The paper proposes a new method for feature extraction using tensor based Each Mode Fisher Discriminant Analysis(EMFDA) over Multilinear Principle Components (MPCA) in effect of different classifiers while changing feature size. Initially the face datasets have been mapped into curvilinear tensor space and features have been extracted using Multilinear Principal Component Analysis (MPCA) followed by Fisher Discriminant Analysis, in each mode of tensor space. The ORL and YALE databases have been used, without any pre-processing, in order to test the effect of classifier in real time environment. © Springer International Publishing Switzerland 2014.
CITATION STYLE
Tripathi, C., Kumar, A., & Mittal, P. (2014). Face Recognition using MPCA-EMFDA based features under illumination and expression variations in effect of different classifiers. In Advances in Intelligent Systems and Computing (Vol. 264, pp. 45–55). Springer Verlag. https://doi.org/10.1007/978-3-319-04960-1_5
Mendeley helps you to discover research relevant for your work.