This study proposed a novel framework for ear recognition based on Gabor wavelets and Support Vector Machine (SVM). The framework has three steps. In the first step, the ear is detected from an image of the face. In the second step, Gabor wavelets are used to extract ear feature. The Gabor wavelets, whose kernels are similar to the 2D receptive field profiles of the mammalian cortical simple cells, exhibit desirable characteristics of spatial locality and orientation selectivity. In the third step, when the Gabor features were obtained, classifications were done by SVM. Experiment results showed that the proposed framework is effective and accurate.