In this thesis, I explore region detection and consider its impact on image matching for exemplar-based object recognition. Detecting regions is important to provide semantically meaningful spatial cues in images. Matching establishes similarity between visual entities, which is crucial for recognition. My thesis starts by detecting regions in both local and object level. Then, I leverage geometric cues of the detected regions to improve image matching for the ultimate goal of object recognition. More specifically, my thesis considers four key questions: 1) how can we extract distinctively-shaped local regions that also ensure repeatability for robust matching? 2) how can object-level shape inform bottom-up image segmentation? 3) how should the spatial layout imposed by segmented regions influence image matching for exemplar-based recognition? and 4) how can we exploit regions to improve the accuracy and speed of dense image matching? I propose novel algorithms to tackle these issues, addressing region-based visual perception from low-level local region extraction, to mid-level object segmentation, to high-level region-based matching and recognition. First, I propose a Boundary Preserving Local Region (BPLR) detector to extract local shapes. My approach defines a novel spanning-tree based image representation whose structure reflects shape cues combined from multiple segmentations, which in turn provide multiple initial hypotheses of the object boundaries. Unlike traditional local region detectors that rely on local cues like color and texture, BPLRs explicitly exploit the segmentation that encodes global object shape. Thus, they respect object boundaries more robustly and reduce noisy regions that straddle object boundaries. The resulting detector yields a dense set of local regions that are both distinctive in shape as well as repeatable for robust matching. Second, building on the strength of the BPLR regions, I develop an approach for object-level segmentation. The key insight of the approach is that objects shapes are (at least partially) shared among different object categories--for example, among different animals, among different vehicles, or even among seemingly different objects. This shape sharing phenomenon allows us to use partial shape matching via BPLR-detected regions to predict global object shape of possibly unfamiliar objects in new images. Unlike existing top-down methods, my approach requires no category-specific knowledge on the object to be segmented. In addition, because it relies on exemplar-based matching to generate shape hypotheses, my approach overcomes the viewpoint sensitivity of existing methods by allowing shape exemplars to span arbitrary poses and classes. For the ultimate goal of region-based recognition, not only is it important to detect good regions, but we must also be able to match them reliably. A matching establishes similarity between visual entities (images, objects or scenes), which is fundamental for visual recognition. Thus, in the third major component of this thesis, I explore how to leverage geometric cues of the segmented regions for accurate image matching. To this end, I propose a segmentation-guided local feature matching strategy, in which segmentation suggests spatial layout among the matched local features within each region. To encode such spatial structures, I devise a string representation whose 1D nature enables efficient computation to enforce geometric constraints. The method is applied for exemplar-based object classification to demonstrate the impact of my segmentation-driven matching approach. Finally, building on the idea of regions for geometric regularization in image matching, I consider how a hierarchy of nested image regions can be used to constrain dense image feature matches at multiple scales simultaneously. Moving beyond individual regions, the last part of my thesis studies how to exploit regions' inherent hierarchical structure to improve the image matching. To this end, I propose a deformable spatial pyramid graphical model for image matching. The proposed model considers multiple spatial extents at once--from an entire image to grid cells to every single pixel. The proposed pyramid model strikes a balance between robust regularization by larger spatial supports on the one hand and accurate localization by finer regions on the other. Further, the pyramid model is suitable for fast coarse-to-fine hierarchical optimization. I apply the method to pixel label transfer tasks for semantic image segmentation, improving upon the state-of-the-art in both accuracy and speed. Throughout, I provide extensive evaluations on challenging benchmark datasets, validating the effectiveness of my approach. In contrast to traditional texture-based object recognition, my region-based approach enables to use strong geometric cues such as shape and spatial layout that advance the state-of-the-art of object recognition. Also, I show that regions' inherent hierarchical structure allows fast image matching for scalable recognition. The outcome realizes the promising potential of region-based visual perception. In addition, all my codes for local shape detector, object segmentation, and image matching are publicly available, which I hope will serve as useful new additions for vision researchers' toolbox. / text

