Eigenfaces for Recognition

By Matthew A. Turk, Alex Pentland. 1991

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

GAN Inversion: A Survey (2021, methodology): “PCA enforces a weak orthogonality constraint, resulting in a distributed representation that uses cancellations to capture global variability [191], [192], while VQ uses a strong winner-take-all constraint that leads to clustering the data into mutually exclusive prototypes [193].”
LabelMe: A Database and Web-Based Tool for Image Annotation (2008, background): “Many algorithms have been developed for image datasets where all training examples have the object of interest well-aligned with the other examples (Turk and Pentland 1991; Heisele et al. 2001; Viola and Jones 2001).”
Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face Recognition (2016, background): “FengandPrabhakaran proposed a system to help artists come up with makeup and hair designs that can be used to prevent FRSs (including Eigenfaces [40] and Fisherfaces [1]) from recognizing subjects [10].”
Variational Autoencoders Pursue PCA Directions (by Accident) (2018, methodology): “s (bottom) here for the linear synthetic dataset. C.3 Non-Linear VAE Eigenfaces In order to highlight the connection with PCA, we use - VAE to produce a non-linear version of the classical eigenfaces [42] on the CelebA dataset [28]. Fig7shows a discrete latent traversal. 17 Starting from the latent ”
Lifting Object Detection Datasets into 3D (2015, background): “Formerly a dominant paradigm, model-based recognition, which reasoned jointly about object identity and 3D geometry [12], [13], [14], was permanently upstaged in the 1990’s by a ﬂurry of view-based approaches [15], [16].”
Multiple Interactions Made Easy (MIME): Large Scale Demonstrations Data for Imitation (2018, background): “This is not surprising; even the early computer vision datasets initially focused on single tasks such as faces [8] and cars [9].”
Learning Face Representation from Scratch (2014, methodology): “The ﬁrst popular face recognition method is Eigen-face [27] which was proposed in 1991.”
Sum-product networks: A new deep architecture (2011, methodology): “PCA has been used extensively in previous image completion works [31].”
Beyond frontal faces: Improving Person Recognition using multiple cues (2015, background): “Face recognition There has been dramatic progress made in face recognition in the past few decades from EigenFace [34] to the state-of-art face recognition system [32] by using deep convolutional nets.”
Principal Component Analysis (2003, neutral): “The breasts and legs of 10 ducks were cut out, and the skin, fat and connective tissue were removed, leaving only the breast and leg muscles.”
Example-Based Learning for View-Based Human Face Detection (1998, neutral): “As a representative recent example, let us consider Turk and Pentland's application of PCA techniques to face recognition [19] and facial feature detection [12].”
Efficient Privacy-Preserving Face Recognition (2009, unknown): “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”
Evidence and a Computational Explanation of Cultural Differences in Facial Expression Recognition (2010, methodology): “At the next level, the gestalt level, the high-dimensional Gabor representation is reduced to a lower-dimensional representation via principal components analysis (PCA), a commonly-used optimal linear compression technique (see, for example, Kirby and Sirovich, 1990; Turk and Pentland, 1991).”
Total variation models for variable lighting face recognition (2006, methodology): “individuals. Various methods have been proposed for face recognition, including Eigenface [ 43 ],”
A new method of feature fusion and its application in image recognition (2005, methodology): “In order to explain the validity of combined feature extraction, the Eigenface (PCA) [24] method and the SVD method [25] based on single feature are given out.”
Detecting and reading text in natural scenes (2004, background): “Faces require only 15 components to achieve this variance [14].”