Face recognition using Laplacianfaces

By Xiaofei He, Shuicheng Yan, Yuxiao Hu, Partha Niyogi, HongJiang Zhang. 2005

3,366 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

SphereFace: Deep Hypersphere Embedding for Face Recognition (2017, background): “A-Softmax loss can be interpreted as constraining learned features to be discriminative on a hypersphere manifold, which intrinsically matches the prior that face images lie on a manifold [14, 5, 31].”
Face recognition across pose: A review (2009, background): “Though many face recognition approaches, for example [4,7,27,35,43,53,75], reported satisfactory performances, their successes are limited to the conditions of controlled environment, which are unrealistic in many real applications.”
Generalized Multiview Analysis: A discriminative latent space (2012, methodology): “Methods that fit this equation include PCA [23, 25], LDA [1, 25], LPP [10, 25], CCA, and MFA [25].”
A Quadrature Formula for Diffusion Polynomials Corresponding to a Generalized Heat Kernel (2010, background): “1 Introduction Many practical applications, for example, document analysis [8], face recognition [17], semi–supervised learning [2, 1], image processing [10], and cataloguing of galaxies [11], involve a large amount of very high dimensional data.”
Motor Bearing Fault Diagnosis Using Trace Ratio Linear Discriminant Analysis (2014, methodology): “The visualization and classification of bearing fault data using TR-LDA are reported and compared with other methods, including unsupervised methods, such as PCA and LPP [26], and supervised methods, such as CCA [48], MMC [49], LDA, and MFA [36].”
Graph Embedding and Extensions: A General Framework for Dimensionality Reduction (2007, neutral): “Another linear technique called Locality Preserving Projections (LPP) [10] has been proposed for dimensionality reduction that preserves local relationships within the data set and uncovers its essential manifold structure.”
Orthogonal Neighborhood Preserving Projections: A Projection-Based Dimensionality Reduction Technique (2007, methodology): “An interesting connection can be made with PCA as was observed in [5].”
Transferred Dimensionality Reduction (2008, methodology): “And the corresponding graph Laplacians are [14]: Lw = I−H(HT H)−1HT (4) Lb = H(H H)−1HT − 1l 1l1l (5) Lt = I− 1l 1l1l , (6) where H = {0, 1}l×C is an indicator matrix: Hij = 1 if xi belongs to the j-th class, and Hij = 0 otherwise.”
Spectral regression: a unified subspace learning framework for content-based image retrieval (2007, background): “When the labeled data points Xl are centered, we have XlX l = St and XlWl×lX l = Sb [12], where St is the total scatter matrix and Sb is the between-class scatter matrix [4].”
Fast Robust PCA on Graphs (2015, positive): “A similar idea is also the motivation of the Laplacianfaces algorithm [13].”
Maximum Correntropy Criterion for Robust Face Recognition (2011, result): “Along this line, Wright et al. [24] recently proposed a sparse representation classifier (SRC) for robust face recognition against occlusions and corruptions, and impressive results were reported as compared to many wellknown face recognition methods [1], [2], [25].”
Robust Face Recognition via Sparse Representation (2009, background): “…the given n i training samples from the i -th class as columns of a matrix In the context of face recognition, we will identify a w × h grayscale image with the vector v ∈ R m ( m = wh ) given by stacking its columns; the columns of A i are then the training face images of the i -th subject.”
Binary Multi-View Clustering (2019, methodology): “Spectral clustering (SC) [2], [8] is another most successful singleview clustering method.”
A General Exponential Framework for Dimensionality Reduction (2014, methodology): “To address the problem, laplacianfaces [16] uses PCA to reduce the dimension, and then applies LPP.”
Controllable Face Privacy (2015, neutral): “Fisherfaces [3], Laplacianfaces [12] and Tensorface [21].”
Bregman Divergence-Based Regularization for Transfer Subspace Learning (2010, background): “C ONVENTIONAL algorithms [2], [4], [15] for image and video data analysis and organization perform well under the assumption that training and testing samples are independent and identically distributed (i.i.d.).”
Efficient kNN Classification With Different Numbers of Nearest Neighbors (2018, neutral): “manifold learning methods [50], [57], [58].”
Frankenstein: Learning Deep Face Representations Using Small Data (2016, neutral): “Conventional features include linear functions of the raw pixel values, including Eigenface (Principal Component Analysis) [59], Fisherface (Linear Discriminant Analysis) [3], and Laplacianface (Locality Preserving Projection) [14].”