Geologic sequestration of CO₂ in deep saline aquifers has been studied extensively over the past two decades as a viable method of reducing anthropological carbon emissions. The monitoring and prediction of the movement of injected CO₂ is important for assessing containment of the gas within the storage volume, and taking corrective measures if required. Given the uncertainty in geologic architecture of the storage aquifers, it is reasonable to depict our prior knowledge of the project area using a vast suite of aquifer models. Simulating such a large number of models using traditional numerical flow simulators to evaluate uncertainty is computationally expensive. A novel stochastic workflow for characterizing the plume migration, based on a model selection algorithm developed by Mantilla in 2011, has been implemented. The approach includes four main steps: (1) assessing the connectivity/dynamic characteristics of a large prior ensemble of models using proxies; (2) model clustering using the principle component analysis or multidimensional scaling coupled with the k-mean clustering approach; (3) model selection using the Bayes' rule on the reduced model space, and (4) model expansion using an ensemble pattern-based matching scheme. In this dissertation, two proxies have been developed based on particle tracking in order to assess the flow connectivity of models in the initial set. The proxies serve as fast approximations of finite-difference flow simulation models, and are meant to provide rapid estimations of connectivity of the aquifer models. Modifications have also been implemented within the model selection workflow to accommodate the particular problem of application to a carbon sequestration project. The applicability of the proxies is tested both on synthetic models and real field case studies. It is demonstrated that the first proxy captures areal migration to a reasonable extent, while failing to adequately capture vertical buoyancy-driven flow of CO₂. This limitation of the proxy is addressed in the second proxy, and its applicability is demonstrated not only in capturing horizontal migration but also in buoyancy-driven flow. Both proxies are tested both as standalone approximations of numerical simulation and within the larger model selection framework. / text

published_or_final_version / Economics and Finance / Doctoral / Doctor of Philosophy

The prevalence of obesity has necessitated developing safe and convenient tools for timely assessing and monitoring this condition for a broad range of population. Three-dimensional (3D) body imaging has become a new mean for obesity assessment. Moreover, it generates body shape information that is meaningful for fitness, ergonomics, and personalized clothing. In the previous work of our lab, we developed a prototype active stereo vision system that demonstrated a potential to fulfill this goal. But the prototype required four computer projectors to cast artificial textures on the body which facilitate the stereo-matching on texture-deficient images (e.g., skin). This decreases the mobility of the system when used to collect a large population data. In addition, the resolution of the generated 3D~images is limited by both cameras and projectors available during the project. The study reported in this dissertation highlights our continued effort in improving the capability of 3Dbody imaging through simplified hardware for passive stereo and advanced computation techniques. The system utilizes high-resolution single-lens reflex (SLR) cameras, which became widely available lately, and is configured in a two-stance design to image the front and back surfaces of a person. A total of eight cameras are used to form four pairs of stereo units. Each unit covers a quarter of the body surface. The stereo units are individually calibrated with a specific pattern to determine cameras' intrinsic and extrinsic parameters for stereo matching. The global orientation and position of each stereo unit within a common world coordinate system is calculated through a 3Dregistration step. The stereo calibration and 3Dregistration procedures do not need to be repeated for a deployed system if the cameras' relative positions have not changed. This property contributes to the portability of the system, and tremendously alleviates the maintenance task. The image acquisition time is around two seconds for a whole-body capture. The system works in an indoor environment with a moderate ambient light. Advanced stereo computation algorithms are developed by taking advantage of high-resolution images and by tackling the ambiguity problem in stereo matching. A multi-scale, coarse-to-fine matching framework is proposed to match large-scale textures at a low resolution and refine the matched results over higher resolutions. This matching strategy reduces the complexity of the computation and avoids ambiguous matching at the native resolution. The pixel-to-pixel stereo matching algorithm follows a classic, four-step strategy which consists of matching cost computation, cost aggregation, disparity computation and disparity refinement. The system performance has been evaluated on mannequins and human subjects in comparison with other measurement methods. It was found that the geometrical measurements from reconstructed 3Dbody models, including body circumferences and whole volume, are highly repeatable and consistent with manual and other instrumental measurements (CV < 0.1$%, R2>0.99). The agreement of percent body fat (%BF) estimation on human subjects between stereo and dual-energy X-ray absorptiometry (DEXA) was found to be improved over the previous active stereo system, and the limits of agreement with 95% confidence were reduced by half. Our achieved %BF estimation agreement is among the lowest ones of other comparative studies with commercialized air displacement plethysmography (ADP) and DEXA. In practice, %BF estimation through a two-component model is sensitive to body volume measurement, and the estimation of lung volume could be a source of variation. Protocols for this type of measurement should still be created with an awareness of this factor. / text

