18 results
Search Results
Now showing 1 - 10 of 18
Item SilSketch: Automated Sketch-Based Editing of Surface Meshes(The Eurographics Association, 2007) Zimmermann, Johannes; Nealen, Andrew; Alexa, Marc; Michiel van de Panne and Eric SaundWe introduce an over-sketching interface for feature-preserving surface mesh editing. The user sketches a stroke that is the suggested position of part of a silhouette of the displayed surface. The system then segments all imagespace silhouettes of the projected surface, identifies among all silhouette segments the best matching part, derives vertices in the surface mesh corresponding to the silhouette part, selects a sub-region of the mesh to be modified, and feeds appropriately modified vertex positions together with the sub-mesh into a mesh deformation tool. The overall algorithm has been designed to enable interactive modification of the surface yielding a surface editing system that comes close to the experience of sketching 3D models on paper.Item Ink Features for Diagram Recognition(The Eurographics Association, 2007) Patel, Rachel; Plimmer, Beryl; Grundy, John; Ihaka, Ross; Michiel van de Panne and Eric SaundThe ability to automatically recognize a sketch accurately is important to computer-based diagramming. Many recognition techniques have been proposed but few researchers have reported the use of formal methods to select the most appropriate ink features for recognition algorithms. We have used a statistical approach to identify the most important distinguishing features of ink for dividing text and shapes. We implemented these into an existing recognition engine and conducted a comparative evaluation. Our feature set more successfully classified a range of common diagram elements than two existing dividers.Item Speech and Sketching: An Empirical Study of Multimodal Interaction(The Eurographics Association, 2007) Adler, A.; Davis, R.; Michiel van de Panne and Eric SaundSketch recognition can capture the sketching component of a multimodal conversation about design, but it does not capture information conveyed in the other modalities. The informal speech that accompanies a sketch often has a considerable amount of additional information. We want to develop a digital whiteboard capable of understanding both sketching and speech, and capable of participating in a conversation similar to one that the user would have with a human design partner. We conducted a user study to help us understand what kinds of conversations users would have with a whiteboard capable of recognizing a sketch. We report results that we believe will help guide the design of an effective multimodal interface, and discuss implications for system architectures.Item A Combinatorial Approach to Multi-Domain Sketch Recognition(The Eurographics Association, 2007) Hall, A.; Pomm, C.; Widmayer, P.; Michiel van de Panne and Eric SaundIn this paper we propose a combinatorial model for sketch recognition. Two fundamental problems, the evaluation of individual symbols and the interpretation of a complete sketch scene possibly containing several symbols, are expressed as combinatorial optimization problems. We settle the computational complexity of the combinatorial problems and present a branch and bound algorithm for computing optimal symbol confidences. To handle sketch scenes in practice we propose a modest restriction of drawing freedom and present an algorithm which only needs to compute a polynomial number of symbol confidences.Item Example-Based Conceptual Styling Framework for Automotive Shapes(The Eurographics Association, 2007) Kókai, István; Finger, Jörg; Smith, Randall C.; Pawlicki, Richard; Vetter, Thomas; Michiel van de Panne and Eric SaundConceptual design in the automotive industry is a time-consuming process. Iterations between concept sketches, created with traditional two dimensional methods, and 3D digital representations of a prototype are currently one of the big bottlenecks. In this paper we present a framework for an integrated 2D-3D design environment. The core of the framework is a model representing the characteristic lines of automotive shapes built from a set of example shapes. From every example shape we extract the same set of characteristic lines and represent them with a feature vector of deformation gradients. Given a set of constraints, our method can generate a new feature vector with an optimization procedure. We provide examples for meaningful manipulations. We demonstrate that these manipulations are intuitive and create plausible shapes.Item Temporal Sketch Recognition in Interspersed Drawings(The Eurographics Association, 2007) Sezgin, Tevfik Metin; Davis, Randall; Michiel van de Panne and Eric SaundSketch recognition has been recognized as an enabling technology for pen-based interfaces. Previous work in the field has shown that in certain domains the stroke orderings used when drawing objects contain temporal patterns that can aid recognition. So far, systems that use temporal information