东南大学学报（自然科学版）2016，Vol.46Issue(6)：1149-1154,6.DOI:10.3969/j.issn.1001-0505.2016.06.007
基于认知分层的图像复杂度研究
Study on image complexity based on cognitive layering method
摘要
Abstract
To investigate the encoding rules between image attributes and image complexity,the im-age complexity was studied from the perspective of the cognitive layering theory.Based on the grad-ual order of the cognitive process,the image complexity was divided into CP (complexity of presen-tation),CS(complexity of semantics)and CM(complexity of memory),mapping to the visual at-tributes,semantic attributes and decoding attributes.Then,a layering mapping model of image com-plexities was presented.Taking the metro map image as example,three complexities in the image were extracted and recoded into three levels as low,medium,high and then a visual search experi-ment was conducted by the eye-tracking technique.Experimental results show that the three com-plexities have many obvious corresponding features in layering encoding.The reaction time of high level CM encoding is the shortest,suggesting that the CM has the greatest effect on the cognitive ef-ficiency.According to the large visual noise in high level CS encoding,the CS should be encoded with high level CM to improve the cognitive efficiency.The high level CP encoding can decrease subjects' cognitive load,which favors the improvement of search efficiency.Experimental results confirm the rationality of layering image complexity,thus providing a reference for the complexity design of information images.关键词
图像复杂度/认知分层/人机交互/图像属性/映射方法Key words
image complexity/cognitive layering/human computer interaction/image attributes/mapping method分类
信息技术与安全科学引用本文复制引用
张晶,薛澄岐,沈张帆,王海燕,周蕾,周小舟,陈晓皎..基于认知分层的图像复杂度研究[J].东南大学学报（自然科学版）,2016,46(6):1149-1154,6.基金项目
国家自然科学基金资助项目（71471037，71271053）、江苏省普通高校研究生科研创新计划资助项目（KYLX15－0062）． （）
