An integrative approach to face and expression recognition from 3D scans

Biometrics is afield of study which pursues the association of a person's identity with his/her physiological or behavioral characteristics.^ As one aspect of biometrics, face recognition has attracted special attention because it is a natural and noninvasive means to identify individuals. Most of the previous studies in face recognition are based on two-dimensional (2D) intensity images. Face recognition based on 2D intensity images, however, is sensitive to environment illumination and subject orientation changes, affecting the recognition results. With the development of three-dimensional (3D) scanners, 3D face recognition is being explored as an alternative to the traditional 2D methods for face recognition.^ This dissertation proposes a method in which the expression and the identity of a face are determined in an integrated fashion from 3D scans. In this framework, there is a front end expression recognition module which sorts the incoming 3D face according to the expression detected in the 3D scans. Then, scans with neutral expressions are processed by a corresponding 3D neutral face recognition module. Alternatively, if a scan displays a non-neutral expression, e.g., a smiling expression, it will be routed to an appropriate specialized recognition module for smiling face recognition.^ The expression recognition method proposed in this dissertation is innovative in that it uses information from 3D scans to perform the classification task. A smiling face recognition module was developed, based on the statistical modeling of the variance between faces with neutral expression and faces with a smiling expression.^ The proposed expression and face recognition framework was tested with a database containing 120 3D scans from 30 subjects (Half are neutral faces and half are smiling faces). It is shown that the proposed framework achieves a recognition rate 10% higher than attempting the identification with only the neutral face recognition module.^

3D navigation with six degrees-of-freedom using a multi-touch display

With the introduction of new input devices, such as multi-touch surface displays, the Nintendo WiiMote, the Microsoft Kinect, and the Leap Motion sensor, among others, the field of Human-Computer Interaction (HCI) finds itself at an important crossroads that requires solving new challenges. Given the amount of three-dimensional (3D) data available today, 3D navigation plays an important role in 3D User Interfaces (3DUI). This dissertation deals with multi-touch, 3D navigation, and how users can explore 3D virtual worlds using a multi-touch, non-stereo, desktop display. ^ The contributions of this dissertation include a feature-extraction algorithm for multi-touch displays (FETOUCH), a multi-touch and gyroscope interaction technique (GyroTouch), a theoretical model for multi-touch interaction using high-level Petri Nets (PeNTa), an algorithm to resolve ambiguities in the multi-touch gesture classification process (Yield), a proposed technique for navigational experiments (FaNS), a proposed gesture (Hold-and-Roll), and an experiment prototype for 3D navigation (3DNav). The verification experiment for 3DNav was conducted with 30 human-subjects of both genders. The experiment used the 3DNav prototype to present a pseudo-universe, where each user was required to find five objects using the multi-touch display and five objects using a game controller (GamePad). For the multi-touch display, 3DNav used a commercial library called GestureWorks in conjunction with Yield to resolve the ambiguity posed by the multiplicity of gestures reported by the initial classification. The experiment compared both devices. The task completion time with multi-touch was slightly shorter, but the difference was not statistically significant. The design of experiment also included an equation that determined the level of video game console expertise of the subjects, which was used to break down users into two groups: casual users and experienced users. The study found that experienced gamers performed significantly faster with the GamePad than casual users. When looking at the groups separately, casual gamers performed significantly better using the multi-touch display, compared to the GamePad. Additional results are found in this dissertation.^

A deep learning-based approach for 3D people tracking

Questa tesi si occupa dell’estensione di un framework software finalizzato all'individuazione e al tracciamento di persone in una scena ripresa da telecamera stereoscopica. In primo luogo è rimossa la necessità di una calibrazione manuale offline del sistema sfruttando algoritmi che consentono di individuare, a partire da un fotogramma acquisito dalla camera, il piano su cui i soggetti tracciati si muovono. Inoltre, è introdotto un modulo software basato su deep learning con lo scopo di migliorare la precisione del tracciamento. Questo componente, che è in grado di individuare le teste presenti in un fotogramma, consente ridurre i dati analizzati al solo intorno della posizione effettiva di una persona, escludendo oggetti che l’algoritmo di tracciamento sarebbe portato a individuare come persone.

