VizDraw: A platform to convert online hand-drawn graphics into computer graphics

With the adoption of tablet-based data entry devices, there is considerable interest in methods for converting hand-drawn sketches of flow charts, graphs and block diagram into accurate machine interpretations, a conversion process with many applications in engineering, presentations, and simulations. However, the recognition of hand-drawn graphics is a great challenge due to the visual similarity of many system components. This is complicated due to the significant differences in drawing styles between users.
The proposed method, VizDraw, establishes an architecture that utilizes a number of pattern recognition tools to convert hand-drawn diagrams into computer graphics by segmenting the original diagram into individual components. This method generates hypothesis graphs for each component, evaluates the hypotheses using forward and backward dynamic programming, and finally utilizes a rule-based floor planning routine for component and symbol placement. VizDraw is invariant to scaling, rotation, translation and style of drawing. The preliminary results show how VizDraw is used for engineering drawings, simulation, and incorporation into computer aided design (CAD) models.