Contributions to unsupervised and supervised learning with applications in digital image processing

311 p. : il.

A practical system for modelling body shapes from single view measurements

This paper describes an interactive system for quickly modelling 3D body shapes from a single image. It provides the user with a convenient way to obtain their 3D body shapes so as to try on virtual garments online. For the ease of use, we first introduce a novel interface for users to conveniently extract anthropometric measurements from a single photo, while using readily available scene cues for automatic image rectification. Then, we propose a unified probabilistic framework using Gaussian processes, which predict the body parameters from input measurements while correcting the aspect ratio ambiguity resulting from photo rectification. Extensive experiments and user studies have supported the efficacy of our system. This system is now being exploited commercially online1. © 2011. The copyright of this document resides with its authors.

Inferring 3D Structure with a Statistical Image-Based Shape Model

We present an image-based approach to infer 3D structure parameters using a probabilistic "shape+structure'' model. The 3D shape of a class of objects may be represented by sets of contours from silhouette views simultaneously observed from multiple calibrated cameras. Bayesian reconstructions of new shapes can then be estimated using a prior density constructed with a mixture model and probabilistic principal components analysis. We augment the shape model to incorporate structural features of interest; novel examples with missing structure parameters may then be reconstructed to obtain estimates of these parameters. Model matching and parameter inference are done entirely in the image domain and require no explicit 3D construction. Our shape model enables accurate estimation of structure despite segmentation errors or missing views in the input silhouettes, and works even with only a single input view. Using a dataset of thousands of pedestrian images generated from a synthetic model, we can perform accurate inference of the 3D locations of 19 joints on the body based on observed silhouette contours from real images.

Estimating 3D Body Pose Using Uncalibrated Cameras

An approach for estimating 3D body pose from multiple, uncalibrated views is proposed. First, a mapping from image features to 2D body joint locations is computed using a statistical framework that yields a set of several body pose hypotheses. The concept of a "virtual camera" is introduced that makes this mapping invariant to translation, image-plane rotation, and scaling of the input. As a consequence, the calibration matrices (intrinsics) of the virtual cameras can be considered completely known, and their poses are known up to a single angular displacement parameter. Given pose hypotheses obtained in the multiple virtual camera views, the recovery of 3D body pose and camera relative orientations is formulated as a stochastic optimization problem. An Expectation-Maximization algorithm is derived that can obtain the locally most likely (self-consistent) combination of body pose hypotheses. Performance of the approach is evaluated with synthetic sequences as well as real video sequences of human motion.

Specialized Mappings Architecture with Applications to Vision-based Estimation of Articulated Body Pose

A fundamental task of vision systems is to infer the state of the world given some form of visual observations. From a computational perspective, this often involves facing an ill-posed problem; e.g., information is lost via projection of the 3D world into a 2D image. Solution of an ill-posed problem requires additional information, usually provided as a model of the underlying process. It is important that the model be both computationally feasible as well as theoretically well-founded. In this thesis, a probabilistic, nonlinear supervised computational learning model is proposed: the Specialized Mappings Architecture (SMA). The SMA framework is demonstrated in a computer vision system that can estimate the articulated pose parameters of a human body or human hands, given images obtained via one or more uncalibrated cameras. The SMA consists of several specialized forward mapping functions that are estimated automatically from training data, and a possibly known feedback function. Each specialized function maps certain domains of the input space (e.g., image features) onto the output space (e.g., articulated body parameters). A probabilistic model for the architecture is first formalized. Solutions to key algorithmic problems are then derived: simultaneous learning of the specialized domains along with the mapping functions, as well as performing inference given inputs and a feedback function. The SMA employs a variant of the Expectation-Maximization algorithm and approximate inference. The approach allows the use of alternative conditional independence assumptions for learning and inference, which are derived from a forward model and a feedback model. Experimental validation of the proposed approach is conducted in the task of estimating articulated body pose from image silhouettes. Accuracy and stability of the SMA framework is tested using artificial data sets, as well as synthetic and real video sequences of human bodies and hands.

Inferring Body Pose without Tracking Body Parts

A novel approach for estimating articulated body posture and motion from monocular video sequences is proposed. Human pose is defined as the instantaneous two dimensional configuration (i.e., the projection onto the image plane) of a single articulated body in terms of the position of a predetermined set of joints. First, statistical segmentation of the human bodies from the background is performed and low-level visual features are found given the segmented body shape. The goal is to be able to map these, generally low level, visual features to body configurations. The system estimates different mappings, each one with a specific cluster in the visual feature space. Given a set of body motion sequences for training, unsupervised clustering is obtained via the Expectation Maximation algorithm. Then, for each of the clusters, a function is estimated to build the mapping between low-level features to 3D pose. Currently this mapping is modeled by a neural network. Given new visual features, a mapping from each cluster is performed to yield a set of possible poses. From this set, the system selects the most likely pose given the learned probability distribution and the visual feature similarity between hypothesis and input. Performance of the proposed approach is characterized using a new set of known body postures, showing promising results.

