SBM06: Sketch Based Interfaces and Modeling 2006

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/420

Browse

Now showing 1 - 19 of 19

Automatic Learning of Symbol Descriptions Avoiding Topological Ambiguities
(The Eurographics Association, 2006) Mas, Juan; Lamiroy, Bart; Sanchez, Gemma; Llados, Josep; Thomas Stahovich and Mario Costa Sousa
In this paper we address both automatic recognition of sketched symbols and the construction of the corresponding models from user drawn examples. Our approach is based on a two stage process. In a first phase we use an Adjacency Grammar to express topological properties of the symbol. In order to be able to further disambiguate topologically similar configurations on the rules of the grammar that are triggered by the recognition process produce a set of local geometric invariants is defined. The combination of both steps results in an efficient recognition method for user drawn sketches. Furthermore, we show that the same approach can easily be adapted for the generation of Adjacency Grammars from user provided and hand drawn examples.
Transformation Strokes
(The Eurographics Association, 2006) Severn, Aaron; Samavati, Faramarz; Sousa, Mario Costa; Thomas Stahovich and Mario Costa Sousa
In this paper, we present a sketch-based technique for specifying transformations for general models by means of a single stroke, offering a more streamlined form of user interaction. The shape of the stroke is interpreted to allow composition of translation, rotation and scaling. We extract two main directions from the input stroke using Principle Component Analysis and use them to obtain an appropriate transformation for the model. Our method helps to have a more natural and faster way of assembling 3D structures. It is general and does not depend on specific knowledge about the type of models. As such, it can fit in the majority of graphics systems or modelling techniques.
An Efficient Graph-Based Symbol Recognizer
(The Eurographics Association, 2006) Lee, WeeSan; Kara, Levent Burak; Stahovich, Thomas F.; Thomas Stahovich and Mario Costa Sousa
We describe a trainable symbol recognizer for pen-based user interfaces. Symbols are represented internally as attributed relational graphs that describe both the geometry and topology of the symbols. Symbol recognition reduces to the task of finding the definition symbol whose attributed relational graph best matches that of the unknown symbol. One challenge addressed in the current work is how to perform this graph matching in an effi- cient fashion so as to achieve interactive performance. We present four approximate graph matching techniques: Stochastic Matching, which is based on stochastic search; Error-driven Matching, which uses local matching errors to drive the solution to an optimal match; Greedy Matching, which uses greedy search; and Sort Matching, which relies on geometric information to accelerate the matching. Finally, we present promising results of initial user studies, and discuss the tradeoffs between the various matching techniques.
A Study of Usability of Sketching Tools Aimed at Supporting Prescriptive Sketches
(The Eurographics Association, 2006) Company, Pedro; Contero, Manuel; Naya, F.; Aleixos, N.; Thomas Stahovich and Mario Costa Sousa
Prescriptive sketches are usually drawn, after conceptual design is over, to prepare the creation of digital 3D models. Designers and draftsmen use them as screenplays that guide the creation of the final 3D model. Prescriptive sketches are still paper-and-pencil, in spite of the existence of some academic or even commercial, computer tools. In this paper, we defend the hypothesis that this is because current computer tools are less usable than paper-andpencil sketches and do not posses significantly improved functionality. A pilot study was conducted to validate this hypothesis. Both the study and its main conclusions are described in detail.
Living Ink: Implementation of a Prototype Sketching Language for Real Time Authoring of Animated Line Drawings
(The Eurographics Association, 2006) Rogers, Bill; Thomas Stahovich and Mario Costa Sousa
Sketching with pen on paper is often used as a way of augmenting spoken descriptions: to help explain how some mechanical device works; to show the flow of information in an organisation, to show the action in a story, and so on. Sketches serve as a focus for the attention of viewers and help make abstract concepts more concrete. But images on paper don t move. Where the time and resources are available, as in preparing a lecture in advance, or producing a television program, authors recognize that moving images are often superior at conveying concepts and holding people s attention. An electronic display is capable of generating moving images in real time. We argue that such a display need not be used just to mimic pen and paper. After all paper is cheap, plentiful, has a wide viewing angle, and doesn t have batteries to run flat. Our Living Ink system is a prototype implementation of a user interface for generating animated line drawings (animated sketches). Our goal was to provide a user interface which can be used in real-time, making interesting animations while an audience watches. This paper describes progress to date towards that objective and discusses proposals for further development.
A New Sketch Based Interface using the Gray-level Co-occurrence Matrix for Perceptual Simplification of Paper Based Scribbles
