Learn More
CALI is a fast, simple and compact online recognizer that identifies Scribbles (multi-stroke geometric shapes) drawn with a stylus on a digitizing tablet. Our method is able to identify shapes of different sizes and rotated at arbitrary angles , drawn with dashed, continuous strokes or overlapping lines. We use temporal adjacency to allow users to input the(More)
Various systems have explored the idea of inferring 3D models from sketched 2D outlines. In all of these systems the underlying modeling methodology limits the complexity of models that can be created interactively. The ShapeShop sketch-based modeling system utilizes Hierarchical Implicit Volume Models (BlobTrees) as an underlying shape representation. The(More)
The emergence of touch-based mobile devices brought fresh and exciting possibilities. These came at the cost of a considerable number of novel challenges. They are particularly apparent with the blind population, as these devices lack tactile cues and are extremely visually demanding. Existing solutions resort to assistive screen reading software to(More)
User interfaces in modeling have traditionally followed the WIMP (Window, Icon, Menu, Pointer) paradigm. Though functional and very powerful, they can also be cumbersome and daunting to a novice user, and creating a complex model requires considerable expertise and effort. A recent trend is toward more accessible and natural interfaces, which has lead to(More)
Many indexing approaches for high–dimensional data points have evolved into very complex and hard to code algorithms. Sometimes this complexity is not matched by increase in performance. Motivated by these ideas, we take a step back and look at simpler approaches to indexing multimedia data. In this paper we propose a simple, (not simplistic) yet efficient(More)
The emergence of touch screen devices poses a new set of challenges regarding text-entry. These are more obvious when considering blind people, as touch screens lack the tactile feedback they are used to when interacting with devices. The available solutions to enable non-visual text-entry resort to a wide set of targets, complex interaction techniques or(More)
This paper presents a simple method to recognise multi-stroke sketches of geometric shapes. It uses temporal adjacency and global geometric properties of gures to recognise a simple vocabulary of geometric shapes including solid and dashed line styles, selection and delete gestures. The geometric features used convex hull, smallest-area regular polygons,(More)
– This paper presents a simple method, based on fuzzy logic, to recognize multi-stroke sketches of geometric shapes and uni-stroke gestural commands. It uses temporal adjacency and global geometric properties of figures to recognize a simple vocabulary of geometric shapes drawn in different line styles. The geometric features used (convex hull, largest-area(More)