No description available.

There are often discrepancies in how a product is perceived in different representation media employed in typical product development processes. The first goal of this research project was to determine how visual illusions influence a designer's perception of a product across three representations: industrial design sketches, computer aided design (CAD) models, and physical prototypes (FDM rapid prototyping). A visualization experiment was conducted in which participants were asked to report how they perceived the shape and size of certain features, representing two types of illusions across the three model representations. Their statements were analyzed to identify the trends of how these two illusions affect overall appearance, categorized by representation type and the users' backgrounds (i.e., specialization and years of experience). The participants included students and professionals with various levels of engineering and industrial design experience. The analysis shows that there are differences in how designers see models depending on the representation media, and to some degree depending on the participants' professional background. The second goal was to explore the process of identifying such illusions automatically during the design process. In this regard, a discussion on how to implement the results from the visualization experiment is presented. Emphasis is on the potential development of a tool in CAD systems that would identify illusory effects and subsequently suggest potential design solutions. The possibility of using spectral analysis (fast Fourier transform) for an automated shape recognition capability in CAD systems is discussed. / Master of Science

This study presents a new shape representation scheme based on disconnected symmetry axes along with a matching framework to address the problem of generic shape recognition. The main idea is to define the relative spatial arrangement of local symmetry axes in a shape centered coordinate frame. The resulting descriptions are invariant to scale, rotation, small changes in viewpoint and articulations. Symmetry points are extracted from a surface whose level curves roughly mimic the motion by curvature. By increasing the amount of smoothing on the evolving curve, only those symmetry axes that correspond to the most prominent parts of a shape are extracted. The representation does not suffer from the common instability problems of the traditional connected skeletons. It captures the perceptual properties of shapes well. Therefore, finding the similarities and the differences among shapes becomes easier. The matching process is able to find the correct correspondence of parts under various visual transformations. Highly successful classification results are obtained on a moderate sized 2D shape database.

>Magister Scientiae - MSc / In order to classify South African Sign Language as a signed gesture, five fundamental parameters need to be considered. These five parameters to be considered are: hand shape, hand orientation, hand motion, hand location and facial expressions. The research in this thesis will utilise Deep Learning techniques, specifically Convolutional Neural Networks, to recognise hand shapes in various hand orientations. The research will focus on two of the five fundamental parameters, i.e., recognising six South African Sign Language hand shapes for each of five different hand orientations. These hand shape and orientation combinations will be recognised by means of a video stream captured on a mobile device. The efficacy of Convolutional Neural Network for gesture recognition will be judged with respect to its classification accuracy and classification speed in both a desktop and embedded context. The research methodology employed to carry out the research was Design Science Research. Design Science Research refers to a set of analytical techniques and perspectives for performing research in the field of Information Systems and Computer Science. Design Science Research necessitates the design of an artefact and the analysis thereof in order to better understand its behaviour in the context of Information Systems or Computer Science. / National Research Foundation (NRF)

>Magister Scientiae - MSc / Hand shape recognition is a pivotal part of any system that attempts to implement Sign Language recognition. This thesis presents a novel system which recognises hand shapes from a single camera view in 2D. By mapping the recognised hand shape from 2D to 3D,it is possible to obtain 3D co-ordinates for each of the joints within the hand using the kinematics embedded in a 3D hand avatar and smooth the transformation in 3D space between any given hand shapes. The novelty in this system is that it does not require a hand pose to be recognised at every frame, but rather that hand shapes be detected at a given step size. This architecture allows for a more efficient system with better accuracy than other related systems. Moreover, a real-time hand tracking strategy was developed that works efficiently for any skin tone and a complex background.

