Topological Coding and Its Application in the Refinement of SIFT

Point pattern matching plays a prominent role in the fields of computer vision and pattern recognition. A technique combining the circular onion peeling and the radial decomposition is proposed to analyze the topology structure of a point pattern. The analysis derives a feature which records the topological structure of a point pattern. This novel feature is free from isometric assumption. It can resist various deformations such as adding points, suppressing points, affine transformations, projective transformations and elastic transformations to some degree. A refinement solution of the well known scale invariant feature transform (SIFT) algorithm is also proposed based on the probabilistic analysis of this feature. Experimental results show that the proposed refinement solution for SIFT using this feature is effective and robust.