scispace - formally typeset
Search or ask a question
Author

Matthew Turk

Bio: Matthew Turk is an academic researcher from Toyota Technological Institute at Chicago. The author has contributed to research in topics: Augmented reality & Facial recognition system. The author has an hindex of 55, co-authored 198 publications receiving 30972 citations. Previous affiliations of Matthew Turk include Massachusetts Institute of Technology & University of California.


Papers
More filters
TL;DR: In this article , the authors quantify the temporal variability and image morphology of the horizon-scale emission from Sgr A*, as observed by the EHT in 2017 April at a wavelength of 1.3 mm.
Abstract: In this paper we quantify the temporal variability and image morphology of the horizon-scale emission from Sgr A*, as observed by the EHT in 2017 April at a wavelength of 1.3 mm. We find that the Sgr A* data exhibit variability that exceeds what can be explained by the uncertainties in the data or by the effects of interstellar scattering. The magnitude of this variability can be a substantial fraction of the correlated flux density, reaching ∼100% on some baselines. Through an exploration of simple geometric source models, we demonstrate that ring-like morphologies provide better fits to the Sgr A* data than do other morphologies with comparable complexity. We develop two strategies for fitting static geometric ring models to the time-variable Sgr A* data; one strategy fits models to short segments of data over which the source is static and averages these independent fits, while the other fits models to the full data set using a parametric model for the structural variability power spectrum around the average source structure. Both geometric modeling and image-domain feature extraction techniques determine the ring diameter to be 51.8 ± 2.3 μas (68% credible intervals), with the ring thickness constrained to have an FWHM between ∼30% and 50% of the ring diameter. To bring the diameter measurements to a common physical scale, we calibrate them using synthetic data generated from GRMHD simulations. This calibration constrains the angular size of the gravitational radius to be 4.8−0.7+1.4 μas, which we combine with an independent distance measurement from maser parallaxes to determine the mass of Sgr A* to be 4.0−0.6+1.1×106 M ⊙.

99 citations

Journal ArticleDOI
TL;DR: A framework of face recognition by adding NMF constraint and classifier constraints to matrix factorization to get both intuitive features and good recognition results is proposed and two novel subspace methods are presented.
Abstract: Non-negative Matrix Factorization (NMF) is a part-based image representation method which adds a non-negativity constraint to matrix factorization. NMF is compatible with the intuitive notion of combining parts to form a whole face. In this paper, we propose a framework of face recognition by adding NMF constraint and classifier constraints to matrix factorization to get both intuitive features and good recognition results. Based on the framework, we present two novel subspace methods: Fisher Non-negative Matrix Factorization (FNMF) and PCA Non-negative Matrix Factorization (PNMF). FNMF adds both the non-negative constraint and the Fisher constraint to matrix factorization. The Fisher constraint maximizes the between-class scatter and minimizes the within-class scatter of face samples. Subsequently, FNMF improves the capability of face recognition. PNMF adds the non-negative constraint and characteristics of PCA, such as maximizing the variance of output coordinates, orthogonal bases, etc. to matrix factorization. Therefore, we can get intuitive features and desirable PCA characteristics. Our experiments show that FNMF and PNMF achieve better face recognition performance than NMF and Local NMF.

98 citations

Book ChapterDOI
16 Oct 2005
TL;DR: A novel framework for automatic 3D facial expression analysis in videos and searches over a probabilistic expression model on the generalized manifold for optimal replacement with the ‘target’ expression to synthesize images of the new expression with the current head pose.
Abstract: We introduce a novel framework for automatic 3D facial expression analysis in videos. Preliminary results demonstrate editing facial expression with facial expression recognition. We first build a 3D expression database to learn the expression space of a human face. The real-time 3D video data were captured by a camera/projector scanning system. From this database, we extract the geometry deformation independent of pose and illumination changes. All possible facial deformations of an individual make a nonlinear manifold embedded in a high dimensional space. To combine the manifolds of different subjects that vary significantly and are usually hard to align, we transfer the facial deformations in all training videos to one standard model. Lipschitz embedding embeds the normalized deformation of the standard model in a low dimensional generalized manifold. We learn a probabilistic expression model on the generalized manifold. To edit a facial expression of a new subject in 3D videos, the system searches over this generalized manifold for optimal replacement with the ‘target’ expression, which will be blended with the deformation in the previous frames to synthesize images of the new expression with the current head pose. Experimental results show that our method works effectively.

