Similarity of Macaque Face Images based on PCA

摘要

In this work, Block PCA based method is used to build several subspaces for each macaque face image and a similarity criterion is proposed to distinguish family properties of macaques. A proper threshold value is determined through statistical analysis. Then, a series of experiments are carried out to verify the feasibility of this approach. The results demonstrate that it is proper to utilize similarity value as judgment criterion of macaque family properties and higher accurate rate is obtained. It can provide an effective way for population recognition of other species.