Abstract | ||
---|---|---|
This paper proposes a novel binary particle swarm optimization (PSO) algorithm using artificial immune system (AIS) for face recognition. Inspired by face recognition ability in human visual system (HVS), this algorithm fuses the information of the holistic and partial facial features. The holistic facial features are extracted by using principal component analysis (PCA), while the partial facial features are extracted by non-negative matrix factorization with sparseness constraints (NMFs). Linear discriminant analysis (LDA) is then applied to enhance adaptability to illumination and expression. The proposed algorithm is used to select the fusion rules by minimizing the Bayesian error cost. The fusion rules are finally applied for face recognition. Experimental results using UMIST and ORL face databases show that the proposed fusion algorithm outperforms individual algorithm based on PCA or NMFs. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1007/s00521-007-0148-0 | Neural Computing and Applications |
Keywords | DocType | Volume |
ORL face databases,holistic facial feature,individual algorithm,binary particle swarm optimization,proposed algorithm,partial facial features fusion,face recognition,artificial immune system,face recognition ability,partial facial feature,face recognitionfusion � multimodal biometricsprincipal component analysis � nonnegative matrix factorizationbinary particle swarm optimizationartificial immune system,proposed fusion algorithm,fusion rule | Journal | 17 |
Issue | ISSN | Citations |
5-6 | 1433-3058 | 3 |
PageRank | References | Authors |
0.44 | 12 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiaorong Pu | 1 | 85 | 11.17 |
Zhang Yi | 2 | 1765 | 194.41 |
Zhongjie Fang | 3 | 4 | 0.83 |