Image features play important roles in a wide range of computer vision applications, such as image registration, 3D reconstruction, object detection and video understanding. These image features include edges, contours, corners, regions, lines, curves, interest points, etc. However, the research is fragmented in these areas, especially when it comes to line and curve detection. In this thesis, we aim to discover, integrate, evaluate and summarize past research as well as our contributions in the area of image features. This thesis provides a comprehensive framework of concept, evaluation, implementation, and applications for image features. Firstly, this thesis proposes a novel concept of interest curves. Interest curves is a concept derived and extended from interest points. Interest curves are significant lines and arcs in an image that are repeatable under various image transformations. Interest curves bring clear guidelines and structures for future curve and line detection algorithms and related applications. Secondly, this thesis presents an evaluation framework for detecting and describing interest curves. The evaluation framework provides a new paradigm for comparing the performance of state-of-the-art line and curve detectors under image perturbations and transformations. Thirdly, this thesis proposes an interest curve detector (Distinctive Curves, DICU), which unifies the detection of edges, corners, lines and curves. DICU represents our state-of-the-art contribution in the areas concerning the detection of edges, corners, curves and lines. Our research efforts cover the most important attributes required by these features with respect to robustness and efficiency. Interest curves preserve richer geometric information than interest points. This advantage gives new ways of solving computer vision problems. We propose a simple description method for curve matching applications. We have found that our proposed interest curve descriptor outperforms all state-of-the-art interest point descriptors (SIFT, SURF, BRISK, ORB, FREAK). Furthermore, in our research we design a novel object detection algorithm that only utilizes DICU geometries without using local feature appearance. We organize image objects as curve chains and to detect an object, we search this curve chain in the target image using dynamic programming. The curve chain matching is scale and rotation-invariant as well as robust to image deformations. These properties have given us the possibility of resolving the rotation-variance problem in object detection applications. In our face detection experiments, the curve chain matching method proves to be scale and rotation-invariant and very computational efficient. / Bilddetaljer har en viktig roll i ett stort antal applikationer för datorseende, t.ex., bildregistrering, 3D-rekonstruktion, objektdetektering och videoförståelse. Dessa bilddetaljer inkluderar kanter, konturer, hörn, regioner, linjer, kurvor, intressepunkter, etc. Forskningen inom dessa områden är splittrad, särskilt för detektering av linjer och kurvor. I denna avhandling, strävar vi efter att hitta, integrera, utvärdera och sammanfatta tidigare forskning tillsammans med vår egen forskning inom området för bildegenskaper. Denna avhandling presenterar ett ramverk för begrepp, utvärdering, utförande och applikationer för bilddetaljer. För det första föreslår denna avhandling ett nytt koncept för intressekurvor. Intressekurvor är ett begrepp som härrör från intressepunkter och det är viktiga linjer och bågar i bilden som är repeterbara oberoende av olika bildtransformationer. Intressekurvor ger en tydlig vägledning och struktur för framtida algoritmer och relaterade tillämpningar för kurv- och linjedetektering. För det andra, presenterar denna avhandling en utvärderingsram för detektorer och beskrivningar av intressekurvor. Utvärderingsramverket utgör en ny paradigm för att jämföra resultatet för de bästa möjliga teknikerna för linje- och kurvdetektorer vid bildstörningar och bildtransformationer. För det tredje presenterar denna avhandling en detektor för intressekurvor (Distinctive curves, DICU), som förenar detektering av kanter, hörn, linjer och kurvor. DICU representerar vårt främsta bidrag inom området detektering av kanter, hörn, kurvor och linjer. Våra forskningsinsatser täcker de viktigaste attribut som krävs av dessa funktioner med avseende på robusthet och effektivitet. Intressekurvor innehåller en rikare geometrisk information än intressepunkter. Denna fördel öppnar för nya sätt att lösa problem för datorseende. Vi föreslår en enkel beskrivningsmetod för kurvmatchningsapplikationer och den föreslagna deskriptorn för intressekurvor överträffar de bästa tillgängliga deskriptorerna för intressepunkter (SIFT, SURF, BRISK, ORB, och FREAK). Dessutom utformar vi en ny objektdetekteringsalgoritm som bara använder geometri för DICU utan att använda det lokala utseendet. Vi organiserar bildobjekt som kurvkedjor och för att upptäcka ett objekt behöver vi endast söka efter denna kurvkedja i målbilden med hjälp av dynamisk programmering. Kurvkedjematchningen är oberoende av skala och rotationer samt robust vid bilddeformationer. Dessa egenskaper ger möjlighet att lösa problemet med rotationsberoende inom objektdetektering. Vårt ansiktsigenkänningsexperiment visar att kurvkedjematchning är oberoende av skala och rotationer och att den är mycket beräkningseffektiv. / INTRO – INteractive RObotics research network

