Global Gabor features for rotation invariant object classification

The human visual system can rapidly and accurately recognize a large number of various objects in cluttered scenes under widely varying and difficult viewing conditions, such as illuminations changing, occlusion, scaling or rotation. One of the state-of-the-art feature extraction techniques used in image recognition and processing is based on the Gabor wavelet model. This paper deals with the application of the aforementioned model for object classification task with respect to the rotation issue. Three training sample sizes were applied to assess the methodpsilas performance. Experiments ran on the COIL-100 database show the robustness of the Gabor approach when globally applied to extract relevant discriminative features. The method out-performs other state-of-the-art techniques compared in the paper such as, principal component analysis (PCA) or linear discriminant analysis (LDA).