Pair-Comparing Based Convolutional Neural Network for Blind Image Quality Assessment

Abstract

The introduction of convolutional neural network (CNN) in no-reference image quality assessment (NR-IQA) gains great success in improving its prediction accuracy, and the performance of CNN relies on the magnitude of training samples. However, many widely-used existing image databases cannot provide adequate samples for CNN training. In this paper, we propose a pair-comparing based convolutional neural network (PC-CNN) for blind image quality assessment. By taking reference images into consideration, we generate more training samples of patch pairs by different combinations of distorted images and reference image. We build a new CNN network which has two inputs for patch pairs and two outputs predicting the scores of patches. We conduct extensive experiments to evaluate the performance of our proposed PC-CNN, and the results show that it outperforms many state-of-the-art methods.