No description available.

<p>The fundamental aim of this study is to examine whether itis possible to automatically convert vector-based drawings toproduct models. The reason fordoing this is that the newobject-based systems cannot make use of the information storedin CAD drawings, which limits the usability of thesesystems.</p><p>Converting paper drawings to vector-format is used today andprovides recognition of lines and text, but does not interpretwhat the shapes represent. A language for describing thegeometrical representations that could be processed directlyinto a recognition program for building elements is missing. Itis easier to describe how to recognize a line as a series ofdots in a raster image, than it is to describe how a complexsymbol of a building element looks like.</p><p>The approach in this research work has been to testdifferent shape recognition algorithms. The proposed method canbe divided into four processes: grouping of geometricalprimitives, classifying these groups, interpreting the contentand analyzing the relationships between the groups. Thealgorithms developed here are based on research within relateddomains, such as pattern recognition and artificialintelligence.</p><p>The algorithms have been developed in a prototypeimplementation and were tested with three layer-structureddrawings used in practice. The results of the tests show thatthere are no crucial obstacles to recognizing a large part ofthe symbols of building elements in a CAD drawing. Therequirement is that the recognition system is able todifferentiate one from another and be tolerant of errors andvariations in the shapes.</p><p><b>Keywords:</b>Shape recognition, shape interpretation,product models</p>

The fundamental aim of this study is to examine whether itis possible to automatically convert vector-based drawings toproduct models. The reason fordoing this is that the newobject-based systems cannot make use of the information storedin CAD drawings, which limits the usability of thesesystems. Converting paper drawings to vector-format is used today andprovides recognition of lines and text, but does not interpretwhat the shapes represent. A language for describing thegeometrical representations that could be processed directlyinto a recognition program for building elements is missing. Itis easier to describe how to recognize a line as a series ofdots in a raster image, than it is to describe how a complexsymbol of a building element looks like. The approach in this research work has been to testdifferent shape recognition algorithms. The proposed method canbe divided into four processes: grouping of geometricalprimitives, classifying these groups, interpreting the contentand analyzing the relationships between the groups. Thealgorithms developed here are based on research within relateddomains, such as pattern recognition and artificialintelligence. The algorithms have been developed in a prototypeimplementation and were tested with three layer-structureddrawings used in practice. The results of the tests show thatthere are no crucial obstacles to recognizing a large part ofthe symbols of building elements in a CAD drawing. Therequirement is that the recognition system is able todifferentiate one from another and be tolerant of errors andvariations in the shapes. <b>Keywords:</b>Shape recognition, shape interpretation,product models / NR 20140805

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).