Practical 3D reconstruction based on photometric stereo

Photometric Stereo is a powerful image based 3D reconstruction technique that has recently been used to obtain very high quality reconstructions. However, in its classic form, Photometric Stereo suffers from two main limitations: Firstly, one needs to obtain images of the 3D scene under multiple different illuminations. As a result the 3D scene needs to remain static during illumination changes, which prohibits the reconstruction of deforming objects. Secondly, the images obtained must be from a single viewpoint. This leads to depth-map based 2.5 reconstructions, instead of full 3D surfaces. The aim of this Chapter is to show how these limitations can be alleviated, leading to the derivation of two practical 3D acquisition systems: The first one, based on the powerful Coloured Light Photometric Stereo method can be used to reconstruct moving objects such as cloth or human faces. The second, permits the complete 3D reconstruction of challenging objects such as porcelain vases. In addition to algorithmic details, the Chapter pays attention to practical issues such as setup calibration, detection and correction of self and cast shadows. We provide several evaluation experiments as well as reconstruction results. © 2010 Springer-Verlag Berlin Heidelberg.

Learning and Exploiting Camera Geometry for Computer Vision

This work explores the use of statistical methods in describing and estimating camera poses, as well as the information feedback loop between camera pose and object detection. Surging development in robotics and computer vision has pushed the need for algorithms that infer, understand, and utilize information about the position and orientation of the sensor platforms when observing and/or interacting with their environment.

The first contribution of this thesis is the development of a set of statistical tools for representing and estimating the uncertainty in object poses. A distribution for representing the joint uncertainty over multiple object positions and orientations is described, called the mirrored normal-Bingham distribution. This distribution generalizes both the normal distribution in Euclidean space, and the Bingham distribution on the unit hypersphere. It is shown to inherit many of the convenient properties of these special cases: it is the maximum-entropy distribution with fixed second moment, and there is a generalized Laplace approximation whose result is the mirrored normal-Bingham distribution. This distribution and approximation method are demonstrated by deriving the analytical approximation to the wrapped-normal distribution. Further, it is shown how these tools can be used to represent the uncertainty in the result of a bundle adjustment problem.

Another application of these methods is illustrated as part of a novel camera pose estimation algorithm based on object detections. The autocalibration task is formulated as a bundle adjustment problem using prior distributions over the 3D points to enforce the objects' structure and their relationship with the scene geometry. This framework is very flexible and enables the use of off-the-shelf computational tools to solve specialized autocalibration problems. Its performance is evaluated using a pedestrian detector to provide head and foot location observations, and it proves much faster and potentially more accurate than existing methods.

Finally, the information feedback loop between object detection and camera pose estimation is closed by utilizing camera pose information to improve object detection in scenarios with significant perspective warping. Methods are presented that allow the inverse perspective mapping traditionally applied to images to be applied instead to features computed from those images. For the special case of HOG-like features, which are used by many modern object detection systems, these methods are shown to provide substantial performance benefits over unadapted detectors while achieving real-time frame rates, orders of magnitude faster than comparable image warping methods.

The statistical tools and algorithms presented here are especially promising for mobile cameras, providing the ability to autocalibrate and adapt to the camera pose in real time. In addition, these methods have wide-ranging potential applications in diverse areas of computer vision, robotics, and imaging.

Advanced Applications of 3D Dosimetry and 3D Printing in Radiation Therapy

As complex radiotherapy techniques become more readily-practiced, comprehensive 3D dosimetry is a growing necessity for advanced quality assurance. However, clinical implementation has been impeded by a wide variety of factors, including the expense of dedicated optical dosimeter readout tools, high operational costs, and the overall difficulty of use. To address these issues, a novel dry-tank optical CT scanner was designed for PRESAGE 3D dosimeter readout, relying on 3D printed components and omitting costly parts from preceding optical scanners. This work details the design, prototyping, and basic commissioning of the Duke Integrated-lens Optical Scanner (DIOS).