>Magister Scientiae - MSc / There are five fundamental parameters that characterize any sign language gesture. They are hand shape, orientation, motion and location, and facial expressions. The SASL group at the University of the Western Cape has created systems to recognize each of these parameters in an input video stream. Most of these systems make use of the Support Vector Machine technique for the classification of data due to its high accuracy. It is, however, unknown how other machine learning techniques compare to Support Vector Machines in the recognition of each of these parameters. This research lays the foundation for the process of determining optimum machine learning techniques for each parameter by comparing Support Vector Machines to Artificial Neural Networks and Random Forests in the context of South African Sign Language hand shape recognition. Li, a previous researcher at the SASL group, created a state-of-the-art hand shape recognition system that uses Support Vector Machines to classify hand shapes. This research re-implements Li’s feature extraction procedure but investigates the use of Artificial Neural Networks and Random Forests in the place of Support Vector Machines as a comparison. The machine learning techniques are optimized and trained to recognize ten SASL hand shapes and compared in terms of classification accuracy, training time, optimization time and classification time.

Since last two decades researches have been working on developing systems that can assistsdrivers in the best way possible and make driving safe. Computer vision has played a crucialpart in design of these systems. With the introduction of vision techniques variousautonomous and robust real-time traffic automation systems have been designed such asTraffic monitoring, Traffic related parameter estimation and intelligent vehicles. Among theseautomatic detection and recognition of road signs has became an interesting research topic.The system can assist drivers about signs they don’t recognize before passing them.Aim of this research project is to present an Intelligent Road Sign Recognition System basedon state-of-the-art technique, the Support Vector Machine. The project is an extension to thework done at ITS research Platform at Dalarna University [25]. Focus of this research work ison the recognition of road signs under analysis. When classifying an image its location, sizeand orientation in the image plane are its irrelevant features and one way to get rid of thisambiguity is to extract those features which are invariant under the above mentionedtransformation. These invariant features are then used in Support Vector Machine forclassification. Support Vector Machine is a supervised learning machine that solves problemin higher dimension with the help of Kernel functions and is best know for classificationproblems.

Topology Optimization has been proven to be a useful tool in discovering non-intuitive optimal designs subject to certain design constraints. The results of Topology Optimization are either represented as a tessellation object composed of thousands of triangular surfaces, or as a point cloud. In either case, the results of Topology Optimization are not suited for use in subsequent steps of the design process which require 3D parametric CAD (Computer Aided Design) models. Converting Topology Optimization results into parametric CAD geometry by hand is an extremely tedious and time consuming process which is highly subjective. This thesis presents a shape recognition algorithm that uses a feature by feature CAD-centric approach to convert Topology Optimization results into parametric CAD geometry. This is accomplished by fitting 2D cross section geometry to various parts of a given feature through the use of Shape Templates and then constructing 3D surfaces through the set of 2D cross sections. This algorithm aids in measuring the geometric approximation error of the generated geometry as compared to the optimal model, and standardizes the process through automation techniques. It also aids the designer / engineer in managing the direct tradeoff between closeness of geometric approximation (measured by volumetric comparison) and model complexity (measured by the number of parameters required to represent the geometry).

No description available.