(The Eurographics Association, 2006) Bartolo, Alexandra; Camilleri, Kenneth P.; Farrugia, Philip J.; Borg, Jonathan C.; Thomas Stahovich and Mario Costa Sousa
The sketching activity has an important role in conceptual design and a variety of tools exist which help designers to facilitate the generation of 3D models form sketched drawings. This paper describes a new sketch-to-3D tool, which uses annotations to aid the interpretation of the drawing. Over-traced lines present in the designer s scribbles provide an interpretation challenge, which must be resolved in order to obtain 3D models from these sketches. Perceptual grouping techniques used to interpret such images require that the drawing is represented as vectors. These are generally obtained through thinning or edge detection. However, we show that processing scribbles using these techniques result in a large number of vectors which do not provide a faithful representation of the drawing. This paper investigates the use of the co-occurrence matrix to perceptually simplify these drawings, thus obtaining a smaller number of vectors which describe the drawing more faithfully.
Parsing Ink Annotations on Heterogeneous Documents
(The Eurographics Association, 2006) Wang, Xin; Shilman, Michael; Raghupathy, Sashi; Thomas Stahovich and Mario Costa Sousa
Annotation is an integral part of reading, comprehending, commenting, and authoring notes and documents. In this paper we present a system for recognizing annotations in a flexible digital notebook that may contain a variety of content ranging from text, to images, to handwritten notes. To accomplish the recognition task in real-time makes the complicated annotation parsing problem more difficult. Our approach differs from previous approaches in several ways. First, our approach handles annotations on ink notes, which are significantly more ambiguous than annotations on printed documents and hence more difficult to recognize. Second, our approach is entirely learned from data, so it is easy to adapt to other scenarios. Third, our approach is more thoroughly evaluated than previous systems. On a test set of real user notes, the system has achieved an average recall of 0.9258 on all annotation types. Finally, the implementation of the approach will be commercially available as an API in the upcoming release of Windows® Vista® and Office 12®.
Sketch-based 3D Engineering Part Class Browsing and Retrieval
(The Eurographics Association, 2006) Hou, Suyu; Ramani, Karthik; Thomas Stahovich and Mario Costa Sousa
We present a two-tier sketch-based engineering part retrieval system enhanced with classifier combination. Given a free-hand user sketch, we propose to use an ensemble of classifiers to estimate the likelihood of the sketch belonging to each category by exploring the strengths of individual classifiers. This supports high quality part retrieval by motivating user feedback with a ranked list of top choices. Three shape descriptors have been used to generate the probability-based classifiers independently. Experiments are conducted using the Engineering Shape Benchmark database in order to evaluate the selected combination rules before we integrate the best rule for sketch classification. User studies with the system show that users can easily identify the desired groups and then the parts. In addition, the precision attained using the synthesis is better than results from independent classifiers when applied to both user sketches and 3D models.
Modeling Plant Variations through 3D Interactive Sketches
(The Eurographics Association, 2006) Streit, Lisa; Lapides, Paul; Sousa, Mario Costa; Sharlin, Ehud; Thomas Stahovich and Mario Costa Sousa
Modeling realistic looking plants is still a complex problem requiring specification of plant structure, geometry and surface characteristics. Modeling a collection of plants is more problematic especially since each plant is slightly different. Altering the shape of branches and stems is one of the most dramatic and natural methods of creating differing instances of the same plant type. We present a sketch-based interface for modeling plant variations through specification of branch and stem shape. Our system is based on interaction with the 3D Tractus: a new physical interface we developed to support direct 3D sketching. The 3D strokes from the 3D Tractus are used as input to a biologically-based modeling method that mimics natural growth variation factors of real plants.
Constellation Models for Sketch Recognition
(The Eurographics Association, 2006) Sharon, Dana; Panne, Michiel van de; Thomas Stahovich and Mario Costa Sousa
Sketch-based modeling shares many of the difficulties of the branch of computer vision that deals with single image interpretation. Most obviously, they must both identify the parts observed in a given 2D drawing or image.We draw on constellation models first proposed in the computer vision literature to develop probabilistic models for object sketches, based on multiple example drawings. These models are then applied to estimate the most-likely labels for a new sketch. A multi-pass branch-and-bound algorithm allows well-formed sketches to be quickly labelled, while still supporting the recognition of more ambiguous sketches. Results are presented for five classes of objects.
Applying Scenarios in User-Centred Design to Develop a Sketching Interface for Human Modelling and Animation
(The Eurographics Association, 2006) Mao, Chen; Qin, Seng Feng; Wright, David K.; Peng, Jun; Thomas Stahovich and Mario Costa Sousa