for recognition have assumed that objects are drawn one at a time. This paper shows how this assumption can be relaxed to permit temporal interspersing of strokes from different objects. We describe a statistical framework based on Dynamic Bayesian Networks that explicitly models the fact that objects can be drawn interspersed. We present recognition results for hand-drawn electronic circuit diagrams. The results show that handling interspersed drawing provides a significant increase in accuracy.Item Free-form Sketch(The Eurographics Association, 2007) Wang, Haixiong; Markosian, Lee; Michiel van de Panne and Eric SaundWe describe a sketch-based system for modeling 3D shapes based on a new multiresolution shape representation we call a layered mesh. Like subdivision surfaces, layered meshes provide a multiresolution hierarchy of meshes. A key difference is that a layered mesh lets you edit the shape and structure of the mesh at any level of the hierarchy, through the notion of shape primitives organized in a dependency network. The simplest primitives are points and curves, which can be used to define several kinds of parameteric surface. Surfaces can be inflated or smoothly joined to produce a broad range of shapes. An important feature of the system is the ability to refine shapes and add detail by oversketching primitives, either directly or via the curves that define them. While our user interface is still in development, our initial results show the potential for this approach.Item Designing a Sketch Recognition Front-End: User Perception of Interface Elements(The Eurographics Association, 2007) Wais, Paul; Wolin, Aaron; Alvarado, Christine; Michiel van de Panne and Eric SaundPrograms that can recognize students' hand-drawn diagrams have the potential to revolutionize education by breaking down the barriers between diagram creation and simulation. Much recent work focuses on building robust recognition engines, but understanding how to support this new interaction paradigm from a user's perspective is an equally important and less well understood problem. We present a user study that investigates four critical sketch recognition user interface issues: how users integrate the process of triggering recognition into their work, when users prefer to indicate which portions of the diagram should be recognized, how users prefer to receive recognition feedback, and how users perceive recognition errors. We find that user preferences emphasize the importance of system reliability, the minimization of distractions, and the maximization of predictability.Item Designing UI Techniques for Handwritten Mathematics(The Eurographics Association, 2007) Zeleznik, Robert; Miller, Timothy; Li, Chuanjun; Michiel van de Panne and Eric SaundWe discuss the design of user interface techniques for visualizing and controlling the recognition of handwritten mathematics. In particular, we present a range of visualization styles for displaying the result of math recognition. These styles offer different trade-offs between ease of user correction of errors in recognition and impact on the user's entry of math. We also describe recognition control techniques, including using user-controlled mappings of allographs to achieve more robust symbol recognition and provide extensions to notation, and UI control of non-spatial information used in recognition. We generally do not discuss the precise user interface implementation necessary to use these techniques, for example whether to use menus or gestures, but just the functionality required. Finally, we provide, in an appendix, a sketch of the recognition and display implementation behind our techniques.Item Addressing Class Distribution Issues of the Drawing vs Writing Classification in an Ink Stroke Sequence(The Eurographics Association, 2007) Wang, Xin; Biswas, Manoj; Raghupathy, Sashi; Michiel van de Panne and Eric SaundComplicated by temporal correlations among the strokes and varying distributions of the underlying classes, the drawing/writing classification of ink strokes in a digital ink file poses interesting challenges. In this paper, we present our efforts in addressing some of the issues. First, we describe how we adjust the outputs of the neural network to a priori probabilities of new observations to produce more accurate estimates of the posterior probabilities. Second, we describe how to adapt the parameters of the HMM to new data sets. Albeit the fact that the emission probabilities of the HMM are computed indirectly from the outputs of the neural network, our modified Baum-Welch algorithm still finds the correct estimates for the HMM's parameters. We also present experimental results of our new algorithms on 6 real world data sets. The results show that our methods increase the F Measures of both the drawing and the writing classes on the more ''drawing intensive'' data sets which have stronger temporal correlations. But they do not perform well on the more ''writing intensive'' data sets.