Fixational Instability and Natural Image Statistics: Implications for Early Visual Representations

Under natural viewing conditions small movements of the eye, head, and body prevent the maintenance of a steady direction of gaze. It is known that stimuli tend to fade when they a restabilized on the retina for several seconds. However; it is unclear whether the physiological motion of the retinal image serves a visual purpose during the brief periods of natural visual fixation. This study examines the impact of fixational instability on the statistics of the visua1 input to the retina and on the structure of neural activity in the early visual system. We show that fixational instability introduces a component in the retinal input signals that in the presence of natural images, lacks spatial correlations. This component strongly influences neural activity in a model of the LGN. It decorrelates cell responses even if the contrast sensitivity functions of simulated cells arc not perfectly tuned to counterbalance the power-law spectrum of natural images. A decorrelation of neural activity at the early stages of the visual system has been proposed to be beneficial for discarding statistical redundancies in the input signals. The results of this study suggest that fixational instability might contribute to establishing efficient representations of natural stimuli.

The effects of curcumin (diferuloylmethane) on body composition of patients with advanced pancreatic cancer.

BACKGROUND: Curcumin is a natural product that is often explored by patients with cancer. Weight loss due to fat and muscle depletion is a hallmark of pancreatic cancer and is associated with worse outcomes. Studies of curcumin's effects on muscularity show conflicting results in animal models. METHODS AND RESULTS: Retrospective matched 1:2 case-control study to evaluate the effects of curcumin on body composition (determined by computerized tomography) of 66 patients with advanced pancreatic cancer (22 treated,44 controls). Average age (SEM) was 63(1.8) years, 30/66(45%) women, median number of prior therapies was 2, median (IQR) time from advanced pancreatic cancer diagnosis to baseline image was 7(2-13.5) months (p>0.2, all variables). All patients lost weight (3.3% and 1.3%, treated vs. control, p=0.13). Treated patients lost more muscle (median [IQR] percent change -4.8[-9.1,-0.1] vs. -0.05%[-4.2, 2.6] in controls,p<0.001) and fat (median [IQR] percent change -6.8%[-15,-0.6] vs. -4.0%[-7.6, 1.3] in controls,p=0.04). Subcutaneous fat was more affected in the treated patients. Sarcopenic patients treated with curcumin(n=15) had survival of 169(115-223) days vs. 299(229-369) sarcopenic controls(p=0.024). No survival difference was found amongst non-sarcopenic patients. CONCLUSIONS: Patients with advanced pancreatic cancer treated with curcumin showed significantly greater loss of subcutaneous fat and muscle than matched untreated controls.

The idea, the machine, and the art: word and image in the 21st century

Taking in recent advances in neuroscience and digital technology, Gander and Garland assess the state of the inter-arts in America and the Western world, exploring and questioning the primacy of affect in an increasingly hypertextual everyday environment. In this analysis they signal a move beyond W. J. T. Mitchell’s coinage of the ‘imagetext’ to an approach that centres the reader-viewer in a recognition, after John Dewey, of ‘art as experience’. New thinking in cognitive and computer sciences about the relationship between the body and the mind challenges any established definitions of ‘embodiment’, ‘materiality’, ‘virtuality’ and even ‘intelligence, they argue, whilst ‘Extended Mind Theory’, they note, marries our cognitive processes with the material forms with which we engage, confirming and complicating Marshall McLuhan’s insight, decades ago, that ‘all media are “extensions of man”’. In this chapter, Gander and Garland open paths and suggest directions into understandings and critical interpretations of new and emerging imagetext worlds and experiences.

Photograph - Governor General's Body Guard at Camp Niagara

Black and white photograph, mounted on board, 18 ½ cm. x 23 ½ cm. of the G.G.B.G. [Governor General’s Body Guard] on horseback at Camp Niagara.

Photograph - B Squadron of the G.G.B.G. [Governor General’s Body Guard] at Niagara

Black and white photograph, mounted on board, 13 cm x 20 cm of the B Squadron of the G.G.B.G. [Governor General’s Body Guard] at Niagara.

Le corps duel dans les Aveux non avenus de Claude Cahun : à la jonction du texte et de l'image

Dans ce mémoire, nous étudions la représentation du corps dans Aveux non avenus de Claude Cahun. Évoquant dans un premier temps quelques grands axes de l’histoire de la réflexion sur le corps et de sa représentation en Occident depuis l’Antiquité, en fonction de leur fécondité pour l’analyse de l’oeuvre de Cahun, nous procédons dans un deuxième temps à une analyse de la représentation du corps dans les fragments de texte qui composent Aveux non avenus, en insistant d’une part sur le rapport ambivalent au corps qui y est exprimé et d’autre part sur la relation étroite qui lie le corps à la problématique identitaire, centrale dans tout l’oeuvre cahunien. Nous étudions ensuite la façon dont le corps est représenté, en nous intéressant à l’écriture particulière que déploie Cahun dans les Aveux ainsi qu’à la démarche intermédiale qu’elle met en place à travers la présence des photomontages au sein du texte. Nous souhaitons ainsi démontrer que la représentation du corps est indissociable d’une réflexion sur l’identité et que le caractère double de cette représentation à travers le texte et l’image complexifie cette réflexion sans lui enlever sa cohérence.

Facteurs de risque individuels et relationnels de l'insatisfaction par rapport à l'image corporelle à l'adolescence

Mémoire numérisé par la Division de la gestion de documents et des archives de l'Université de Montréal