The convex scanning geometry was designed in ScanSim, an in-house Monte Carlo optical ray-tracing simulation. ScanSim parameters were used to build a 3D rendering of a convex ‘solid tank’ for optical-CT, which is capable of collimating a point light source into telecentric geometry without significant quantities of refractive-index matched fluid. The model was 3D printed, processed, and converted into a negative mold via rubber casting to produce a transparent polyurethane scanning tank. The DIOS was assembled with the solid tank, a 3W red LED light source, a computer-controlled rotation stage, and a 12-bit CCD camera. Initial optical phantom studies show negligible spatial inaccuracies in 2D projection images and 3D tomographic reconstructions. A PRESAGE 3D dose measurement for a 4-field box treatment plan from Eclipse shows 95% of voxels passing gamma analysis at 3%/3mm criteria. Gamma analysis between tomographic images of the same dosimeter in the DIOS and DLOS systems show 93.1% agreement at 5%/1mm criteria. From this initial study, the DIOS has demonstrated promise as an economically-viable optical-CT scanner. However, further improvements will be necessary to fully develop this system into an accurate and reliable tool for advanced QA.

Pre-clinical animal studies are used as a conventional means of translational research, as a midpoint between in-vitro cell studies and clinical implementation. However, modern small animal radiotherapy platforms are primitive in comparison with conventional linear accelerators. This work also investigates a series of 3D printed tools to expand the treatment capabilities of the X-RAD 225Cx orthovoltage irradiator, and applies them to a feasibility study of hippocampal avoidance in rodent whole-brain radiotherapy.

As an alternative material to lead, a novel 3D-printable tungsten-composite ABS plastic, GMASS, was tested to create precisely-shaped blocks. Film studies show virtually all primary radiation at 225 kVp can be attenuated by GMASS blocks of 0.5cm thickness. A state-of-the-art software, BlockGen, was used to create custom hippocampus-shaped blocks from medical image data, for any possible axial treatment field arrangement. A custom 3D printed bite block was developed to immobilize and position a supine rat for optimal hippocampal conformity. An immobilized rat CT with digitally-inserted blocks was imported into the SmART-Plan Monte-Carlo simulation software to determine the optimal beam arrangement. Protocols with 4 and 7 equally-spaced fields were considered as viable treatment options, featuring improved hippocampal conformity and whole-brain coverage when compared to prior lateral-opposed protocols. Custom rodent-morphic PRESAGE dosimeters were developed to accurately reflect these treatment scenarios, and a 3D dosimetry study was performed to confirm the SmART-Plan simulations. Measured doses indicate significant hippocampal sparing and moderate whole-brain coverage.

The (Un)Folding of Multidomain Proteins Through the Lens of Single-molecule Force-spectroscopy and Computer Simulation

Proteins are specialized molecules that catalyze most of the reactions that can sustain life, and they become functional by folding into a specific 3D structure. Despite their importance, the question, "how do proteins fold?" - first pondered in in the 1930's - is still listed as one of the top unanswered scientific questions as of 2005, according to the journal Science. Answering this question would provide a foundation for understanding protein function and would enable improved drug targeting, efficient biofuel production, and stronger biomaterials. Much of what we currently know about protein folding comes from studies on small, single-domain proteins, which may be quite different from the folding of large, multidomain proteins that predominate the proteomes of all organisms.

In this thesis I will discuss my work to fill this gap in understanding by studying the unfolding and refolding of large, multidomain proteins using the powerful combination of single-molecule force-spectroscopy experiments and molecular dynamic simulations.

The three model proteins studied - Luciferase, Protein S, and Streptavidin - lend insight into the inter-domain dependence for unfolding and the subdomain stabilization of binding ligands, and ultimately provide new insight into atomistic details of the intermediate states along the folding pathway.

