Abstract | ||
---|---|---|
Recognizing human faces is one of the most important areas of research in biometrics. However, drastic change of facial poses is a big challenge for its practical application. This paper proposes generating frontal view face image using linear transformation in feature space for face recognition. We extract features from a posed face image using the kernel PCA. Then, we transform the posed face image into its corresponding frontal face image using the transformation matrix predetermined by learning. Then, the generated frontal face image is identified by three different discrimination methods such as LDA, NDA, or GDA. Experimental results show that the recognition rate with the pose transformation outperforms that without pose transformation greatly. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1016/j.patrec.2005.11.003 | Pattern Recognition Letters |
Keywords | Field | DocType |
face image,discriminant analysis,pose transformation,frontal face image,kernel pca,pose invariant face recognition,linear transformation,big challenge,face recognition,human face,generating frontal view face,recognition rate,pca,corresponding frontal face image,frontal view face image,invariant face recognition,transformation matrix,feature space | Facial recognition system,Computer vision,Feature vector,Pattern recognition,Three-dimensional face recognition,Kernel principal component analysis,Artificial intelligence,Linear discriminant analysis,Biometrics,Face detection,Transformation matrix,Mathematics | Journal |
Volume | Issue | ISSN |
27 | 7 | Pattern Recognition Letters |
Citations | PageRank | References |
22 | 0.89 | 10 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hyung-Soo Lee | 1 | 132 | 13.10 |
Daijin Kim | 2 | 1882 | 126.85 |