Recent theoretical study shows that the sparsest solution to an underdetermined linear system is unique, provided the solution vector is sufficiently sparse, and the operator matrix has sufficiently incoherent column vectors. In addition, efficient algorithms have been discovered to find such solutions. This intriguing result opens a new door for many potential applications. In this thesis, we study the design of a class of greedy algorithms that are extremely efficient, e.g., Orthogonal Matching Pursuit (OMP). These greedy algorithms suffer from a stability issue that the greedy selection approach always make locally optimal decisions, thereby easily biasing and mistaking the solutions in particular under data noise. We propose a solution approach that in designing greedy algorithms, new constraints can be devised by leveraging application-specific insights and incorporated into the algorithms. Given that sparse recovery problems by definition are underdetermined, introducing additional constraints can significantly improve the stability of greedy algorithms, yet retain their efficiency. / Engineering and Applied Sciences

How to properly aggregate indirect information is more and more important. In this dissertation, we will present two aspects of the issue: indirect comparison of treatment effects and aggregation of ordered-based rank data. / Statistics

The design and use of metamaterials have shown exciting applications in electrical engineering, physics, optics, and other science fields that are expanding our physical understanding and leading to unprecedented performance of many standard devices such as antennas, microwave circuits, and sensors. The manufacturing of metamaterials, while ingenious, has typically been exotic and depended on the inclusion of sub-wavelength particles in a host medium to tailor the effective characteristics of a material. This work verifies a much more simple approach to realizing a kind of metamaterial, the epsilon-near-zero (ENZ) metamaterial. The intriguing aspect of this metamaterial is that while it is simple to realize, it is a novel approach to many practical applications such as the tunneling energy through highly discontinuous bends and abruptions, cloaking of sensors, miniaturization of microwave components, and design of highly directive antennas. Further, the physics and mathematical formulation of these ENZ materials is both intriguing and counterintuitive. / text

Diamond is a SPARQL query engine for linked data. Linked data is a sub-topic of the Semantic Web where data is represented as a labeled directed graph using the Resource Description Framework (RDF), a conceptual data model for web resources, to affect a web-wide interconnected, distributed labeled graph. SPARQL graph patterns entail portions of this distributed graph. Diamond compiles SPARQL queries into a physical query plan based on a set of newly defined operators that implement a new variant of the Rete match, a well known artificial intelligence (AI) algorithm used for complex pattern-matching problems. / text

The three chapters in this dissertation look at different aspects of the labor market and its players. The first chapter estimates the impact of using the internet for job search on job match quality. Using both the semi-parametric Meyer (1990) model and the non-parametric Hausman Woutersen (2014) hazard model, the paper finds that exit rate from employment is at least 28% lower when internet is used as a job search tool. The second chapter looks at the effect of past unemployment on future wages. It is believed that employers may use past unemployment as a signal of low productivity. In this situation workers with a history of unemployment may receive lower wages. The paper uses the Machado Mata (2005) quantile decomposition technique to decompose the wage difference into differences due to characteristics and differences due to rewards. Results indicate that workers with an unemployment spell of more than three months receive at least 12% lower wages and that more than 40% of this wage difference can be attributed to the lower rewards received by the previously unemployed.. The last chapter focuses on human capital formation and looks at some of the reasons behind the low levels of schooling India. Using the Indian Household Development Survey (2005), the paper finds that income continues to be an important factor behind the low level of primary school enrollment. On average, poor students have at least 3% lower enrollment rates, when compared to similar skilled non-poor students.