Accuracy of computer-aided design/computer-assisted manufacture (CAD/CAM) fabricated dental restorations: a comparative study

Introduction: Computer-Aided-Design (CAD) and Computer-Aided-Manufacture (CAM) has been developed to fabricate fixed dental restorations accurately, faster and improve cost effectiveness of manufacture when compared to the conventional method. Two main methods exist in dental CAD/CAM technology: the subtractive and additive methods. While fitting accuracy of both methods has been explored, no study yet has compared the fabricated restoration (CAM output) to its CAD in terms of accuracy. The aim of this present study was to compare the output of various dental CAM routes to a sole initial CAD and establish the accuracy of fabrication. The internal fit of the various CAM routes were also investigated. The null hypotheses tested were: 1) no significant differences observed between the CAM output to the CAD and 2) no significant differences observed between the various CAM routes. Methods: An aluminium master model of a standard premolar preparation was scanned with a contact dental scanner (Incise, Renishaw, UK). A single CAD was created on the scanned master model (InciseCAD software, V2.5.0.140, UK). Twenty copings were then fabricated by sending the single CAD to a multitude of CAM routes. The copings were grouped (n=5) as: Laser sintered CoCrMo (LS), 5-axis milled CoCrMo (MCoCrMo), 3-axis milled zirconia (ZAx3) and 4-axis milled zirconia (ZAx4). All copings were micro-CT scanned (Phoenix X-Ray, Nanotom-S, Germany, power: 155kV, current: 60µA, 3600 projections) to produce 3-Dimensional (3D) models. A novel methodology was created to superimpose the micro-CT scans with the CAD (GOM Inspect software, V7.5SR2, Germany) to indicate inaccuracies in manufacturing. The accuracy in terms of coping volume was explored. The distances from the surfaces of the micro-CT 3D models to the surfaces of the CAD model (CAD Deviation) were investigated after creating surface colour deviation maps. Localised digital sections of the deviations (Occlusal, Axial and Cervical) and selected focussed areas were then quantitatively measured using software (GOM Inspect software, Germany). A novel methodology was also explored to digitally align (Rhino software, V5, USA) the micro-CT scans with the master model to investigate internal fit. Fifty digital cross sections of the aligned scans were created. Point-to-point distances were measured at 5 levels at each cross section. The five levels were: Vertical Marginal Fit (VF), Absolute Marginal Fit (AM), Axio-margin Fit (AMF), Axial Fit (AF) and Occlusal Fit (OF). Results: The results of the volume measurement were summarised as: VM-CoCrMo (62.8mm3 ) > VZax3 (59.4mm3 ) > VCAD (57mm3 ) > VZax4 (56.1mm3 ) > VLS (52.5mm3 ) and were all significantly different (p presented as areas with different colour. No significant differences were observed at the internal aspect of the cervical aspect between all groups of copings. Significant differences (p< M-CoCrMo Internal Occlusal, Internal Axial and External Axial 2 ZAx3 > ZAx4 External Occlusal, External Cervical 3 ZAx3 < ZAx4 Internal Occlusal 4 M-CoCrMo > ZAx4 Internal Occlusal and Internal Axial The mean values of AMF and AF were significantly (p M-CoCrMo and CAD > ZAx4. Only VF of M-CoCrMo was comparable with the CAD Internal Fit. All VF and AM values were within the clinically acceptable fit (120µm). Conclusion: The investigated CAM methods reproduced the CAD accurately at the internal cervical aspect of the copings. However, localised deviations at axial and occlusal aspects of the copings may suggest the need for modifications in these areas prior to fitting and veneering with porcelain. The CAM groups evaluated also showed different levels of Internal Fit thus rejecting the null hypotheses. The novel non-destructive methodologies for CAD/CAM accuracy and internal fit testing presented in this thesis may be a useful evaluation tool for similar applications.

