A Novel Online Textual/Graphical Domain Separation Approach for Sketch-Based Interfaces

Multimodal interfaces can be profitably used to manage the increasingly complex applications and services which support human activities in everyday life. In particular, sketch-based interfaces enable users to effortless and powerful communication way to represent concepts and/or commands on different devices. This kind of information can be expressed by users performing two types of object: freehand drawing (graphical domain) and/or handwriting (textual domain). Usually, current frameworks require that users, somehow, indicate whether they are performing one or the other object. In this way, the frameworks can adopt the suitable recognition process to interpret as expressed by users. Moreover, more complex situations can occur when users perform, on a same schema, both types of object. This paper describes a novel intelligent framework able to automatically distinguish, in online way, freehand drawing from handwriting. The proposed approach works taking into account only the mathematical features belonging to the sketch performed by the user during interaction activity. Moreover, the approach can be used on schemata made up by heterogeneous objects which can also be overlapped. © 2009 Springer-Verlag Berlin Heidelberg