Related Work
lUML Sketch Recognition
ØHse – Wizard of Oz – prefer to mouse and palette
ØIdeogramic UML, graffiti-like implementation
ØQueen’s Unversity, based on stroke length
lUML for Designing Agent Based Systems
ØOdell, Parunak and Bauer
ØBergenti and Poggi
lIndexing Audio-Visual Material
ØBrunelli, Mich, and Modena
lSketch Recognition to Locate Video Moment
ØKato, Kurita, Otsu, and Hirata
ØCho and Yoo
ØJacobs, Finkelstein, and Salesin
Others have been interested in recognizing sketches of UML diagrams.  Hse developed a wizard of oz experiment and determined that users  preferred a sketch-based tool to a mouse and palette tool.  Damm and others created a tool called Ideogrammic UML which recognizes UML class diagrams uses a graffiti-like implementation.  Users are required to draw objects in a particular direction and in a single stroke.  This is not always intuitive since some objects don’t look like they are sketched.  Queen’s University also developed a system for recognizing UML class diagrams where recognition is done on stroke length compared to the drawn perimeter.  This could cause some false positives since the letter M could be recognized as a rectangle using this metric.

UML diagrams have been found lacking simple ways to describe agent-based technologies (Odell, Parunak, and Bauer, 2000).  Bergenti and Poggi (2001) have created a CAD system to input UML diagrams for agent-based systems.  The system requires designers to enter their diagrams using a rigid CAD interface rather than allowing designers to sketch as they would naturally.

Much research has been done on indexing audio-visual material (Brunelli, Mich, and Modena, 1996).  Researchers have attempted to label the video with salient features within the video itself, focusing on the recognition and description of color, texture, shape, spatial location, regions of interest, facial characteristics, and specifically for motion materials, video segmentation, extraction of representative key frames, scene change detection, extraction of specific objects and audio keywords.
   While not much research has been done using sketch recognition to label and index a particular moment in video, a considerable body of work has been done using sketch recognition to find a particular moment in a pre-indexed video (Kato, Kurita, Otsu, and Hirata, 1992; Cho and Yoo, 1998; Jacobs, FinkelStein, and Salesin, 1995).