Affine Invariant Interesting Descriptors
Ron Kimmel, Cuiping Zhang, Alexander M. Bronstein, Michael M. Bronstein · 2009
Component trees or level set graphs have proved to be efficient tools for the extraction of stable features in many image analysis and understanding applications. In this paper, we explore the relation between level sets as feature descriptors and curvature scale-space. While most classical image feature detectors are based on linear scale-space, affine-invariant descriptors can be related to the curvature scale-space, in which closed level sets vanish at time proportional to their area and the connectedness is preserved. We provide observations about the affine invariance of objects in an image and design a framework for extracting more informative invariant features.