Template matching method based on fusion of small number of positive samples

The invention relates to a template matching method based on fusion of a small number of positive samples. The invention is oriented to the field of image target recognition and positioning, and particularly relates to a target recognition and positioning method based on template matching. The method is characterized in that, through the fusion of a small number of template positive samples, robust and rapid recognition and positioning on a target can be achieved when the target has relatively large shielding, deformation, and gradient direction mutation. The method comprises the following four steps: 1, extracting target edge point sets in template images; 2, registering target edge point sets under different template images; 3, fusing target edge points; 4, performing similarity statistics based on the fused point sets. According to the method, the template matching problem, when a target has relatively large shielding, deformation, and gradient direction mutation, is solved, and the target identification a