Fast 2D/3D object representation with growing neural gas

This work presents the design of a real-time system to model visual objects with the use of self-organising networks. The architecture of the system addresses multiple computer vision tasks such as image segmentation, optimal parameter estimation and object representation. We first develop a framework for building non-rigid shapes using the growth mechanism of the self-organising maps, and then we define an optimal number of nodes without overfitting or underfitting the network based on the knowledge obtained from information-theoretic considerations. We present experimental results for hands and faces, and we quantitatively evaluate the matching capabilities of the proposed method with the topographic product. The proposed method is easily extensible to 3D objects, as it offers similar features for efficient mesh reconstruction.

Application of computer-aided tomography techniques to visualize kelp holdfast structure reveals the importance of habitat complexity for supporting marine biodiversity

Ecosystem engineers that increase habitat complexity are keystone species in marine systems, increasing shelter and niche availability, and therefore biodiversity. For example, kelp holdfasts form intricate structures and host the largest number of organisms in kelp ecosystems. However, methods that quantify 3D habitat complexity have only seldom been used in marine habitats, and never in kelp holdfast communities. This study investigated the role of kelp holdfasts (Laminaria hyperborea) in supporting benthic faunal biodiversity. Computer-aided tomography (CT-) scanning was used to quantify the three-dimensional geometrical complexity of holdfasts, including volume, surface area and surface fractal dimension (FD). Additionally, the number of haptera, number of haptera per unit of volume, and age of kelps were estimated. These measurements were compared to faunal biodiversity and community structure, using partial least-squares regression and multivariate ordination. Holdfast volume explained most of the variance observed in biodiversity indices, however all other complexity measures also strongly contributed to the variance observed. Multivariate ordinations further revealed that surface area and haptera per unit of volume accounted for the patterns observed in faunal community structure. Using 3D image analysis, this study makes a strong contribution to elucidate quantitative mechanisms underlying the observed relationship between biodiversity and habitat complexity. Furthermore, the potential of CT-scanning as an ecological tool is demonstrated, and a methodology for its use in future similar studies is established. Such spatially resolved imager analysis could help identify structurally complex areas as biodiversity hotspots, and may support the prioritization of areas for conservation.

Application of computer-aided tomography techniques to visualize kelp holdfast structure reveals the importance of habitat complexity for supporting marine biodiversity

Ecosystem engineers that increase habitat complexity are keystone species in marine systems, increasing shelter and niche availability, and therefore biodiversity. For example, kelp holdfasts form intricate structures and host the largest number of organisms in kelp ecosystems. However, methods that quantify 3D habitat complexity have only seldom been used in marine habitats, and never in kelp holdfast communities. This study investigated the role of kelp holdfasts (Laminaria hyperborea) in supporting benthic faunal biodiversity. Computer-aided tomography (CT-) scanning was used to quantify the three-dimensional geometrical complexity of holdfasts, including volume, surface area and surface fractal dimension (FD). Additionally, the number of haptera, number of haptera per unit of volume, and age of kelps were estimated. These measurements were compared to faunal biodiversity and community structure, using partial least-squares regression and multivariate ordination. Holdfast volume explained most of the variance observed in biodiversity indices, however all other complexity measures also strongly contributed to the variance observed. Multivariate ordinations further revealed that surface area and haptera per unit of volume accounted for the patterns observed in faunal community structure. Using 3D image analysis, this study makes a strong contribution to elucidate quantitative mechanisms underlying the observed relationship between biodiversity and habitat complexity. Furthermore, the potential of CT-scanning as an ecological tool is demonstrated, and a methodology for its use in future similar studies is established. Such spatially resolved imager analysis could help identify structurally complex areas as biodiversity hotspots, and may support the prioritization of areas for conservation.

Face recognition using a unified 3D morphable model

We address the problem of 3D-assisted 2D face recognition in scenarios when the input image is subject to degradations or exhibits intra-personal variations not captured by the 3D model. The proposed solution involves a novel approach to learn a subspace spanned by perturbations caused by the missing modes of variation and image degradations, using 3D face data reconstructed from 2D images rather than 3D capture. This is accomplished by modelling the difference in the texture map of the 3D aligned input and reference images. A training set of these texture maps then defines a perturbation space which can be represented using PCA bases. Assuming that the image perturbation subspace is orthogonal to the 3D face model space, then these additive components can be recovered from an unseen input image, resulting in an improved fit of the 3D face model. The linearity of the model leads to efficient fitting. Experiments show that our method achieves very competitive face recognition performance on Multi-PIE and AR databases. We also present baseline face recognition results on a new data set exhibiting combined pose and illumination variations as well as occlusion.

