Human face profile recognition using attributed string

摘要

A new attributed string matching method for human face profile recognition is proposed in this work. It is a novel idea to apply structural and syntactic technique on face profile matching. The approach works on a chain of profile line segments and highlights the favor of curve matching by suppressing the operations of insert and delete. The technique relies mainly on the merge and change operations of string to tackle the inconsistency problem of feature point detection. A quadratic penalty function is proposed to prohibit large angle changes and overmerging. The method produces very encouraging results and is found to be suitable for similar shape classification.