首页 | 本学科首页   官方微博 | 高级检索  
     

采用边缘信息的屏幕图像质量评价
引用本文:符颖,曾焕强,倪张凯,陈婧,蔡灿辉.采用边缘信息的屏幕图像质量评价[J].信号处理,2017,33(4):540-545.
作者姓名:符颖  曾焕强  倪张凯  陈婧  蔡灿辉
作者单位:华侨大学信息科学与工程学院,厦门市移动多媒体通信重点实验室
基金项目:国家自然科学基金(61401167,61372107);福建省自然科学基金(2016J01308);华侨大学中青年教师科研提升资助计划(ZQN YX403);华侨大学高层次人才资助项目(600005 Z16X011);华侨大学研究生科研创新能力培育计划资助项目
摘    要:考虑到人类视觉系统(HVS)对边缘信息敏感且屏幕图像中包含大量边缘信息,本文提出采用边缘信息的屏幕图像质量评价方法。该方法首先从空域和频域分别提取参考和失真屏幕图像的边缘信息进而得到边缘信息相似度图,接着基于边缘信息提取屏幕图像中人眼感兴趣区域,最后利用感兴趣区域加权对所得边缘相似度图进行融合计算以获取最终评价分数值。实验结果表明所提算法具有较高的图像质量评价主客观一致性,其性能优于多个最新图像质量评价方法。 

关 键 词:屏幕图像(SCI)    人类视觉系统(HVS)    图像质量评价(IQA)
收稿时间:2016-10-25

Screen Content Image Quality Assessment Using Edge Information
Affiliation:School of Information Science and Engineering, Huaqiao University, Xiamen Key Laboratory of Mobile? Multimedia Communications
Abstract:Based on the observation that the human visual system (HVS) is sensitive to the edge information and the screen content image (SCI) contains fruitful edge information, a new SCI quality assessment method using edge information is presented in this paper. Firstly, the proposed method individually extracts the edge information of the reference SCI and its distorted version from the spatial and frequency domain and further computes the edge information similarity. Then, the interest region by human eye is established based on edge information. Finally, the interest region is used as weighting map to pool the edge information similarity map as a final SCI quality score. Experimental results show that the proposed method is able to achieve a high correlation with subjective prediction and outperforms multiple state-of-the-art quality assessment methods. 
Keywords:
点击此处可从《信号处理》浏览原始摘要信息
点击此处可从《信号处理》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号