COMPUTING SCIENCE An Efficient Application of Gesture Recognition from a 2D Camera for Rehabilitation of Patients with Impaired Dexterity

An efficient method for utilising a two-dimensional camera to recognise hand gestures in three-dimensional space is described. The work is presented within the context of a recuperation aid for younger children with impaired movement of the upper limbs. The application is designed for use on a standard Android tablet device in the home, as part of an interactive storybook, so the algorithms are necessarily efficient. The hand movement recognition is achieved through the attachment of brightly coloured models to the child's fingers which serve the dual purpose of providing easily trackable elements of the image, and encouraging the child to regard the application as a game rather than a chore. The application promotes repeated use of specific hand skills identified by the medical profession to stimulate and assess rehabilitation of patients with impaired upper limb dexterity. © 2013 Newcastle University. Printed and published by Newcastle University, Computing Science, Claremont Tower, Claremont Road, Newcastle upon Tyne, NE1 7RU, England. Bibliographical details USHAW, G., ZIOGAS, E., EYRE, J., MORGAN, G. An Efficient Application of Gesture Recognition from a 2D Camera for Rehabilitation of Patients with Impaired Dexterity [By] G. Ushaw, E. Ziogas, J. Eyre, G. Morgan Newcastle upon Tyne: Newcastle University: Computing Science, 2013. (Newcastle University, Computing Science, Technical Report Series, No. CS-TR-1368)