Feature clusters for online recognition of graphic units in drawings

Abstract

Automated recognition of sketch drawings can provide the means for a natural interface between the designer and a design support system. Sketch drawing recognition is knowledge-intensive in the sense that the system must know what to look for in a drawing. In earlier work, we identified 24 different types of representations, termed graphic units. For recognition of graphic units we combine a multi-agent approach and online recognition. Each agent is specialised for one graphic unit. It continuously parses the online input stream for stroke features that fall within its scope. When an agent-specific threshold is reached, the agent puts a claim. Each agent has a specific cluster of features that can be viewed as distributed over a decision tree. The activation pattern of feature clusters over the decision tree is an indication which graphic unit is likely to be identified by the system. In this paper, we present the exhaustive set of features for agents and a binary decision tree over which the features are distributed.