This paper presents our user and usability studies for applying scenarios in user-centred design to develop a sketching interface for virtual human modelling and animation. In this approach, we utilise the User Centred System Design (UCSD) strategy and spiral lifecycles to ensure system usability and functionalities. A series of usability techniques were employed. After the initial conceptual design, a preliminary user study (including questionnaires and sketching observations) was undertaken to establish the formal interface design. Second, an informal user test was conducted on the first prototype: a sketch-based 3D stick figure animation interface . Finally, a formal user evaluation (including performance tests, sketching observations, and interviews) was carried out on the latest version: a sketch-based virtual human builder . During this iterative process, various paper-based and electronic-based sketching scenarios were created, which were acted-out by users to help designers evoke and verify design ideas, identify users needs, and test the prototype interfaces in real contexts. Benefiting from applying the UCSD strategy and scenario-based design to develop a natural and supportive sketching interface, our investigation can be a useful instantiation for the design of other sketching interfaces where these techniques have not been widely acknowledged and utilised in the past.
Sketching Reaction-Diffusion Texture
(The Eurographics Association, 2006) Phan, Ly; Grimm, Cindy; Thomas Stahovich and Mario Costa Sousa
In this work, we present an interactive interface for sketching synthesized textures. Reaction-Diffusion (RD) is used as the basis for texture synthesis. RD allows an unlimited amount of non-repeating texture and offers great flexibility for mapping textures to arbitrary surfaces. However, it can be difficult to find starting values of parameters that will produce interesting patterns. We use machine learning to resolve the difficulty of determining appropriate initial values of the RD system. The system described here allows a user to sketch a pattern of spots or stripes with arbitrary orientations, and then automatically generates a pattern with the same attributes as the sketch. It also allows the user to interactively create more complex textures by adding another layer of pattern, as well as manipulate the color of the resulting texture. We also show that this procedure can be applied to realistic 3D surfaces.
Parts, Image, and Sketch based 3D Modeling Method
(The Eurographics Association, 2006) Murakawa, Jun; Yoon, Ilmi; Hong, Tracie; Lank, Edward; Thomas Stahovich and Mario Costa Sousa
Despite their many benefits, challenges exist in the creation of 3D models, particularly for individual not currently skilled with 3D modeling software. To address this, we explore the creation of 3D modeling software for non-domain experts that uses a hierarchical parts database of generic 3D models, and deforms models into specific related target objects using image guided 3D model morphing. A human-in-the-loop sketching interface supports image registration and constrains our geometrical transformation to support real time morphing of generic models into accurate representations of new objects for which users wish a 3D model. Applying the application to the study of insects in biology, we find that the application supports the creation of realistic 3D models, and that the application is of value to educators and researchers in entomology.
An Initial Evaluation of a Pen-Based Tool for Creating Dynamic Mathematical Illustrations
(The Eurographics Association, 2006) LaViola Jr., Joseph J.; Thomas Stahovich and Mario Costa Sousa
MathPad2is a pen-based application prototype for creating mathematical sketches. Using a modeless gestural interface, it lets users make dynamic illustrations by associating handwritten mathematics with free-form drawings and provides a set of tools for graphing and evaluating mathematical expressions and solving equations. In this paper, we present the results of an initial evaluation of the MathPad2prototype, examining the user interface s intuitiveness and the application s perceived usefulness. Our evaluations are based on both performance and questionnaire results including first attempt gesture performance, interface recall tests, and surveys of user interface satisfaction and perceived usefulness. The results of our evaluation suggest that, although some test subjects had difficulty with our mathematical expression recognizer, they found the interface, in general, intuitive and easy to remember. More importantly, these results suggest the prototype has the potential to assist beginning physics and mathematics students in problem solving and understanding scientific concepts.
Producing Models From Drawings of Curved Surfaces
(The Eurographics Association, 2006) Kaplan, Matthew; Cohen, Elaine; Thomas Stahovich and Mario Costa Sousa
