Automated glaucoma detection is an important application of retinal image analysis. Compared with segmentation based approaches, image classification based approaches have a potential of better performance. However, it still remains a challenging problem for two reasons. Firstly, due to insufficient sample size, learning effective features is difficult. Secondly, the shape variations of optic disc introduce misalignment. To address these problem, a new classification based approach for glaucoma detection is proposed, in which deep convolutional networks derived from large-scale generic dataset is used to representing the visual appearance and holistic and local features are combined to mitigate the influence of misalignment. The proposed method achieves an area under the receiver operating characteristic curve of 0.8384 on the Origa dataset, which clearly demonstrates its effectiveness.