基于图像区分模型的标牌可读性度量方法  

Metrics for aircraft signs readability based on image discriminability model

作　　者：门海艳[1] 杨凯[2] 黎谦[1] 

机构地区：[1]四川大学计算机科学学院,四川成都610065 [2]四川大学计算机学院图形图像研究所视觉合成图形图像技术国防重点学科实验室,四川成都610065

出　　处：《计算机工程与设计》2010年第20期4422-4425,共4页Computer Engineering and Design

基　　金：国家863高技术研究发展计划基金项目(2006AA12A104);国家自然科学基金重点项目(60736046)

摘　　要：为了能够对界面设计的优劣给出一个客观的度量标准,研究了背景图片上文字的可读性,提出了一种基于图像区分模型文本可读性度量方法。对基于JND的图像区分模型进行了认知与分析,在此基础上建立了文本可读性预测分析模型。分析了全局遮掩指数在预测文本可读性方面存在的问题与不足,综合考虑了文本及背景的对比度对背景RMS对比度的影响,提出了改进后的文本可读性预测算法。实验过程中,应用改进后的算法对高级气象显示情况下飞机标牌的可读性进行了计算,实验结果表明,用改进后的度量算法预测出来的结果更接近与真实值。从而表明了该方法的实用性。The goal of the metric is to provide objective measures of discriminability in support of design and manufacturing requirements for improved cockpit and air traffic management.The metric is based on our earlier work on image discrimination models for detection and discrimination.First,the introduction on the image discrimination models is given based on JND.Next,and the model about the pridiction of text readability is proposed.Third,the global masking index is analyzed,then the effect of the contrast from the text and background is expounded,the improved prediction algorithm is given.The experiment,we use the algorithm calculated the readability of the aircraft on the advanced weather display.The result is closer to the fact than the global masking index.This method is usefulness.

关 键 词：可读性 度量标准 图像区分 预测 文本信息 

分 类 号：TP39[自动化与计算机技术—计算机应用技术] TP753[自动化与计算机技术—计算机科学与技术]