Les buts des recherches présentées dans cette thèse étaient d’évaluer le rôle de la stéréoscopie dans la reconnaissance de forme, dans la perception du relief et dans la constance de forme. La première étude a examiné le rôle de la stéréoscopie dans la perception des formes visuelles en utilisant une tâche de reconnaissance de formes. Les stimuli pouvaient être présentés en 2D, avec disparité normale (3D) ou avec disparité inversée. La performance de reconnaissance était meilleure avec les modes de présentation 2D et 3D qu’avec la 3D inversée. Cela indique que la stéréoscopie contribue à la reconnaissance de forme. La deuxième étude s’est intéressée à la contribution conjointe de l’ombrage et de la stéréoscopie dans la perception du relief des formes. Les stimuli étaient des images d’une forme 3D convexe synthétique présentée sous un point de vue menant à une ambigüité quant à sa convexité. L’illumination pouvait provenir du haut ou du bas et de la gauche ou de la droite, et les stimuli étaient présentés dichoptiquement avec soit de la disparité binoculaire normale, de la disparité inversée ou sans disparité entre les vues. Les participants ont répondu que les formes étaient convexes plus souvent lorsque la lumière provenait du haut que du bas, plus souvent avec la disparité normale qu’en 2D, et plus souvent avec absence de disparité qu’avec disparité inversée. Les effets de direction d’illumination et du mode de présentation étaient additifs, c’est-à-dire qu’ils n’interagissaient pas. Cela indique que l’ombrage et la stéréoscopie contribuent indépendamment à la perception du relief des formes. La troisième étude a évalué la contribution de la stéréoscopie à la constance de forme, et son interaction avec l’expertise perceptuelle. Elle a utilisé trois tâches de discrimination séquentielle de trombones tordus ayant subi des rotations en profondeur. Les stimuli pouvaient être présentés sans stéréoscopie, avec stéréoscopie normale ou avec stéréoscopie inversée. Dans la première moitié de l’Exp. 1, dans laquelle les variations du mode de présentation étaient intra-sujets, les performances étaient meilleures en 3D qu’en 2D et qu’en 3D inversée. Ces effets ont été renversés dans la seconde moitié de l’expérience, et les coûts de rotation sont devenus plus faibles pour la 2D et la 3D inversée que pour la 3D. Dans les Exps. 2 (variations intra-sujets du mode de présentation, avec un changement de stimuli au milieu de l’expérience) et 3 (variations inter-sujets du mode de présentation), les effets de rotation étaient en tout temps plus faibles avec stéréoscopie qu’avec stéréoscopie inversée et qu’en 2D, et plus faibles avec stéréoscopie inversée que sans stéréoscopie. Ces résultats indiquent que la stéréoscopie contribue à la constance de forme. Toutefois, cela demande qu’elle soit valide avec un niveau minimal de consistance, sinon elle devient stratégiquement ignorée. En bref, les trois études présentées dans cette thèse ont permis de montrer que la stéréoscopie contribue à la reconnaissance de forme, à la perception du relief et à la constance de forme. De plus, l’ombrage et la stéréoscopie sont intégrés linéairement. / The goals of the researches presented in this thesis were to evaluate the role of stereopsis in shape recognition, in relief perception, and in shape constancy. The first study examined the role of stereopsis in visual shape perception using a recognition task. The stimuli were presented with null binocular disparity (i.e. 2D), normal binocular disparity (3D) or reversed disparity. Recognition performance was better with 2D and 3D displays than with reversed 3D. This indicates that stereopsis contributes to shape recognition. The second study examined the joint contribution of shading and stereopsis to the relief perception of shape. The stimuli were the images of a synthetic convex 3D shape seen from viewpoints leading to ambiguity as to its convexity. Illumination either came from above, or below and from the right or the left, and stimuli were presented dichoptically with either normal binocular disparity, reversed disparity, or no disparity between the views presented at each eye. Participants responded “convex” more often when the lighting came from above than from below. Also, participants responded that the shape was convex more often with normal than with zero disparity, and more often with 2D than with reversed stereopsis. The effects of lighting direction and display mode were additive; i.e. they did not interact. This indicates that shading and stereopsis contribute independently to shape perception. The third study assessed the contribution of stereopsis to shape constancy and how it interacts with perceptual expertise using three sequential matching tasks with bent paperclips rotated in depth. Stimuli were presented without stereopsis, or with normal or reversed stereopsis. In the first half of Exp. 1, where display mode variations were within-subject, the performances were better with stereoscopic displays than with 2D or reversed stereoscopic presentations. In the second half of the experiment, the rotation costs became weaker for the 2D and reversed 3D display modes than for the 3D one. In Exps. 2 (display mode within-subject, with stimuli switched halfway into the experiment) and 3, (display mode between-subjects) the rotation effect was consistently weaker with normal stereo than with either 2D or reversed stereoscopic displays. These experiments also demonstrate an advantage of reversed stereo over 2D presentations. This indicates that stereo may contribute to shape constancy. This, however, requires stereoscopic information to be valid with a minimal degree of consistency. Otherwise, stereo may become strategically ignored. In a nutshell, the three studies presented in this thesis showed that stereo contributes to shape recognition, relief perception and shape constancy. Furthermore stereopsis and shading are integrated independently.