16 October 2013 Recent developments in automated lip-reading
Author Affiliations +
Human lip-readers are increasingly being presented as useful in the gathering of forensic evidence but, like all humans, suffer from unreliability. Here we report the results of a long-term study in automatic lip-reading with the objective of converting video-to-text (V2T). The V2T problem is surprising in that some aspects that look tricky, such as real-time tracking of the lips on poor-quality interlaced video from hand-held cameras, but prove to be relatively tractable. Whereas the problem of speaker independent lip-reading is very demanding due to unpredictable variations between people. Here we review the problem of automatic lip-reading for crime fighting and identify the critical parts of the problem.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Richard Bowden, Richard Bowden, Stephen Cox, Stephen Cox, Richard Harvey, Richard Harvey, Yuxuan Lan, Yuxuan Lan, Eng-Jon Ong, Eng-Jon Ong, Gari Owen, Gari Owen, Barry-John Theobald, Barry-John Theobald, "Recent developments in automated lip-reading", Proc. SPIE 8901, Optics and Photonics for Counterterrorism, Crime Fighting and Defence IX; and Optical Materials and Biomaterials in Security and Defence Systems Technology X, 89010J (16 October 2013); doi: 10.1117/12.2029464; https://doi.org/10.1117/12.2029464


Back to Top