The CMU Pose, Illumination, and Expression Database

By Terence Sim, Simon Baker, Maan Bsat. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003

1,924 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/7ffa7a36e5414a0f2b16b1d8f93442ab15e2235d

How researchers see this paper

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

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

Rotation Invariant Image Description with Local Binary Pattern Histogram Fourier Features (2009, methodology): “The CMU PIE (Pose, Illumination, and Expression) database [9] was used for this experiment.”
Multiple Kernel Fuzzy Clustering (2012, methodology): “To combine these kernels, as well as to ensure that the resulted kernel still satisfies Mercer’s condition, we consider a nonnegative combination of these feature maps, φ′, i.e., φ′(x) = M∑ k=1 ωkφk (x), with ωk ≥ 0.”
Multilinear Discriminant Analysis for Higher-Order Tensor Data Classification (2014, methodology): “We compare DGTDA and CMDA with three other MDA methods that employ TTP, DATER, GTDA and tensorbased subspace learning (TBSL) [22] for face image ensemble recognition on the Extended Yale Face Database B [25], CMU PIE Database [26], the Weizmann Face Database [27] and for human gait image ensemble re”
Subspace Interpolation via Dictionary Learning for Unsupervised Domain Adaptation (2013, methodology): “Face recognition under pose variation on CMU-PIE dataset [30]”
A Database and Evaluation Methodology for Optical Flow (2007, background): “Many areas of computer vision, such as stereo [63], face recognition [28, 55, 68], and object recognition [23, 24], have challenging datasets to track the progress made by leading algorithms and to stimulate new ideas.”
Appearance-based face recognition and light-fields (2004, methodology): “In extensive evaluations, we compare the performance of eigen lightfields to standard face recognition algorithms on both the FERET [22] and CMU PIE [26] databases.”
An Analysis of Random Projection for Changeable and Privacy-Preserving Biometric Verification (2010, methodology): “It originally contains 5676 images of 1020 subjects from five well-known databases, namely, FERET [44], [45], PIE [46], AR [47], Aging [48], and BioID [49].”
Sampling Methods for the Nyström Method (2012, neutral): “These empirical results suggest a trade-off between time and space requirements, as noted by Schölkopf and Smola (2002)[Chapter 10.2].”
Coupled Kernel Embedding for Low-Resolution Face Image Recognition (2012, background): “The CMU pose, illumination, and expression (PIE) images were captured by 13 synchronized cameras and 21 flashes, under varying pose, illumination, and expression [36].”
Optimal Local Basis: A Reinforcement Learning Approach for Face Recognition (2009, methodology): “The number of features employed by the studied methods for PIE database.”
Subspace Learning Based on Tensor Analysis (2005, background): “The CMU PIE face database contains 68 individuals with 41,368 face images as a whole.”
Spectral Embedded Clustering: A Framework for In-Sample and Out-of-Sample Spectral Clustering (2011, methodology): “(c) CMU PIE.”
Face Recognition Under Varying Illumination Using Gradientfaces (2009, background): “In [30], the authors describe a uniﬁed framework for performing these operations on video in the gradient domain.”
How far can you get with a modern face recognition test set using only simple features? (2009, methodology): “An alternative approach would be to use (or create) controlled photographic sets such as the PIE Face Set [16, 27] (or the NORB Object Set [8, 25]), which systematically vary parameters such as camera and lighting angle.”
Orthogonal Laplacianfaces for Face Recognition (2006, background): “is the ORL (Olivetti Research Laboratory) database2, and the third is the PIE (pose, illumination, and expression) database from CMU [ 18 ].”
Understanding OSN-based facial disclosure against face authentication systems (2014, background): “As previously explained, most of face authentication products [10, 8, 34, 23, 24, 35] provide very limited choices on security level.”
Recognition of blurred faces using Local Phase Quantization (2008, methodology): “The efficiency of the proposed face descriptor in the face recognition scenario was tested using two datasets, the CMU PIE (Pose, Illumination, and Expression) dataset [6] and the Face Recognition Grand Challenge (FRGC) experiment 1.0.4 [5].”
A 3D facial expression database for facial behavior research (2006, neutral): “2D FERET [31], FRGC [30], CMU-PIE [ 39 ], BioID[50]”