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.

Characterizing the shadow space of camera-light pairs

Abstract: We present a theoretical analysis for characterizing the shadows cast by a point light source given its relative position to the camera. In particular, we analyze the epipolar geometry of camera-light pairs, including unusual camera-light configurations such as light sources aligned with the camerapsilas optical axis as well as convenient arrangements such as lights placed in the camera plane. A mathematical characterization of the shadows is derived to determine the orientations and locations of depth discontinuities when projected onto the image plane that could potentially be associated with cast shadows. The resulting theory is applied to compute a lower bound on the number of lights needed to extract all depth discontinuities from a general scene using a multiflash camera. We also provide a characterization of which discontinuities are missed and which are correctly detected by the algorithm, and a foundation for choosing an optimal light placement. Experiments with depth edges computed using two-flash setups and a four-flash setup illustrate the theory, and an additional configuration with a flash at the camerapsilas center of projection is exploited as a solution for some degenerate cases.

BLT: Balancing Long-Tailed Datasets with Adversarially-Perturbed Images

Abstract: Real visual-world datasets tend to have few classes with large numbers of samples (i.e., head classes) and many others with smaller numbers of samples (i.e., tail classes). Unfortunately, this imbalance enables a visual recognition system to perform well on head classes but poorly on tail classes. To alleviate this imbalance, we present BLT, a novel data augmentation technique that generates extra training samples for tail classes to improve the generalization performance of a classifier. Unlike prior long-tail approaches that rely on generative models (e.g., GANs or VQ-VAEs) to augment a dataset, BLT uses a gradient-ascent-based image generation algorithm that requires significantly less training time and computational resources. BLT avoids the use of dedicated generative networks, which adds significant computational overhead and require elaborate training procedures. Our experiments on natural and synthetic long-tailed datasets and across different network architectures demonstrate that BLT consistently improves the average classification performance of tail classes by \(11\%\) w.r.t. the common approach that balances the dataset by oversampling tail-class images. BLT maintains the accuracy on head classes while improving the performance on tail classes.

Human Activity Recognition Using Local Shape Descriptors

Abstract: We propose a method for human activity recognition in videos, based on shape analysis. We define local shape descriptors for interest points on the detected contour of the human action and build an action descriptor using a Bag of Features method. We also use the temporal relation among matching interest points across successive video frames. Further, an SVM is trained on these action descriptors to classify the activity in the scene. The method is invariant to the length of the video sequence, and hence it is suitable in online activity recognition. We have demonstrated the results on an action database consisting of nine actions like walk, jump, bend, etc., by twenty people, in indoor and outdoor scenarios. The proposed method achieves an accuracy of 87%, and is comparable to other state-of-the-art methods.

Automatic Head-size Equalization in Panorama Images for Video Conferencing

Abstract: In panorama images captured by omni-directional cameras during video conferencing, the image sizes of the people around the conference table are not uniform due to the varying distances to the camera. Spatially-varying-uniform (SVU) scaling functions have been proposed to warp a panorama image smoothly such that the participants have similar sizes on the image. To generate the SVU function, one needs to segment the table boundaries, which was generated manually in the previous work. In this paper, we propose a robust algorithm to automatically segment the table boundaries. To ensure the robustness, we apply a symmetry voting scheme to filter out noisy points on the edge map. Trigonometry and quadratic fitting methods are developed to fit a continuous curve to the remaining edge points. We report experimental results on both synthetic and real images

A global geometric framework for nonlinear dimensionality reduction.

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.

Eigenfaces vs. Fisherfaces: recognition using class specific linear projection

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.

Learning the parts of objects by non-negative matrix factorization

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.

Robust Face Recognition via Sparse Representation

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.

Learning parts of objects by non-negative matrix factorization

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.