Accelerometers are common on many devices, including those required for text-entry. The GesText project investigated how to enter text with devices that are solely enabled with accelerometers. The challenge of text-entry with such devices can be overcome by the careful investigation of the human limitations in gestural movements with accelerometers. Preliminary studies provided insights into two potential text-entry designs that purely use accelerometers for gesture recognition. Later studies verified that a matrix-based text-entry system with a small set of simple gestures was the most efficient.
Eleanor Jones, Jason Alexander, Andreas Andreou, Pourang Irani, Sriram Subramanian, GesText: Accelerometer-based Gestural Text-entry Systems, In Conference on Human Factors in Computing Systems, ACM New York, NY, USA, 2010.