Results 1 -
3 of
3
AN INTEGRATED FRAMEWORK ENHANCED WITH APPEARANCE MODEL FOR FACIAL MOTION MODELING, ANALYSIS AND SYNTHESIS
, 2004
"... Human faces provide important cues of human activities. Thus they are useful for human-human communication, human-computer interaction (HCI) and intelligent video surveillance. Computational models for face analysis and synthesis are useful for both basic research and practical applications. In this ..."
Abstract
- Add to MetaCart
Human faces provide important cues of human activities. Thus they are useful for human-human communication, human-computer interaction (HCI) and intelligent video surveillance. Computational models for face analysis and synthesis are useful for both basic research and practical applications. In this dissertation, we present a unified framework for 3D face motion modeling, analysis and synthesis. We first derive a compact geometric facial motion model from motion capture data. Then it is used for robust 3D non-rigid face tracking and face animation. One limitation of the geometric model is that it can not handle the motion details, which are important for both human perception and computer analysis. Therefore, we enhance our framework with appearance models. To adapt the appearance model to different illumination conditions and different people, we propose the following methods: (1) modeling illumination effects from one single face image; (2) reducing person-dependency using ratio-image technique; and (3) online appearance model transformation during tracking. We demonstrate the efficacy of this framework by experimental results on face recognition, expression recognition and face synthesis in varying conditions. We will also show the use
Capturing Subtle Facial Motions in 3D Face Tracking
"... Facial motions produce not only facial feature points motions, but also subtle appearance changes such as wrinkles and shading changes. These subtle changes are important yet difficult issues for both analysis (tracking) and synthesis (animation). Previous approaches were mostly based on models lear ..."
Abstract
- Add to MetaCart
(Show Context)
Facial motions produce not only facial feature points motions, but also subtle appearance changes such as wrinkles and shading changes. These subtle changes are important yet difficult issues for both analysis (tracking) and synthesis (animation). Previous approaches were mostly based on models learned from extensive training appearance examples. However, the space of all possible facial motion appearance is huge. Thus, it is not feasible to collect samples covering all possible variations due to lighting conditions, individualities, and head poses. Therefore, it is difficult to adapt such models to new conditions. In this paper, we present an adaptive technique for analyzing subtle facial appearance changes. We propose a new ratio-image based appearance feature, which is independent of a person’s face albedo. This feature is used to track face appearance variations based on exemplars. To adapt the exemplar appearance model to new people and lighting conditions, we develop an online EM-based algorithm. Experiments show that the proposed method improves classification results in a facial expression recognition task, where a variety of people and lighting conditions are involved. 1.
THREE-DIMENSIONAL HUMAN FACE FEATURE EXTRACTION FROM MULTI IMAGES
"... In this paper, we describe methods developed and preliminary results achieved by a fully automatic system for the measurement of 3-D face features using multi-images acquired simultaneously by multiple cameras. The method is based on multi-image photogrammetry and consists basically of five steps: c ..."
Abstract
- Add to MetaCart
(Show Context)
In this paper, we describe methods developed and preliminary results achieved by a fully automatic system for the measurement of 3-D face features using multi-images acquired simultaneously by multiple cameras. The method is based on multi-image photogrammetry and consists basically of five steps: calibration of the multiple camera system, acquisition of multi-images, edge extraction in all the acquired images, edge matching in the different images and computation of 3-D edges. A multi-image acquisition system was especially designed for face measurement purposes. Five IEEE-1394 progressive scan CCD cameras arranged convergently are used. A graphical user interface was developed for the real-time camera control, for the real-time display of multiple camera views and for the synchronized acquisition of multi-images. A reference field with signalized points was especially designed for the five camera acquisition system to allow a full automatic calibration procedure. The process is integrated in the graphical user interface software and the unique task required for the user is to place the calibration field at the indicated position. The signalized points are then fully automatically recognized and measured in the different images and the establishment of the external and internal orientation as well as parameters modeling the lens distortion is performed by