94 citations

Proceedings ArticleDOI
23 Aug 2004
TL;DR: Analysis of the in-plane rotational robustness of the Viola-Jones object detection method when used for hand appearance detection finds that randomly rotating the training data within these bounds allows for detection rates about one order of magnitude better than those trained on strictly aligned data.
Abstract: The research described in this paper analyzes the in-plane rotational robustness of the Viola-Jones object detection method when used for hand appearance detection We determine the rotational bounds for training and detection for achieving undiminished performance without an increase in classifier complexity The result - up to 15/spl deg/ total - differs from the method's performance on faces (30/spl deg/ total) We found that randomly rotating the training data within these bounds allows for detection rates about one order of magnitude better than those trained on strictly aligned data The implications of the results effect both savings in training costs as well as increased naturalness and comfort of vision-based hand gesture interfaces

93 citations

Journal ArticleDOI
TL;DR: There are still obstacles to achieving general, robust, high-performance computer vision systems, but the last decade has seen significant progress in vision technologies for human-computer interaction.
Abstract: There are still obstacles to achieving general, robust, high-performance computer vision systems. The last decade, however, has seen significant progress in vision technologies for human-computer interaction.

89 citations


Cited by
More filters
Journal ArticleDOI
22 Dec 2000-Science
TL;DR: An approach to solving dimensionality reduction problems that uses easily measured local metric information to learn the underlying global geometry of a data set and efficiently computes a globally optimal solution, and is guaranteed to converge asymptotically to the true structure.
Abstract: Scientists working with large volumes of high-dimensional data, such as global climate patterns, stellar spectra, or human gene distributions, regularly confront the problem of dimensionality reduction: finding meaningful low-dimensional structures hidden in their high-dimensional observations. The human brain confronts the same problem in everyday perception, extracting from its high-dimensional sensory inputs-30,000 auditory nerve fibers or 10(6) optic nerve fibers-a manageably small number of perceptually relevant features. Here we describe an approach to solving dimensionality reduction problems that uses easily measured local metric information to learn the underlying global geometry of a data set. Unlike classical techniques such as principal component analysis (PCA) and multidimensional scaling (MDS), our approach is capable of discovering the nonlinear degrees of freedom that underlie complex natural observations, such as human handwriting or images of a face under different viewing conditions. In contrast to previous algorithms for nonlinear dimensionality reduction, ours efficiently computes a globally optimal solution, and, for an important class of data manifolds, is guaranteed to converge asymptotically to the true structure.

13,652 citations

Journal ArticleDOI
TL;DR: A face recognition algorithm which is insensitive to large variation in lighting direction and facial expression is developed, based on Fisher's linear discriminant and produces well separated classes in a low-dimensional subspace, even under severe variations in lighting and facial expressions.
Abstract: We develop a face recognition algorithm which is insensitive to large variation in lighting direction and facial expression. Taking a pattern classification approach, we consider each pixel in an image as a coordinate in a high-dimensional space. We take advantage of the observation that the images of a particular face, under varying illumination but fixed pose, lie in a 3D linear subspace of the high dimensional image space-if the face is a Lambertian surface without shadowing. However, since faces are not truly Lambertian surfaces and do indeed produce self-shadowing, images will deviate from this linear subspace. Rather than explicitly modeling this deviation, we linearly project the image into a subspace in a manner which discounts those regions of the face with large deviation. Our projection method is based on Fisher's linear discriminant and produces well separated classes in a low-dimensional subspace, even under severe variation in lighting and facial expressions. The eigenface technique, another method based on linearly projecting the image space to a low dimensional subspace, has similar computational requirements. Yet, extensive experimental results demonstrate that the proposed "Fisherface" method has error rates that are lower than those of the eigenface technique for tests on the Harvard and Yale face databases.

