3D objects recognition by optimal matching search of multinary relations graphs

Abstract A new method for 3D object optimal recognition from 2D single images is described. It introduces an optimization approach to inexact graph matching implemented by ordered search algorithm. The search is conducted on homomorphic or monomorphic trees constructed in a combinatorial state space. A min-max structure of the search guiding cost function combines error criteria based on hypothesized multinary geometrical relations with non-geometrical featural and contextual image information. The geometrical error criterion reflects the disparity of the estimated observation vectors derived from partial matches. These vectors are calculated by a novel “area ratio” method based on points or planar region primitives that are preferred for practical image segmentation. The experimental results demonstrate a significant reduction in the complexity of the matching problem (usually exponential), and low sensitivity to large image data errors.