Locating Facial Features and Pose Estimation Using a 3D Shape Model
ISVC '09 Proceedings of the 5th International Symposium on Advances in Visual Computing: Part I
Specularity removal for enhancing face recognition
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Face image enhancement using 3D and spectral information
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Adding facial actions into 3D model search to analyse behaviour in an unconstrained environment
ISVC'10 Proceedings of the 6th international conference on Advances in visual computing - Volume Part I
ACCV'10 Proceedings of the 2010 international conference on Computer vision - Volume part II
Face image enhancement taking into account lighting behavior on a face
CAIP'11 Proceedings of the 14th international conference on Computer analysis of images and patterns - Volume Part II
| Hi-index | 0.00 |
This paper proposes a method to estimate facial pose, ranging from frontal to profile, from an image captured under various illumination conditions. Our proposed method formulates pose estimation by minimization of the errorbetween the target image and an image reproduced by a 3Dappearance model. Taking a rough initial estimate, the pose is optimized so that the error is decreased by the steepest descent. The performances for static and realtime pose estimation are evaluated with test images captured under drastically varied illumination conditions. The experimental results show that our proposed method estimates facial poses including rotations indepth up to 60 degrees from the frontal with an average error of 2.3 degreeseven when the initial error is 10 degrees. Our proposed method is fast enough to realize a realtime face tracking system which runs at 20 frames per second on a Pentium 4 3.2 GHz PC.