Computer facial animation for sign language visualization

[摘要] ENGLISH ABSTRACT:Sign Language is a fully-fledged natural language possessing its own syntax and grammar; a factwhich implies that the problem of machine translation from a spoken source language to SignLanguage is at least as difficult as machine translation between two spoken languages. SignLanguage, however, is communicated in a modality fundamentally different from all spokenlanguages. Machine translation to Sign Language is therefore burdened not only by a mappingfrom one syntax and grammar to another, but also, by a non-trivial transformation from onecommunicational modality to another.With regards to the computer visualization of Sign Language; what is required is a threedimensional, temporally accurate, visualization of signs including both the manual and nonmanualcomponents which can be viewed from arbitrary perspectives making accurate understandingand imitation more feasible. Moreover, given that facial expressions and movementsrepresent a fundamental basis for the majority of non-manual signs, any system concerned withthe accurate visualization of Sign Language must rely heavily on a facial animation componentcapable of representing a well-defined set of emotional expressions as well as a set of arbitraryfacial movements.This thesis investigates the development of such a computer facial animation system. We addressthe problem of delivering coordinated, temporally constrained, facial animation sequencesin an online environment using VRML. Furthermore, we investigate the animation, using a musclemodel process, of arbitrary three-dimensional facial models consisting of multiple alignedNURBS surfaces of varying refinement.Our results showed that this approach is capable of representing and manipulating highfidelity three-dimensional facial models in such a manner that localized distortions of the modelsresult in the recognizable and realistic display of human facial expressions and that these facialexpressions can be displayed in a coordinated, synchronous manner.

[发布机构] Stellenbosch University