Classification with the Hybrid of Manifold Learning and Gabor Wavelet

Abstract

AbstractWhile manifold learning algorithms can discover intrinsic low-dimensional manifold embedded in the high-dimensional Euclidean space, the discriminant ability of the low-dimensional subspaces obtained by the algorithms is often lower than those obtained by the conventional dimensionality reduction approaches. Furthermore, the original feature vectors may include redundancy such as high-order correlation which cannot be removed by manifold learning algorithms. To address the two problems, we first employ Gabor wavelet to remove intrinsic redundancies of images and obtain a set of over-completed feature vectors. Then a supervised manifold learning algorithm (ULLELDA) is applied to project Gabor-based data and out-of-the-samples into a common low-dimensional subspace. Experiments in two FERET face databases indicate that Gabors indeed help supervised manifold learning to remarkably improve the discriminant ability of low-dimensional subspaces.KeywordsFace RecognitionLinear Discriminant AnalysisDiscriminant AbilityFace DatabaseGabor WaveletThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.