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.

Large Scale SfM with the Distributed Camera Model

Abstract: We introduce the distributed camera model, a novel model for Structure-from-Motion (SfM). This model describes image observations in terms of light rays with ray origins and directions rather than pixels. As such, the proposed model is capable of describing a single camera or multiple cameras simultaneously as the collection of all light rays observed. We show how the distributed camera model is a generalization of the standard camera model and we describe a general formulation and solution to the absolute camera pose problem that works for standard or distributed cameras. The proposed method computes a solution that is up to 8 times more efficient and robust to rotation singularities in comparison with gDLS[21]. Finally, this method is used in an novel large-scale incremental SfM pipeline where distributed cameras are accurately and robustly merged together. This pipeline is a direct generalization of traditional incremental SfM, however, instead of incrementally adding one camera at a time to grow the reconstruction the reconstruction is grown by adding a distributed camera. Our pipeline produces highly accurate reconstructions efficiently by avoiding the need for many bundle adjustment iterations and is capable of computing a 3D model of Rome from over 15,000 images in just 22 minutes.

CLEAR: Cumulative LEARning for One-Shot One-Class Image Recognition

Abstract: This work addresses the novel problem of one-shot one-class classification. The goal is to estimate a classification decision boundary for a novel class based on a single image example. Our method exploits transfer learning to model the transformation from a representation of the input, extracted by a Convolutional Neural Network, to a classification decision boundary. We use a deep neural network to learn this transformation from a large labelled dataset of images and their associated class decision boundaries generated from ImageNet, and then apply the learned decision boundary to classify subsequent query images. We tested our approach on several benchmark datasets and significantly outperformed the baseline methods.

The Postural Comfort Zone for Reaching Gestures

Abstract: We have proposed a method for objective assessment of postural comfort (Kolsch et al, 2003) We defined comfort as the range of postures that is voluntarily assumed despite the availability of other postures Designing user interfaces within the limits of comfort zones can avert risks associated with unknown alternative use patters of the interfaceHere we report on a user study that investigated the comfort zone for free-hand gestures in the horizontal plane at about stomach height This space is of particular interest to novel technologies such as gesture recognition and virtual reality The results are in line with previous studies on postural discomfort, but improve on resolution and are not based on subjective, questionnaire-based data acquisition This study also serves as an example for how to design studies for comfort evaluation

The Autonomous Land Vehicle (ALV) Preliminary Road-Following Demonstration

Abstract: The ALV project is sponsored by the Defense Advanced Research Project Agency (DARPA) as part of its Strategic Computing Program and contracted through the Army Engineer Topo-graphic Laboratories (ETL) under contract DACA76-84-C-0005. The purpose of the strategic computing program is to advance the state of the art in artificial intelligence, image understanding, and advanced computer architectures and to demonstrate the applicability of these technologies to advanced military systems.1© (1985) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Real-time view-based face alignment using active wavelet networks

Abstract: The active wavelet network (AWN) [C. Hu et al., (2003)] approach was recently proposed for automatic face alignment, showing advantages over active appearance models (AAM), such as more robustness against partial occlusions and illumination changes. We (1) extend the AWN method to a view-based approach, (2) verify the robustness of our algorithm with respect to unseen views in a large dataset and (3) show that using only nine wavelets, our method yields similar performance to state-of-the-art face alignment systems, with a significant enhancement in terms of speed. After optimization, our system requires only 3 ms per iteration on a 1.6 GHz Pentium IV. We show applications in face alignment for recognition and real-time facial feature tracking under large pose variations.

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.