Détection, reconstruction 3D et identification des êtres vivants du règne animal

L’automatisation de la détection et de l’identification des animaux est une tâche qui a de l’intérêt dans plusieurs domaines de recherche en biologie ainsi que dans le développement de systèmes de surveillance électronique. L’auteur présente un système de détection et d’identification basé sur la vision stéréo par ordinateur. Plusieurs critères sont utilisés pour identifier les animaux, mais l’accent a été mis sur l’analyse harmonique de la reconstruction en temps réel de la forme en 3D des animaux. Le résultat de l’analyse est comparé avec d’autres qui sont contenus dans une base évolutive de connaissances.

Analysis of Local Search Methods for 3D Data

In questa tesi sono stati analizzati alcuni metodi di ricerca per dati 3D. Viene illustrata una panoramica generale sul campo della Computer Vision, sullo stato dell’arte dei sensori per l’acquisizione e su alcuni dei formati utilizzati per la descrizione di dati 3D. In seguito è stato fatto un approfondimento sulla 3D Object Recognition dove, oltre ad essere descritto l’intero processo di matching tra Local Features, è stata fatta una focalizzazione sulla fase di detection dei punti salienti. In particolare è stato analizzato un Learned Keypoint detector, basato su tecniche di apprendimento di machine learning. Quest ultimo viene illustrato con l’implementazione di due algoritmi di ricerca di vicini: uno esauriente (K-d tree) e uno approssimato (Radial Search). Sono state riportate infine alcune valutazioni sperimentali in termini di efficienza e velocità del detector implementato con diversi metodi di ricerca, mostrando l’effettivo miglioramento di performance senza una considerabile perdita di accuratezza con la ricerca approssimata.

The Role of Art in Computer Game Design

Computer games are significant since they embody our youngsters’ engagement with contemporary culture, including both play and education. These games rely heavily on visuals, systems of sign and expression based on concepts and principles of Art and Architecture. We are researching a new genre of computer games, ‘Educational Immersive Environments’ (EIEs) to provide educational materials suitable for the school classroom. Close collaboration with subject teachers is necessary, but we feel a specific need to engage with the practicing artist, the art theoretician and historian. Our EIEs are loaded with multimedia (but especially visual) signs which act to direct the learner and provide the ‘game-play’ experience forming semiotic systems. We suggest the hypothesis that computer games are a space of deconstruction and reconstruction (DeRe): When players enter the game their physical world and their culture is torn apart; they move in a semiotic system which serves to reconstruct an alternate reality where disbelief is suspended. The semiotic system draws heavily on visuals which direct the players’ interactions and produce motivating gameplay. These can establish a reconstructed culture and emerging game narrative. We have recently tested our hypothesis and have used this in developing design principles for computer game designers. Yet there are outstanding issues concerning the nature of the visuals used in computer games, and so questions for contemporary artists. Currently, the computer game industry employs artists in a ‘classical’ role in production of concept sketches, storyboards and 3D content. But this is based on a specification from the client which restricts the artist in intellectual freedom. Our DeRe hypothesis places the artist at the generative centre, to inform the game designer how art may inform our DeRe semiotic spaces. This must of course begin with the artists’ understanding of DeRe in this time when our ‘identities are becoming increasingly fractured, networked, virtualized and distributed’ We hope to persuade artists to engage with the medium of computer game technology to explore these issues. In particular, we pose several questions to the artist: (i) How can particular ‘periods’ in art history be used to inform the design of computer games? (ii) How can specific artistic elements or devices be used to design ‘signs’ to guide the player through the game? (iii) How can visual material be integrated with other semiotic strata such as text and audio?