基于视觉敏感度JPEG图像质量评价.pdfVIP

第37 卷 第19 期 计 算 机 工 程 2011 年10 月 Vol.37 No.19 Computer Engineering October 2011 ·图形图像处理· 文章编号：1000—3428(2011)19—0191—03 文献标识码：A 中图分类号：TP306 基于视觉敏感度的JPEG 图像质量评价 张尤赛，陈忠君 (江苏科技大学电子信息学院，江苏 镇江 212003) 摘 要：为解决无参考图像质量评价与人眼视觉系统(HVS)特征的一致性问题，提出一种基于视觉敏感度的 JPEG 图像质量评价方法。采 用支持向量回归神经网络学习和模拟 HVS 特征与平均主观得分之间的函数关系，利用边缘幅度和长度、背景活动度和亮度等视觉敏感度 特征，实现符合HVS 特征的无参考图像质量评价。实验结果表明，该方法的误差小、精度高、预测性能好，并与HVS 感知特征具有高度 一致性。 关键词：视觉敏感度；支持向量回归；神经网络；图像质量；无参考评价 JPEG Image Quality Assessment Based on Visual Sensitivity ZHANG You-sai, CHEN Zhong-jun (School of Electrical Information, Jiangsu University of Science and Technology, Zhenjiang 212003, China) 【Abstract 】This paper presents a visual sensitivity measurement method to assess the visual quality of JPEG images for consistency between image quality assessment without reference image and Human Visual System(HVS) features. Support Vector Regression Neural Network(SVR-NN) is used to approximate the functional relationship between HVS feature and Mean Opinion Score(MOS). The measuring of visual quality of JPEG images is realized using HVS features such as edge amplitude and length, background activity and luminance. Experimental results show that the method has less error, high accuracy, excellent estimation, and exhibits much higher correlation with HVS perception feature. 【Key words 】visual sensitivity; Support Vector Regression(SVR); neural network; image quality; no-reference assessment DOI: 10.3969/j.issn.1000-3428.2011.19.063 1 概述