In this work, we introduce a simple deep learning network, namely, PCANet to general-purpose blind/no-reference image quality assessment (NR-IQA). The goal of no-reference/blind image quality assessment (NR-IQA) is to devise a perceptual model that can accurately predict the quality of a distorted image as human opinions, in which feature extraction is an important issue. However, for most NR-IQA models, their features extraction process were some kind of supervised models and the features are usually natural scene statistics (NSS) based or are perceptually relevant, therefore the performance of these models is limited. In this paper, we present a new NR-IQA metric in which the features are extracted unsupervisely. Once the parameters have been given to the trained deep network, it outputs the final result without any manual mending. Experimental results on the LIVE dataset show that this approach yields state-of-the-art performance.