Appearance-based face recognition and light-fields

By Ralph Gross, Iain Matthews, Simon Baker. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004

298 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/6f3c43ada1c69ba3b614325ba76143bcab506606

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Computer Vision and Pattern Recognition

Citations in the corpus

Names and faces in the news (2004, background): “Early face recognition is done in [19, 21] and is reviewed in [12, 6, 13].”
Face recognition in hyperspectral images (2003, background): “10, 11, 12, and 13.”
A Comparative Study of Local Matching Approach for Face Recognition (2007, methodology): “Prompted by the work of Belhumeur and Kriegman [5], the second approach, modeling illumination variations, has received increasing attention [17], [24].”
Facial Landmark Detection: A Literature Survey (2018, background): “It is well known that the AAM model has limited generalization ability and it has diﬃ-culty ﬁtting the unseen face variations (e.g. across subjects, illumination, partial occlusion, etc.) [37][38].”
Subspace Interpolation via Dictionary Learning for Unsupervised Domain Adaptation (2013, methodology): “Furthermore, our average performance is comparable to [16], which relies on a generic training set to build pose specific models, while DA methods do not make such an assumption.”
Recognizing Rotated Faces From Frontal and Side Views: An Approach Toward Effective Use of Mugshot Databases (2008, methodology): “The police have used mug shots to identify criminals for more than a century [49] and there are many legacy mugshot databases which were routinely taken during the police booking process [31].”
Light Field Image Processing: An Overview (2017, methodology): “[174] introduced a novel face recognition approach using a light field system composed of 13 cameras.”
Face recognition across pose: A review (2009, methodology): “All rights reserved. doi:10.1016/j.patcog.2009.04.017 a few promising methods have been proposed in tackling the problem of recognising faces in arbitrary poses, such as tied factor analysis (TFA) [63], 3D morphable model (3DMM) [14], eigen light-field (ELF) [33], illumination cone model (ICM) [30],”
A 3D Face Model for Pose and Illumination Invariant Face Recognition (2009, methodology): “[23, 10]) the same face database is used for both training and testing.”
The CAS-PEAL Large-Scale Chinese Face Database and Baseline Evaluations (2008, background): “studied extensively in recent years [16], [31], [37], [42], [47], [48] and that the integration of 3D face model techniques to the existing face recognition algorithms has also been investigated [49], [50].”
Gesture Recognition: A Survey (2007, methodology): “Baker et al. have developed facial recognition , interpretation, and coding techniques based on the AAM in [58]–[61].”
Locally Linear Regression for Pose-Invariant Face Recognition (2007, methodology): “Gross et al. propose the Eigen light-ﬁeld (ELF) method to tackle the pose problem [10], [11].”