The Application of Binary Particle Swarm Algorithm in Face Recognition
Guojian Cheng, Caiyun Shi, Kai Zhu, Kevin Gong · 2011
The Binary Particle Swarm Optimization (BPSO) algorithm is introduced for face recognition. To do this, the original face images are first transformed into feature vectors by utilizing two-dimensional Discrete Cosine Transform (DCT). Secondly, the features are selected by means of the BPSO algorithm from the feature vectors, in order to obtain the most representative features of human faces. Compared to Genetic Algorithms (GA), the BPSO algorithm can achieve a higher recognition rate by a few features. The results demonstrate that the BSPO algorithm possesses a high recognition rate for various human face recognition applications, verifying it as an effective feature selection approach.