On affine invariance in the Beltrami framework for vision

We use the geometric Beltrami framework to incorporate and explain some of the known invariant flows, e.g., the equi-affine invariant flow. It is also demonstrated that the new concepts put forward in this framework enable us to construct new invariant flows for the case where the codimension is greater than one, e.g., for color images and video.

[1]  Ron Kimmel,et al.  A general framework for low level vision , 1998, IEEE Trans. Image Process..

[2]  Luc Van Gool,et al.  An Extended Class of Scale-Invariant and Recursive Scale Space Filters , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Guillermo Sapiro,et al.  Invariant Geometric Evolutions of Surfaces and Volumetric Smoothing , 1997, SIAM J. Appl. Math..

[4]  A. Polyakov.  Quantum Geometry of Bosonic Strings , 1981 .

[5]  Olivier Faugeras,et al.  Three-Dimensional Computer Vision , 1993 .

[6]  On projective plane curve evolution , 1996 .

[7]  Yehoshua Y. Zeevi,et al.  Representation of colored images by manifolds embedded in higher dimensional non-Euclidean space , 1998, Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269).

[8]  Andrew P. Witkin,et al.  Scale-Space Filtering , 1983, IJCAI.

[9]  Ron Kimmel,et al.  From High Energy Physics to Low Level Vision , 1997, Scale-Space.

[10]  David A. Forsyth,et al.  Invariant Descriptors for 3D Object Recognition and Pose , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  A. Bruckstein,et al.  Invariant signatures for planar shape recognition under partial occlusion , 1993 .

[12]  P. Lions,et al.  Axioms and fundamental equations of image processing , 1993 .

[13]  K. Reidemeister.  Vorlesungen über Differentialgeometrie II , 1926 .

[14]  Guillermo Sapiro,et al.  Affine invariant detection: edges, active contours, and segments , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.