We present a method for creating 2 1 2D models from line drawings of opaque solid objects. We allow the artist to draw naturally, differing from many previous approaches. Our system allows both perspective and orthographic projection to be used and makes no a priori assumptions about the type of model to be produced (i.e. planar, curved, normalon) . The frontal geometry is reconstructed by placing constraints at the contours and solving a 2D variational system for the smoothest piecewise smooth surface. An analysis of line labelling allows us to determine what constraints are possible and/or required for each input line. However, because line labelling produces a combinatorial explosion of valid output geometries, we allow the user to guide the constraint selection and optimization with a simple user interface that abstracts the technical details away from the user. The system produces candidate reconstructions using different constraint values, from which the user selects the one that most closely approximates the model represented by the drawing. These choices allow the system to determine the constraints and reconstruct the model. The system runs at interactive speeds.
A Sketching Interface for 3D Modeling of Polyhedrons
(The Eurographics Association, 2006) Ku, Day Chyi; Qin, S. F.; Wright, D. K.; Thomas Stahovich and Mario Costa Sousa
We present an intuitive and interactive freehand sketching interface for 3D polyhedrons reconstruction. The interface mimics sketching with pencil on paper and takes freehand sketches as input directly. The sketching environment is natural by allowing sketching with discontinuous, overlapping and multiple strokes. The input sketch is a natural line drawing with hidden lines removed that depicts a 3D object in an isometric view. The line drawing is interpreted by a series of 2D tidy-up processes to produce a vertex-edge graph for 3D reconstruction. A novel reconstruction approach based on three-line-junction analysis and planarity constraint is then used to approximate the 3D geometry and topology of the graph. The reconstructed object can be transformed so that it can be viewed from different viewpoints for interactive design or as immediate feedback to the designers. A new sketch can then be added to the existing 3D object, and reconstructed into 3D by referring to the existing 3D object from the current viewpoint. The incremental modeling enables a 3D object to be reconstructed from multiple sketching sessions from different viewpoints. However, the interface is limited to reconstructing trihedrons from sketches without T-junctions to avoid ambiguity in the hidden topology determination.
Sketch-based Volumetric Seeded Region Growing
(The Eurographics Association, 2006) Chen, Hung-Li Jason; Samavati, Faramarz F.; Sousa, Mario Costa; Mitchell, J. Ross; Thomas Stahovich and Mario Costa Sousa
Interactive volume segmentation is an essential and important step in medical image processing. Conventional interactive methods typically demand significant amounts of time and do not lend to a natural interaction scheme with the 3D volume. In this paper we present a sketch-based interface for seeded region growing volume segmentation. In our approach, the user freely sketches regions of interest (ROI) directly over the 3D volume. Parts of the volume outside the ROIs are then automatically cut out in real-time. The user repeats this process as many times as necessary until he/she decides to specify the seed point 3D location directly at the ROI. To prevent unexpected segmentations, the region growing is restricted to the specified ROI. Our sketch-based system utilizes GPU programming to achieve real-time processing for both rendering and volumetric cutting independent from the size and shape of the sketched strokes.
Construction and Modification of 3D Geometry Using a Sketch-based Interface
(The Eurographics Association, 2006) Kara, Levent Burak; Shimada, Kenji; Thomas Stahovich and Mario Costa Sousa
We present an interactive pen-based computer program for designing 3D objects through direct sketching. The proposed techniques are tailored toward the creation of free-form curves and surfaces, and are therefore particulary useful for styling design purposes. In our approach, the design process consists of two main steps. In the first step, the user designs a wireframe model by sketching its constituent curves in 3D. Using purely sketch-based operations, the initial curves can then be modified as desired. In the second step, the user constructs interpolating surfaces on the wireframe to obtain a solid model. Again, through sketch-based operations, the user can modify the initial surfaces, and specify the boundary conditions if necessary. In addition to the main modeling operations, a gesture-based command interface allows many of the frequently used commands to be input through pen strokes. The utility of our system is demonstrated with various examples.
Automatic Interpretation of Proofreading Sketches
(The Eurographics Association, 2006) Rodríguez, Jose A.; Sánchez, Gemma; Lladós, Josep; Thomas Stahovich and Mario Costa Sousa
We present a sketch-based system for proofreading documents. The gestures and words drawn by the proofreader on a document view are translated into high-level actions that represent editions such as replace, insert, delete and others. Our particular system is not restricted to a predefined alphabet of gestures. Instead, any symbol can be employed for striking out words or drawing inserts. This provides more flexibility and adaptability to the user. In contrast to other similar works, our interface integrates interpretation and recognition of handwritten words. The described system has been implemented for proofreading digital documents on screen but also for paper documents printed on Anoto paper and annotated using a digital pen.

Browse

Browsing SBM06: Sketch Based Interfaces and Modeling 2006 by Issue Date

Results Per Page

Sort Options