Proceedings ArticleDOI
Pose-invariant recognition of faces at unknown aspect views
Ashit Talukder,David P. Casasent +1 more
- Vol. 5, pp 3286-3290
TLDR
A new technique is discussed to recognize human faces under varying aspect views (pose) using a feature extraction procedure that inherently removes distortions due to pose variations, and therefore requires only single training and/or test face images, which could be at different aspect views.Abstract:
A new technique is discussed to recognize human faces under varying aspect views (pose). We first estimate the pose of an unknown human face from a 2D gray-scale image and then transform the unknown face to a reference pose using a feature extraction procedure. A different set of features for discriminating between different individuals are then extracted from these reconstructed faces for recognition. The feature extraction scheme used is known as the maximum representation and discrimination feature method. The advantage of our procedure is that it inherently removes distortions due to pose variations, and therefore requires only single training and/or test face images, which could be at different aspect views. For transformation, it does not require the face to be in the database during training. For recognition, only one aspect view at any pose is necessary.read more
Citations
More filters
Journal ArticleDOI
Efficient 3D reconstruction for face recognition
TL;DR: An efficient two-dimensional-to-three-dimensional integrated face reconstruction approach is introduced to reconstruct a personalized 3D face model from a single frontal face image with neutral expression and normal illumination and the synthesized virtual faces significantly improve the accuracy of face recognition with changing PIE.
Journal ArticleDOI
Learning multiview face subspaces and facial pose estimation using independent component analysis
TL;DR: It is demonstrated that ICA, TICA, and ISA are able to learn view-specific basis components unsupervisedly from the mixture data and thereby explain underlying reasons for the emergent formation of view subspaces.
Journal ArticleDOI
Design and Fusion of Pose-Invariant Face-Identification Experts
Tae-Kyun Kim,Josef Kittler +1 more
TL;DR: The proposed fusion architecture of the pose-invariant face experts achieves an impressive accuracy gain by virtue of the individual experts diversity.
Journal ArticleDOI
A closed-form neural network for discriminatory feature extraction from high-dimensional data
Ashit Talukder,David P. Casasent +1 more
TL;DR: A new neural network for data discrimination in pattern recognition applications that is theoretically shown to provide nonlinear transforms of the input data that are more general than those provided by other nonlinear multilayer perceptron neural network and support-vector machine techniques for cases involving high-dimensional inputs.
Journal ArticleDOI
Multipose Face Recognition Based on Frequency Analysis and Modified LDA
TL;DR: The aims of proposed system are to reduce the high memory space requirement and to overcome retraining problem of classical LDA and PCA.
References
More filters
Journal ArticleDOI
Application of the Karhunen-Loeve procedure for the characterization of human faces
Michael Kirby,Lawrence Sirovich +1 more
TL;DR: The use of natural symmetries (mirror images) in a well-defined family of patterns (human faces) is discussed within the framework of the Karhunen-Loeve expansion, which results in an extension of the data and imposes even and odd symmetry on the eigenfunctions of the covariance matrix.
Proceedings ArticleDOI
View-based and modular eigenspaces for face recognition
Pentland,Moghaddam,Starner +2 more
TL;DR: In this paper, a view-based multiple-observer eigenspace technique is proposed for use in face recognition under variable pose, which incorporates salient features such as the eyes, nose and mouth, in an eigen feature layer.
Journal ArticleDOI
Linear object classes and image synthesis from a single example image
Thomas Vetter,Tomaso Poggio +1 more
TL;DR: For linear object classes, it is shown that linear transformations can be learned exactly from a basis set of 2D prototypical views and preliminary evidence that the technique can effectively "rotate" high-resolution face images from a single 2D view is shown.
Proceedings ArticleDOI
Bayesian face recognition using deformable intensity surfaces
TL;DR: A novel technique for face recognition based on deformable intensity surfaces which incorporates both the shape and texture components of the 2D image and an increased recognition rate over the previous best methods are described.
Journal ArticleDOI
General methodology for simultaneous representation and discrimination of multiple object classes
Ashit Talukder,David P. Casasent +1 more
TL;DR: A novel nonlinear eigenfeature extraction technique to represent data with closed-form solutions and use it to derive a nonlinear MRDF algorithm, which is applied to an automated product inspection problem and for classification and pose estimation of two similar objects under 3-D aspect angle variations.