摘要
目的为了更有效地评价各种失真类型的图像,提出了一种新颖的通用型无参考图像质量评价方法,它采取学习感知特征和空域自然统计特征相结合的方法来构建图像质量评价模型。方法在提取显著分块的36个空域自然统计特征的基础上,增加基于相位一致性熵、基于相位一致性均值、梯度均值以及失真图像的熵4个感知特征,采用支持向量机回归的学习方式来构建图像特征与人的主观分数的映射关系,进而根据所提取特征预测图像质量。结果在LIVE图像库上的实验结果表明,本文方法预测质量分数与人的主观分数具有较高的一致性,基本呈线性关系,鲁棒性较好,运行时间较短,综合性能较好。结论本文方法预测性能较好,特征选取合理,学习方法有效。
Objective In order to evaluate different kinds of distorted images efficiently, a novel general-purpose blind/no- reference image quality assessment is proposed, which combines perceptual features with spatial natural statistics features to construct an image quality assessment model. Method Four perceptual features-phase congruency entropy, mean phase congruency, mean gradient, and entropy of the distorted images are selected beside the 36 spatial natural statistics features of sharp patches, features. Support Vector Machine Regression （SVR） is adopted to build the relationship between image features and quality scores, yielding a measure of image quality. Result Experimental results in the LIVE database show that the proposed method accords closely with human subjective judgment. It has good robustness and short running time. Conclusion The proposed method has a good performance. The selected features are rational and the learning method is effective.
出处
《中国图象图形学报》
CSCD
北大核心
2014年第6期859-867,共9页
Journal of Image and Graphics
基金
国家自然科学基金项目(61273251)
民用航天"十二五"预先研究项目(D040201)
中国航天科技集团公司科技创新基金项目(CASC05131418)
关键词
无参考图像质量评价
感知特征
统计特征
支持向量机回归
blind/no-reference image quality assessment
perceptual feature
statistics feature
support vector machine regression
