A Fully-Blind and Fast Image Quality Predictor with Convolutional Neural Networks

Zhengxue CHENG  Masaru TAKEUCHI  Kenji KANAI  Jiro KATTO  

Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E101-A   No.9   pp.1557-1566
Publication Date: 2018/09/01
Online ISSN: 1745-1337
DOI: 10.1587/transfun.E101.A.1557
Type of Manuscript: PAPER
Category: Image
Keyword: 
no-reference image quality assessment,  convolutional neural networks,  distortion recognition,  saliency map,  

Full Text: PDF(3.1MB)
>>Buy this Article


Summary: 
Image quality assessment (IQA) is an inherent problem in the field of image processing. Recently, deep learning-based image quality assessment has attracted increased attention, owing to its high prediction accuracy. In this paper, we propose a fully-blind and fast image quality predictor (FFIQP) using convolutional neural networks including two strategies. First, we propose a distortion clustering strategy based on the distribution function of intermediate-layer results in the convolutional neural network (CNN) to make IQA fully blind. Second, by analyzing the relationship between image saliency information and CNN prediction error, we utilize a pre-saliency map to skip the non-salient patches for IQA acceleration. Experimental results verify that our method can achieve the high accuracy (0.978) with subjective quality scores, outperforming existing IQA methods. Moreover, the proposed method is highly computationally appealing, achieving flexible complexity performance by assigning different thresholds in the saliency map.