Retinal fundus images are of great importance in terms of disease diagnosis and their quality affects the accuracy and reliability of the diagnosis result. Therefore, image quality assessment is essential for retinal image analysis. There are many aspects for quality assessment, such as blur, noise, poor illumination, etc. In this paper, a no-reference quality assessment method for retinal image based on supervised classification is introduced. It mainly focuses on the blur and noise of an image. First, the images are enhanced by curvelet transformation to reduce the influence of noise when choosing the anisotropic patches. Second, anisotropic patches are selected on the enhanced images and then extracted on the original images. Then, nine features are adopted on the original green channel at the extracted anisotropic patches, which are effective with regard to blur and noise. Subsequently, random forest is used to classify the selected patches in an image. Finally, the image quality is obtained by the voting of the classifying result. The method is tested on the public digital retinal images database (HRF) for quality assessment. The area under the receiver operating characteristic (ROC) curve (AUC) is 95.7%, which is superior compared to existing methods. When compared pair-wise, our method obtains 18 out of 18 pairs which agrees to the human observer 100%. The algorithm is demonstrated to be effective to measure quality of retina images.