Abstract
We propose a homography estimation method from the contours of planar regions. Standard pro jective invariants such as cross ratios or canonical frames based on hot points obtained from local dif- ferential properties are extremely unstable in real images suffering from pixelization, thresholding artifacts, and other noise sources. We explore alternative constructions based on global convexity properties of the con- tour such as discrete tangents and concavities. We show that a pro jec- tive frame can be robustly extracted from arbitrary shapes with at least one appreciable concavity. Algorithmic complexity and stability are the- oretically discussed and experimentally evaluated in a number of real applications including pro jective shape matching, alignment and pose estimation. We conclude that the procedure is computationally efficient and notably robust given the ill-conditioned nature of the problem.