篇名 | A New Extended Classifier to the NNC for Face Recognition |
---|---|
卷期 | 30:4 |
作者 | Jingyuan Zeng 、 Jianghong Guo 、 Xiansheng Wang 、 Tiansheng Hong |
頁次 | 045-056 |
關鍵字 | face recognition 、 least square problem 、 nearest neighbor classifier 、 skinny QRdecomposition 、 EI 、 MEDLINE 、 Scopus |
出刊日期 | 201908 |
DOI | 10.3966/199115992019083004004 |
In this paper, we propose a novel classifier which is based on subspaces of each class of training samples. This method has the following basic idea: the training samples among different classes are uncorrelated, but the distance between the test sample and the training samples in one class should be taking into account all training samples in this class. Compared with other methods, the contribution of this paper is that we use the skinny QR-decomposition for L small least square problems. From our analysis, we can find that our method is equivalent to the nearest neighbor classifier (NNC) when the training sample in any class is one. A large number of face recognition experiments on two face image databases show that our method can work efficiently and effectively.