计算机科学 ›› 2018, Vol. 45 ›› Issue (8): 223-228.doi: 10.11896/j.issn.1002-137X.2018.08.040

所属专题: 医学图像

• 图形图像与模式识别 • 上一篇    下一篇

合成纹理图像的视觉相似性眼动分析

郭小英1, 李亮2, 耿海军1   

  1. 山西大学软件学院 太原0300061
    立命馆大学 京都60385772
  • 收稿日期:2017-11-10 出版日期:2018-08-29 发布日期:2018-08-29
  • 作者简介:郭小英(1985-),女,博士,讲师,硕士生导师,主要研究方向为图像视觉感知、图像分析、眼动数据分析和计算机视觉等,E-mail:guoxiaoying@sxu.edu.cn(通信作者); 李 亮(1982-),男,博士,副教授,主要研究方向为纹理合成与视觉感知等; 耿海军(1983-),男,博士,讲师,主要研究方向为网络体系结构和路由算法、计算机视觉等。
  • 基金资助:
    本文受国家自然科学基金项目(61603228)资助。

Eye-movement Analysis of Visual Similarity Perception on Synthesized Texture Images

GUO Xiao-ying1, LI Liang2, GENG Hai-jun1   

  1. School of Software Engineering,Shanxi University,Taiyuan 030006,China1
    Ritsumeikan University,Kyoto 6038577,Japan2
  • Received:2017-11-10 Online:2018-08-29 Published:2018-08-29

摘要: 探索了当人眼视觉感知纹理图像相似性时纹理特征(整体特征和局部特征)对视觉注意过程及相似性结果选择的影响。采用PGPC纹理合成方法,分别控制纹理的整体特征和局部特征,合成具有相同整体特征和局部特征的纹理。实验分为3组纹理场景,每一组有3幅纹理图像(A,B和S),S为对比纹理图像;实验者带着“纹理A和纹理B,哪个与纹理S更相似”的视觉感知任务观察纹理场景;利用Tobii T60眼动仪记录实验过程中观察者的眼动,跟踪获取89位实验者的眼动数据(眼动数据度量指标包含感兴趣区域内注视点散度和不同感兴趣区域间的眼跳次数);通过Tobii studio导出眼动数据,并基于R软件进行了方差分析和配对T检验等统计分析。通过对3组纹理图像的注视轨迹图及热点图的分析,验证了纹理整体特征和局部特征对视觉感知过程中的注视模式和相似性结果的选择有影响。实验结果表明:1)对于全局特征与对比纹理图像一致的纹理,其眼动注视点分散,而对于局部特征与对比纹理图像一致的纹理,其眼动注视点集中。2)纹理组相似性的最终选择结果与纹理组内不同纹理图像间的视觉搜索行为有关。

关键词: 纹理合成, 纹理图像, 相似性感知, 眼动数据, 眼动仪

Abstract: Global features and local features are very important for texture visual perception.This paper investigated the influence of the global features and local features of texture on the eye movement pattern and the relationship between the eye movement pattern and visual similarity selection.Firstly,the texture images were synthesized by separately controlling global textural features and local textural features with primitive,grain,and point configuration (PGPC) texture model,which is a mathematical morphology based texture model.In the experiment,three scenes were utilized.For each scene,three textures (A,B,and S) were included.Secondly,an experiment was conducted on visual similarity selection to acquire eye movement data while the subjects were viewing the visual similarities of texture scenes under the task of “Which texture is more similar to texture S,texture A or texture B?”.Experimental data were obtained with an eye tracker Tobii T60 by conducting two tests on 89 subjects.The collected eye-tracking data were analyzed in terms of fi-xation point variance in each ROI and fixation transfer count between different ROIs.Analysis results indicate that the global features and local features of texture influence the eye-movement pattern,namely,the texture image that is glo-bally similar to the compared texture contains dispersed fixation points,and the texture image that is locally similar to the compared texture contains concentrated fixation points.Besides,the final visual similarity selection is related to the visual search between different ROIs.

