Face recognition using Eigenfaces

By V. Kshirsagar, M. Baviskar, M. Gaikwad. 2011

2,989 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

Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks (2017, background): “For example, Turk and Pentland’s early work pointed out that many pixels are irrelevant features in the face recognition tasks, and the face images can be projected to a feature space named eigenfaces [41].”
Diversity in Faces (2019, methodology): “The gender annotations used two class labels (male and female) and the age group labeling used seven classes ([0-3],[4-12],[13-19],[20-30],[31-45],[46-60],[61-]), as well as a continuous age value to be consistent with the automatic prediction labels.”
Principal Component Analysis (2003, neutral): “All 4 groups of raw duck meat samples and 4 groups of cooked duck meat samples were vacuumed and stored in a - 40℃ refrigerator for testing.”
Improving Generalization via Scalable Neighborhood Component Analysis (2018, background): “For example, for face recognition [41,40], new identities should be recognized after just one-time occurrence.”
CosFace: Large Margin Cosine Loss for Deep Face Recognition (2018, background): “Face recognition, as one of the most common computer vision tasks, has been extensively studied for decades [37, 45, 22, 19, 20, 40, 2].”
Surpassing Human-Level Face Verification Performance on LFW with GaussianFace (2014, methodology): “Although there has been signiﬁcant work [22, 9, 5, 14, 47, 13, 59, 50, 51, 53] on LFW and the accuracy rate has been improved from 60.02% [56] to 97.35% [53] since LFW is established in 2007, these studies have not closed the gap to human-level performance [28] in face veriﬁcation.”
Interventional Few-Shot Learning (2020, background): “2) X → C: features can be represented using (or projected onto) the manifold base linearly [60, 9] or nonlinearly [6].”
Deep Clustering for Unsupervised Learning of Visual Features (2018, methodology): “Unsupervised learning has been widely studied in the Machine Learning community [19], and algorithms for clustering, dimensionality reduction or density estimation are regularly used in computer vision applications [27, 54, 60].”
Adaptive Subspaces for Few-Shot Learning (2020, methodology): “To this end, we make another contribution and propose to construct the symmetric function using subspaces which have a long history in modeling visual data [16–19].”
PriorGAN: Real Data Prior for Generative Adversarial Nets (2020, methodology): “To reduce the computation cost, we apply PCA on the feature extracted from InceptionV3 model and keep 98% of the total variance by default.”
Gaze locking: passive eye contact detection for human-object interaction (2013, methodology): “In the ﬁnal phase, we project the high-dimensional feature vector onto a low-dimensional space via principal component analysis (PCA) [37] and multiple discriminant analysis (MDA) [11], then feed the projected vector into a support vector machine (SVM) [7] that we trained ofﬂine.”
Efficient Privacy-Preserving Face Recognition (2009, neutral): “In the most recent proposal for privacy-preserving face recognition [12] the authors use the standard and popular Eigenface [34,33] recognition algorithm and design a protocol that performs operations on encrypted images by means of homomorphic encryption schemes, more concretely, Pailler [29,11] as”
Blessing of Dimensionality: High-Dimensional Feature and Its Efficient Compression for Face Verification (2013, methodology): “It can be implemented as an unsupervised [21, 36] or supervised subspace methods [3, 10, 26].”
Multiresolution Dynamic Mode Decomposition (2015, methodology): “…performance achieved to date with an SVD-based method with multiple time-scale objects. applications such as PCA-based face recognition (eigenfaces) [21], well-cropped and centered faces for reasonable performance, i.e. translation and rotation are removed in an expensive pre-processing procedure.”
Spatial pyramid matching (2009, neutral): “The origin of many of today’s image classiﬁcation systems can be traced to empirical appearance-based methods for recognition, including subspace methods (Turk and Pentland, 1991; Murase and Nayar, 1995) and histograms (Swain and Ballard, 1991; Schiele and Crowley, 2000).”
When Face Recognition Meets with Deep Learning: An Evaluation of Convolutional Neural Networks for Face Recognition (2015, methodology): “For example, to implement eigenface [29], the features (pixel values) are usually normalised via Eq.”
Domain adaptation for object recognition: An unsupervised approach (2011, methodology): “2 d refers to the number of eigenvectors of the PCA covariance matrix that have non-zero eigenvalues.”
CVAE-GAN: Fine-Grained Image Generation through Asymmetric Training (2017, background): “Conventional wisdom and early research of generative models, including Principle Component Analysis (PCA) [40], Independent Component Analysis (ICA) [10],and the Gaussian Mixture Model (GMM) [46, 27, 37], all assume a simple formation of data.”
The CASIA NIR-VIS 2.0 Face Database (2013, methodology): “Section 5 presents the performances of baseline methods: PCA [15] and its combination with two tricks.”