基于图像非平坦区域DCT特性和EGRNN的盲图像质量评价

被引：8

作者：

王俊平

李超

陈伟华

机构：

[1] 西安电子科技大学通信工程学院

来源：

计算机学报 | 2017年 / 40卷 / 11期

关键词：

盲图像质量评价; 图像非平坦区域; 视觉特征; DCT特征; 视觉屏蔽; 均衡广义回归神经网络;

D O I：

暂无

中图分类号：

TP391.41 [];

学科分类号：

080203 ;

摘要：

对图像的质量进行评价有着广泛的应用,为定量的衡量图像的降质水平,文中在无指定图像失真类型的情况下,提出了一种通用的盲图像质量评价(Blind Image Quality Assessment,BIQA)方法.该方法首先提出了图像平坦区域和非平坦区域及视觉屏蔽的概念.将分割图像的平坦和非平坦区域引入评价系统中,从图像的非平坦区域中提取出能反应图像质量的视觉特征(Visual Features,VF),视觉特征涵盖了图像空域特性和DCT变化后的频域特性.利用非平坦区域中提取的空域与频域的联合VF和差分平均意见得分(Difference Mean Opinion Score,DMOS)训练提出的均衡广义回归神经网络(Equalization General Regression Neural Network,EGRNN).最后用LIVE的IQA数据库Release2测试了该方法.实验表明,分割图像非平坦区域,降低了平坦背景对图像质量评价的干扰,提升了预测的稳定性和准确性.此外,EGRNN通过均衡层的引入解决了视觉屏蔽现象,对图像质量的预测效果高于GRNN(General Regression Neural Network).该BIQA方法较其他方法预测更准确、更稳定.

引用

页码：2492 / 2505

页数：14

共 13 条

[1] Blind image quality assessment for measuring image blur. Wang X,Tian B F,Liang C,et al. Proceedings of the Image and Signal Processing . 2008
[2] Blind image quality assessment based on multichannel feature fusion and label transfer. Wu Qingbo,Li Hongliang,Meng Fanman,et al. IEEE Transactions on Circuits . 2016
[3] A DCT statistics-based blind image quality index. Saad, Michele A.,Bovik, Alan C.,Charrier, Christophe. IEEE Signal Processing Letters . 2010
[4] A Two-Step Framework for Constructing Blind Image Quality Indices. Anush Krishna Moorthy,Alan Conrad Bovik. IEEE Signal Processing Letters . 2010
[5] A general regression neural network. Specht DF. IEEE Transactions on Neural Networks . 1991
[6] The Discrete Cosine Transform. Gilbert Strang. SIAM Review . 1999
[7] Image quality assessment: From error visibility to structural similarity. Wang, Zhou,Bovik, Alan Conrad,Sheikh, Hamid Rahim,Simoncelli, Eero P. IEEE Transactions on Image Processing . 2004
[8] Blind image quality assessment using a general regression neural network. Li, Chaofeng,Bovik, Alan Conrad,Wu, Xiaojun. IEEE Transactions on Neural Networks . 2011
[9] Blind image quality assessment using joint statistics of gradient magnitude and Laplacian features. Xue Wufeng,Mou Xuanqin,Zhang Lei,et al. IEEE Transactions on Image Processing . 2014
[10] Objective image quality assessment based on support vector regression. Manish Narwaria,Weisi Lin. IEEE Transactions on Neural Networks . 2010

← 1 2 →