear Discriminant methods have demonstrated their success in face detection, recognition, and tracking. The representation in these subspace methods is based on second order statistics of the image set, and does not address higher order statistical dependenc ..."
Abstract
-
Cited by 28 (0 self)
- Add to MetaCart
Principal Component Analysis and Fisher Linear Discriminant methods have demonstrated their success in face detection, recognition, and tracking. The representation in these subspace methods is based on second order statistics of the image set, and does not address higher order statistical dependencies such as the relationships among three or more pixels. Recently Higher Order Statistics and Independent Component Analysis (ICA) have been used as informative low dimensional representations for visual recognition.
Boosting for Fast Face Recognition
- In Proc. IEEE ICCV Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems
, 2001
"... We propose to use the AdaBoost algorithm for face recognition. AdaBoost is a kind of large margin classifiers and is efficient for on-line learning. In order to adapt the AdaBoost algorithm to fast face recognition, the original Adaboost which uses all given features is compared with the boosting al ..."
Abstract
-
Cited by 21 (0 self)
- Add to MetaCart
(Show Context)
We propose to use the AdaBoost algorithm for face recognition. AdaBoost is a kind of large margin classifiers and is efficient for on-line learning. In order to adapt the AdaBoost algorithm to fast face recognition, the original Adaboost which uses all given features is compared with the boosting along feature dimensions. The comparable results assure the use of the latter, which is faster for classification. The AdaBoost is typically a classification between two classes. To solve the multi-class recognition problem, a majority voting (MV) strategy can be used to combine all the pairwise classification results. However, the number of pairwise comparisons �is huge, when the number of individuals is very large in the face database. We propose to use a constrained majority voting (CMV) strategy to largely reduce the number of pairwise comparisons, without losing the recognition accuracy. Experimental results on a large face database of 1079 faces of 137 individuals show the feasibility of our approach for fast face recognition. Keywords: Face recognition, large margin classifiers, AdaBoost, constrained majority voting (CMV), principal component analysis (PCA). 1.
Learning Multiview Face Subspaces and Facial Pose Estimation using Independent Component Analysis
- IEEE Trans. Image Processing
, 2005
"... Abstract—An independent component analysis (ICA) based ap-proach is presented for learning view-specific subspace representa-tions of the face object from multiview face examples. ICA, its vari-ants, namely independent subspace analysis (ISA) and topographic independent component analysis (TICA), ta ..."
Abstract
-
Cited by 17 (0 self)
- Add to MetaCart
Abstract—An independent component analysis (ICA) based ap-proach is presented for learning view-specific subspace representa-tions of the face object from multiview face examples. ICA, its vari-ants, namely independent subspace analysis (ISA) and topographic independent component analysis (TICA), take into account higher order statistics needed for object view characterization. In con-trast, principal component analysis (PCA), which de-correlates the second order moments, can hardly reveal good features for charac-terizing different views, when the training data comprises a mix-ture of multiview examples and the learning is done in an unsu-pervised way with view-unlabeled data. We demonstrate that ICA, TICA, and ISA are able to learn view-specific basis components un-supervisedly 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. Index Terms—Appearance-based approach, face analysis, inde-pendent component analysis (ICA), independent subspace analysis (ISA), learning by examples, topographic independent component analysis (TICA), view subspaces. I.
Non-linear Bayesian Image Modelling
- In Proceedings Sixth European Conference on Computer Vision
, 2000
"... . In recent years several techniques have been proposed for modelling the low-dimensional manifolds, or `subspaces', of natural images. Examples include principal component analysis (as used for instance in `eigen-faces'), independent component analysis, and auto-encoder neural networks ..."
Abstract
-
Cited by 16 (4 self)
- Add to MetaCart
(Show Context)
. In recent years several techniques have been proposed for modelling the low-dimensional manifolds, or `subspaces', of natural images. Examples include principal component analysis (as used for instance in `eigen-faces'), independent component analysis, and auto-encoder neural networks. Such methods suffer from a number of restrictions such as the limitation to linear manifolds or the absence of a probablistic representation. In this paper we exploit recent developments in the fields of variational inference and latent variable models to develop a novel and tractable probabilistic approach to modelling manifolds which can handle complex non-linearities. Our framework comprises a mixture of sub-space components in which both the number of components and the effective dimensionality of the sub-spaces are determined automatically as part of the Bayesian inference procedure. We illustrate our approach using two classical problems: modelling the manifold of face images and mode...
Recognizing faces with pca and ica
- COMPUTER VISION AND IMAGE UNDERSTANDING, SPECIAL ISSUE ON FACE RECOGNITION
, 2003
"... ..."
(Show Context)
