Multi-band modelling of appearance

Earlier work has demonstrated generative models capable of synthesising near photo-realistic grey-scale images of objects. These models have been augmented with colour information, and recently with edge information. This paper extends the active appearance model framework by modelling the appearance of both derived feature bands and an intensity band. As a special case of feature-band augmented appearance modelling we propose a dedicated representation with applications to face segmentation. The representation addresses a major problem within face recognition by lowering the sensitivity to lighting conditions. Results show that the localisation accuracy of facial features is considerably increased using this appearance representation under diffuse and directional lighting and at multiple scales.

[1]  Thomas Vetter,et al.  Learning novel views to a single face image , 1996, Proceedings of the Second International Conference on Automatic Face and Gesture Recognition.

[2]  Pierre Comon,et al.  Independent component analysis, A new concept? , 1994, Signal Process..

[3]  Timothy F. Cootes,et al.  Statistical models of appearance for medical image analysis and computer vision , 2001, SPIE Medical Imaging.

[4]  Stan Sclaroff,et al.  Active blobs , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[5]  Timothy F. Cootes,et al.  Statistical models of appearance for computer vision , 1999 .

[6]  Milan Sonka,et al.  Time-continuous segmentation of cardiac MR image sequences using active appearance motion models , 2001, SPIE Medical Imaging.

[7]  Gary Bradski,et al.  Computer Vision Face Tracking For Use in a Perceptual User Interface , 1998 .

[8]  Hans Henrik Thodberg.  Hands-on experience with active appearance models , 2002, SPIE Medical Imaging.

[9]  Nicholas I. Fisher,et al.  Statistical Analysis of Circular Data , 1993 .

[10]  Fred L. Bookstein,et al.  Principal Warps: Thin-Plate Splines and the Decomposition of Deformations , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Milan Sonka,et al.  Active appearance motion models for endocardial contour detection in time sequences of echocardiograms , 2001, SPIE Medical Imaging.

[12]  Michael Jones,et al.  Multidimensional Morphable Models: A Framework for Representing and Matching Object Classes , 2004, International Journal of Computer Vision.

[13]  Timothy F. Cootes,et al.  Face Recognition Using Active Appearance Models , 1998, ECCV.

[14]  Bjarne Kjær Ersbøll,et al.  Extending and Applying Active Appearance Models for Automated, High Precision Segmentation* , 2001 .

[15]  Timothy F. Cootes,et al.  On representing edge structure for model matching , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[16]  Timothy F. Cootes,et al.  Active Appearance Models , 1998, ECCV.

[17]  Timothy F. Cootes,et al.  Interpreting face images using active appearance models , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[18]  Milan Sonka,et al.  Multistage hybrid active appearance model matching: segmentation of left and right ventricles in cardiac MR images , 2001, IEEE Transactions on Medical Imaging.

[19]  Mikkel B. Stegmann,et al.  Object tracking using active appearance models , 2001 .

[20]  Jitendra Malik,et al.  Scale-Space and Edge Detection Using Anisotropic Diffusion , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  S. Sclaroff,et al.  Active voodoo dolls: a vision based input device for nonrigid control , 1998, Proceedings Computer Animation '98 (Cat. No.98EX169).

[22]  J. Gower.  Generalized procrustes analysis , 1975 .