Parameterized point pattern matching and its application to recognition of object families

The problem of recognizing and localizing objects that can vary in parameterized ways is considered. To achieve this goal, a concept of parameterized point pattern is introduced to model parameterized families of such objects, and a parameterized point pattern matching algorithm is proposed. A parameterized point pattern is a very flexible concept that can be used to model a large class of parameterized objects, such as a pair of scissors with rotating blades. The proposed matching algorithm is formulated as a tree search procedure, and it generates all maximum matchings satisfying a condition called δ-boundedness. Several pruning methods based on the condition of δ-boundedness and their efficient computing techniques are given. The proposed matching algorithm is applied to a real shape matching problem in order to check the validity of the approach