11,674 citations

Journal ArticleDOI
21 Oct 1999-Nature
TL;DR: An algorithm for non-negative matrix factorization is demonstrated that is able to learn parts of faces and semantic features of text and is in contrast to other methods that learn holistic, not parts-based, representations.
Abstract: Is perception of the whole based on perception of its parts? There is psychological and physiological evidence for parts-based representations in the brain, and certain computational theories of object recognition rely on such representations. But little is known about how brains or computers might learn the parts of objects. Here we demonstrate an algorithm for non-negative matrix factorization that is able to learn parts of faces and semantic features of text. This is in contrast to other methods, such as principal components analysis and vector quantization, that learn holistic, not parts-based, representations. Non-negative matrix factorization is distinguished from the other methods by its use of non-negativity constraints. These constraints lead to a parts-based representation because they allow only additive, not subtractive, combinations. When non-negative matrix factorization is implemented as a neural network, parts-based representations emerge by virtue of two properties: the firing rates of neurons are never negative and synaptic strengths do not change sign.

11,500 citations

Journal ArticleDOI
TL;DR: This work considers the problem of automatically recognizing human faces from frontal views with varying expression and illumination, as well as occlusion and disguise, and proposes a general classification algorithm for (image-based) object recognition based on a sparse representation computed by C1-minimization.
Abstract: We consider the problem of automatically recognizing human faces from frontal views with varying expression and illumination, as well as occlusion and disguise. We cast the recognition problem as one of classifying among multiple linear regression models and argue that new theory from sparse signal representation offers the key to addressing this problem. Based on a sparse representation computed by C1-minimization, we propose a general classification algorithm for (image-based) object recognition. This new framework provides new insights into two crucial issues in face recognition: feature extraction and robustness to occlusion. For feature extraction, we show that if sparsity in the recognition problem is properly harnessed, the choice of features is no longer critical. What is critical, however, is whether the number of features is sufficiently large and whether the sparse representation is correctly computed. Unconventional features such as downsampled images and random projections perform just as well as conventional features such as eigenfaces and Laplacianfaces, as long as the dimension of the feature space surpasses certain threshold, predicted by the theory of sparse representation. This framework can handle errors due to occlusion and corruption uniformly by exploiting the fact that these errors are often sparse with respect to the standard (pixel) basis. The theory of sparse representation helps predict how much occlusion the recognition algorithm can handle and how to choose the training images to maximize robustness to occlusion. We conduct extensive experiments on publicly available databases to verify the efficacy of the proposed algorithm and corroborate the above claims.

9,658 citations

01 Jan 1999
TL;DR: In this article, non-negative matrix factorization is used to learn parts of faces and semantic features of text, which is in contrast to principal components analysis and vector quantization that learn holistic, not parts-based, representations.
Abstract: Is perception of the whole based on perception of its parts? There is psychological and physiological evidence for parts-based representations in the brain, and certain computational theories of object recognition rely on such representations. But little is known about how brains or computers might learn the parts of objects. Here we demonstrate an algorithm for non-negative matrix factorization that is able to learn parts of faces and semantic features of text. This is in contrast to other methods, such as principal components analysis and vector quantization, that learn holistic, not parts-based, representations. Non-negative matrix factorization is distinguished from the other methods by its use of non-negativity constraints. These constraints lead to a parts-based representation because they allow only additive, not subtractive, combinations. When non-negative matrix factorization is implemented as a neural network, parts-based representations emerge by virtue of two properties: the firing rates of neurons are never negative and synaptic strengths do not change sign.

9,604 citations