Reverse-engineering scanning keyboards

Abstract

Scanning or soft keyboards are alternatives to physical computer keyboards that allow users with motor disabilities to compose text and control the computer using a small number of input actions. In this paper, we present the reverse Huffman algorithm (RHA), a novel Information Theoretic method that extracts a representative latent probability distribution from a given scanning keyboard design. By calculating the Jensen-Shannon Divergence (JSD)between the extracted probability distribution and the probability distribution that represents the body of text that will be composed by the scanning keyboard, the efficiency of the design can be predicted and designs can be compared with each other. Thus, using RHS provides a novel a priori context-aware method for reverse-engineering scanning keyboards. © 2012 Springer-Verlag.