얼굴 특징 정보를 이용한 동작 인식

다국어 초록 (Multilingual Abstract)

This paper describes a computer vision system based on active IR illumination for real-time gaze discrimination system. Unlike most of the existing gaze discrimination techniques, which often require assuming a static head to work well and require a cumbersome calibration process for each person, our gaze discrimination system can perform robust and accurate gaze estimation without calibration and under rather significant head movement. This is made possible by a new gaze calibration procedure that identifies the mapping from pupil parameters to screen coordinates using generalized regression neural networks (GRNNs). With GRNNs, the mapping does not have to be an analytical function and head movement is explicitly accounted for by the gaze mapping function. Furthermore, the mapping function can generalize to other individuals not used in the training. To further improve the gaze estimation accuracy, we employ a reclassification scheme that deals with the classes that tend to be misclassified. This leads to a 10% improvement in classification error. The angular gaze accuracy is about 5°horizontally and 8°vertically. The effectiveness of our gaze tracker is demonstrated by experiments that involve gaze-contingent interactive graphic display.

참고문헌 (Reference)

1 C. Morimoto, "Real-time multiple face detection using active illumination" 8-13, 2000

2 V. Pavlovic, "Multimodal speaker detection using error feedback dynamic Bayesian networks" 2000

3 I. Cohen, "Learning bayesian network classi.ers for facial expression recognition using both labeled and unlabeled data" 2003

4 C. Bregler, "Learning and recognizing human dynamics in video sequences" 568-574, 1997

5 P. Ekman, "Facial Action Coding System (FACS): Manual" Consulting Psychologists Press 1978

6 P. Ekman, "Facial Action Coding System (FACS): Manual" CD Rom 2002

7 N. Sebe, "Emotion recognition using a cauchy naive bayes classi.er" 2002

8 F.V. Jensen, "Bayesian Networks and Decision Graphs" Springer-Verlag 2001

9 A. Bobick, "Action recognition using probabilistic parsing" 196-202, 1998