Schnass, KarinVandergheynst, Pierre2010-01-252010-01-252010-01-25201010.1109/ICASSP.2010.5495208https://infoscience.epfl.ch/handle/20.500.14299/46085WOS:000287096005101We present a new and computationally efficient scheme for classifying signals into a fixed number of known classes. We model classes as subspaces in which the corresponding data is well represented by a dictionary of features. In order to ensure low misclassification, the subspaces should be incoherent so that features of a given class cannot represent efficiently signals from another. We propose a simple iterative strategy to learn dictionaries which are are the same time good for approximating within a class and also discriminant. Preliminary tests on a standard face images database show competitive results.LTS2lts2classificationfeature selectionsubspace learningGrassmannian manifoldsdictionary learningtext::conference output::conference proceedings::conference paper