Parameterisation of a stochastic model for human face identification

By F. Samaria, A. Harter. 1994

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

Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning (2017, methodology): “We conducted our experiments on twowell-known datasets, namely MNIST [43] and AT&T dataset of faces [71] (a.”
Understanding How Dimension Reduction Tools Work: An Empirical Approach to Deciphering t-SNE, UMAP, TriMAP, and PaCMAP for Data Visualization (2020, methodology): “, 2019), we use the following datasets to evaluate and compare DR methods: Olivetti Faces (Samaria and Harter, 1994), COIL-20”
Sum-product networks: A new deep architecture (2011, methodology): “Additionally, we also ran experiments on the Olivetti face dataset [28] containing 400 faces.”
Input Convex Neural Networks (2016, methodology): “, 2008], image completion using the Olivetti face dataset [Samaria and Harter, 1994], and continuous action reinforcement learning in the OpenAI Gym [Brockman et al.”
SIFT Flow: Dense Correspondence across Scenes and Its Applications (2011, methodology): “For our experiment, we want to compare two motion fields at a coarse level because careful comparisons such as AAE would not be meaningful.”
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.”
Deep forest (2017, methodology): “The ORL dataset [Samaria and Harter, 1994] contains 400 gray-scale facial images taken from 40 persons.”
Orthogonal Neighborhood Preserving Projections: A Projection-Based Dimensionality Reduction Technique (2007, background): “The ORL database [14] contains 40 individuals and 10 dif-”
Face Recognition Using Line Edge Map (2002, unknown): “Finally, the paper concludes in Section 7.”
The Empirical Interpolation Method (2013, methodology): “We therefore use the same library of face images, which is from [23].”
Semi-Supervised and Unsupervised Extreme Learning Machines (2014, methodology): “1) Datasets: The data sets used for testing US-ELM include three UCI data sets (IRIS, WINE, and SEGMENT) [58], two face recognition data sets (YALEB and ORL) [59], [60], and two data sets used in Section VII-A (COIL20 and USPST).”
Discriminative Least Squares Regression for Multiclass Classification and Feature Selection (2012, background): “AT and T Data Set: It includes 40 different persons, and each person has ten gray images with different expressions and facial details [46].”
Deep Structured Energy-Based Image Inpainting (2018, methodology): “The Olivetti face dataset [8] contains 400 grayscale face images of size 64×64, and 50 images of the dataset were used for testing.”
Generalized Low Rank Approximations of Matrices (2004, background): “–O RL 3 is a well-known dataset for face recognition ( Samaria & Harter, 1994 ).”
Face recognition by support vector machines (2000, background): “The experimental results show that the SVMs are a better learning algorithm than the nearest center approach for face recognition.”
Projection functions for eye detection (2004, methodology): “Representatives are Pentland et al.’s modular eigenspaces [6] and Samaria’s HMM based algorithm [ 7 ].”
Beyond pixels: exploring new representations and applications for motion analysis (2009, methodology): “(a): Ten samples of one subject in ORL database [93].”