No-reference image quality assessment with shearlet transform and deep neural networks

• Published in: Neurocomputing (Amsterdam) Vol. 154; pp. 94 - 109
• Main Authors: Li, Yuming, Po, Lai-Man, Xu, Xuyuan, Feng, Litong, Yuan, Fang, Cheung, Chun-Ho, Cheung, Kwok-Wai
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 22.04.2015
• Subjects: No-reference image quality assessment; Shearlet transform; Softmax classification; Stacked autoencoders; Shearlet transform; Softmax classification; Stacked autoencoders; No-reference image quality assessment
• ISSN: 0925-2312; 1872-8286
• DOI: 10.1016/j.neucom.2014.12.015

Nowadays, Deep Neural Networks have been applied to many applications (such as classification, denoising and inpainting) and achieved impressive performance. However, most of these works pay much attention to describe how to construct the relative framework but ignore to provide a clear and intuitive understanding of why their framework performs so well. In this paper, we present a general-purpose no-reference (NR) image quality assessment (IQA) framework based on deep neural network and give insight into the operation of this network. In this NR-IQA framework, simple features are extracted by a new multiscale directional transform (shearlet transform) and the sum of subband coefficient amplitudes (SSCA) is utilized as primary features to describe the behavior of natural images and distorted images. Then, stacked autoencoders are applied as ‘evolution process’ to ‘amplify’ the primary features and make them more discriminative. Finally, by translating the NR-IQA problem into classification problem, the differences of evolved features are identified by softmax classifier. Moreover, we have also incorporated some visualization techniques to analysis and visualize this NR-IQA framework. The resulting algorithm, which we name SESANIA (ShEarlet and Stacked Autoencoders based No-reference Image quality Assessment) is tested on several database (LIVE, Multiply Distorted LIVE and TID2008) individually and combined together. Experimental results demonstrate the excellent performance of SESANIA, and we also give intuitive explanations of how it works and why it works well. In addition, SESANIA is extended to estimate quality in local regions. Further experiments demonstrate the local quality estimation ability of SESANIA on images with local distortions. •A NR-IQA framework is proposed using shearlet transform and deep neural networks.•Intuitive explanations of how this framework works and why it works well are given.•This framework is extended to estimate image quality in local regions.