No-Reference Image Quality Assessment using Transfer Learning

Abstract

With the recent advancements in deep learning, high performance neural networks have been introduced. These neural networks also can be used to solve similar problems in a transfer learning approach. Recently, several state-of-the-art Convolutional Neural Networks (CNNs) are proposed for computer vision tasks. On the other hand, in-the-wild No-Reference (Blind) Image Quality Assessment (NR-IQA) problem is known as a challenging human perceptual problem. In this paper, a transfer learning approach is used to solve the problem of in-the-wild NR-IQA. With a few training times, the proposed neural network exceeds all the previous methods which are not using deep neural networks. Further, the proposed method predicts the opinion score distribution in its output which has more valuable information than single Mean Opinion Score (MOS). Moreover, the proposed method can accept arbitrary image size in its input which is often not applicable in the most CNNs which have a certain output size.