Title: Vision-based technique for secure recognition of voice-less commands

Authors: Wai Chee Yau, Dinesh Kant Kumar, Hans Weghorn

Addresses: School of Electrical and Computer Engineering, RMIT University, GPO Box 2476V Melbourne, Victoria 3001, Australia. ' School of Electrical and Computer Engineering, RMIT University, GPO Box 2476V Melbourne, Victoria 3001, Australia. ' Mechatronics Department, BA-University of Cooperative Education, Stuttgart 70174, Germany

Abstract: This article presents a secure method for identification of voice-less commands using mouth images, without evaluating sound signals. The main limitation in voice recognition technologies for internet applications is that the commands will be audible to other people in the vicinity. The proposed technique identifies the unspoken utterances using support vector machines. The proposed system is based on temporal integration of the video data to generate spatiotemporal templates (STT). Sixty-four Zernike Moments are extracted from each STT. The experimental results demonstrate that the proposed system yields promising in recognising English phonemes. The proposed technique is demonstrated to be invariant to global variations of illumination level. Such a system could be invaluable when it is important to communicate without making a sound, such as giving passwords and internet applications on mobile devices.

Keywords: human-computer interaction; HCI; motion segmentation; support vector machines; SVM; visual speech recognition; Zernike Moments; voiceless commands; mouth images; secure recognition; voice recognition; vision; security; soundless comminucation.

DOI: 10.1504/IJESDF.2008.021450

International Journal of Electronic Security and Digital Forensics, 2008 Vol.1 No.4, pp.323 - 335

Published online: 27 Nov 2008 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article