From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose

By Athinodoros S. Georghiades, Peter N. Belhumeur, David J. Kriegman. 2001

5,219 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Privacy Risks of Securing Machine Learning Models against Adversarial Examples (2019, methodology): “The extended Yale Face database B is used to train face recognition models, and contains gray scale face images of 38 subjects under various lighting conditions [14, 27].”
Unsupervised Adversarial Invariance (2018, neutral): “Extended Yale-B.”
Learning Disentangled Representations with Semi-Supervised Deep Generative Models (2017, methodology): “Here, we use the “Yale B” dataset [6] as processed by Jampani et al.”
Mitigating Information Leakage in Image Representations: A Maximum Entropy Approach (2019, methodology): “We used the Extended Yale B dataset [6] comprising of face images of 38 people under different lighting conditions (directions of the light source) : upper right, lower right, lower left, upper left, or the front.”
Naive-Deep Face Recognition: Touching the Limit of LFW Benchmark or Not? (2015, background): “The LFW benchmark [8] is intended to test the recognition system’s performance in unconstrained environment, which is considerably harder than many other constrained dataset (e.g., YaleB [6] and MultiPIE [7]).”
Recent Advances in Open Set Recognition: A Survey (2018, methodology): “YALEB [138]: The Extended Yale B (YALEB) dataset has”
PCANet: A Simple Deep Learning Baseline for Image Classification? (2014, methodology): “We then apply the PCANet with the PCA filters learned from MultiPIE to Extended Yale B dataset [20].”
Half-Quadratic-Based Iterative Minimization for Robust Sparse Representation (2014, methodology): “Two public face recognition databases, namely, the AR [47] and Extended Yale B [48] databases, were selected for experiments.”
Recognizing Rotated Faces From Frontal and Side Views: An Approach Toward Effective Use of Mugshot Databases (2008, background): “Color versions of one or more of the figures in this paper are available online at http://ieeexplore.ieee.org.”
Robust sparse coding for face recognition (2011, methodology): “2, we test RSC for FR without occlusion on three face databases (Extended Yale B [5, 13], AR [17], and Multi-PIE [6]).”
Learning a discriminative dictionary for sparse coding via label consistent K-SVD (2011, methodology): “The Extended YaleB database contains 2, 414 frontalface images of 38 persons [9].”
Face recognition: A literature survey (2003, background): “23 To address GBR ambiguity, the authors proposed exploiting face symmetry (to correct tilt) and the fact that the chin and the forehead are at about the same height (to correct slant), and requiring that the range of heights of the surface be about twice the distance between the eyes (to correct sc”
Face Recognition Based on Fitting a 3D Morphable Model (2003, background): “Three-dimension face reconstruction can also be employed to generate synthetic views from gallery or probe images [3], [35], [15], [38].”
Kernel Sparse Representation for Image Classification and Face Recognition (2010, methodology): “We evaluate our method on Extended Yale B Database [7], which contains 38 categories, 2414 frontal-face images.”
Smooth Representation Clustering (2014, background): “…with each subspace corresponding to one category or class, e.g., point trajectories of moving objects captured by an afﬁne camera [24], images of several subjects under varying illumination or under different poses [6], and local patches or texture features of pixels/superpixels on an image [20].”
Structured AutoEncoders for Subspace Clustering (2018, methodology): “the COIL20 image data set [46], the Extended Yale database B (YaleB) [47], the BF0502 data set [48], the CIFAR10 image database [49], and the mnist handwritten digits [50].”