Graphics Reference
In-Depth Information
rather than simply responding to user commands. In this environment, the
test-bed is to teach school kids scientific principles via LEGO games. In this
learning task, the kids are taught to put gears together so that they can learn
principles about ratio and forces. In this HCI environment, we use face tracking
and facial expression techniques to estimate the users' states. Moreover, we use
animated 3D synthetic face as avatar to interact with the kids. In this topic, we
describe the experiment we have done so far and the lessons we have learned
in this process.
3. Book Organization
The remainder of the topic is organized as follows. In the next chapter,
we first give a review on the work in 3D face modeling. Then we present our
tools for modeling personalized 3D face geometry. Such 3D models will be used
throughout our framework. Chapter 3 introduces our 3D facial motion database
and the derivation of the geometric motion model. In Chapter 4, we describe
how to use the derived geometric facial motion model to achieve robust 3D
non-rigid face tracking. We will present experimental results in a model-based
very low bit-rate face video coding application. We shall present the facial mo-
tion synthesis using the learned geometric motion model in Chapter 5. Three
types of animation are described: (1) text-driven face animation; (2) offline
speech-driven animation; and (3) real-time speech driven animation. Chap-
ter 6 presents our flexible appearance model for dealing with motion details
in our face processing framework. An efficient method is proposed to model
illumination effects from a single face image. The illumination model helps
reduce the illumination dependency of the appearance model. We also present
ratio-image based techniques to reduce person-dependency of our appearance
model. In Chapter 7 and Chapter 8, we describe our works on coping with
appearance details in analysis and synthesis based on the flexible appearance
model. Experimental results on facial expression recognition and face synthe-
sis in varying conditions are presented to demonstrate the effectiveness of the
flexible appearance model. Finally, the topic is concluded with summary and
comments on future research directions.
Search WWH ::




Custom Search