Investigating Human Performance in Hand-Drawn Symbol Autocompletion

Auto completion has proven effective in various text-based applications. Conversely, no experiments have been carried out on the automatic completion of hand-drawn symbols and only a few systems have been presented in the literature for this purpose. Nevertheless, such a feature might be useful in different domains, e.g. for accelerating symbol retrieval and for launching complex gestural commands. In this paper we present a user study aimed at evaluating the human performance in hand-drawn symbol auto completion. In particular, using a set of more than 100 symbols belonging to the Military Course of Action domain, we evaluated the conditions under which the users are willing to exploit the auto completion functionality and those under which they can use it efficiently. As a result, we obtained that in a drawing task the auto completion functionality can be used in a profitable way, with a drawing time saving of about 18%.