Key words: Eye-movement data, Eye-tracker, Similarity perception, Texture image, Texture synthesis

中图分类号: 

  • TP391
[1]NAVON D.Forest before trees:The precedence of global features in visual perception[J].Cognitive Psychology,1977,9(3):353-383.
[2]GRICE G R,CANHAM L,BOROUGHS J M,et al.Forest before trees?It depends where you look[J].Attention Perception &Psychophysics,1983,33(2):121-128.
[3]DULANEY C L,MARKS W.The effects of training and transfer on global/local processing[J].Acta Psychologica,2007,125(2):203-220.
[4]LI L,ASANO A,ASANO C M,et al.Statistical quantification of the effects of viewing distance on texture perception[J].Journal of The Optical Society of America Aoptics Image Science and Vision,2013,30(7):1394-1403.
[5]MILLS M,DODD M D.Which way is which? Examing global/local processing with symbolic cues[J].Journal of Experimental Psychology General,2014,143(4):1429-1436.
[6]TAMURA H,MORI S,YAMAWAKI T,et al.Textural Features Corresponding to Visual Perception[J].Systems Man and Cybernetics,1978,8(6):460-473.
[7]AMADASUN M,KING R A.Textural features correspondingto textural properties[J].Systems Man and Cybernetics,1989,19(5):1264-1274.
[8]LI L,ASANO A,ASANO C M,et al.Statistical analysis of human visual impressions on morphological image manipulation of gray scale textures[J].Optical Review,2010,17(2):90-96.
[9]DEARBORN W F.Book Review:How People Look at Pictures:A Study of the Psychology of Perception in Art Guy Thomas Buswell[J].The Elementary School Journal,1936,37(1):1,66-67.
[10]NELSON W W,LOFTUS G R.The functional visual field du-ring picture viewing.
[J].Journal of Experimental Psychology:Human Learning & Memory,1980,6(4):391-399.
[11]CHUA H F,BOLAND J E,NISBETT R E,et al.Cultural variation in eye movements during scene perception[J].Proceedings of the National Academy of Sciences of the United States of America,2005,102(35):12629-12633.
[12]GODWIN H J,HOUT M C,MENNEER T,et al.Visual Similarity Is Stronger Than Semantic Similarity in Guiding Visual Search for Numbers[J].Psychonomic Bulletin & Review,2014,21(3):689-695.
[13]HWANG Y M,LEE K C.Using an Eye-Tracking Approach to Explore Gender Differences in Visual Attention and Shopping Attitudes in an Online Shopping Environment[J/OL].http://dx.doi.org/10.1080/10447318.2017.1314611.
[14]HAN Y C.The Sequential Quality of Eye Movement in Obser-ving Different Shapes and Colors[J].Psychological Science,1997,20(1):40-43.(in Chinese)韩玉昌.观察不同形状和颜色时眼运动的顺序性[J].心理科学,1997,20(1):40-43.
[15]TAO Y.Research on eye movement perception to the pictures[J].Psychological Science,2001,24(2):194-196.(in Chinese)陶云.图画知觉过程的眼动研究进展[J].心理科学,2001,24(2):194-196.
[16]CAO X H.CAO L R.A Eye Movements Study on Sampling Traits for Irregular Geometric Figure Recognition[J].Acta Psychologica Sinica,2005,37(6):748-752.(in Chinese)曹晓华,曹立人.不规则几何图形识别取样特征的眼动研究[J].心理学报,2005,37(6):748-752.
[17]YANG W.Research on the difference bettween experts and no-vice When appreciating photograph works[D].Tianjin:Tianjin Normal University,2008.(in Chinese)杨文.专家与新手观看明星黑白头像图片的眼动研究[D].天津:天津师范大学,2008.
[18]GUO X.Visual analysis method of eye tracking signal in subjective image quality assessment[J].Modern Electronics Technique,2015(12):70-73.(in Chinese)郭昕.图像质量主观评价中眼动信号的可视化分析方法[J].现代电子技术,2015(12):70-73.
[19]JIANG W M,YANG Z X,JIANG M,et al.A Study on Usability of Application Icon Design in Smart Phones[J].Chinese Journal of Ergonomics,2015,21(3):21-24.(in Chinese)蒋文明,杨志新,蒋敏,等.智能手机应用程序图标设计的可用性研究[J].人类工效学,2015,21(3):21-24.
[20]ASANO A,OHKUBO T,MUNEYASU M,et al.Primitive and point configuration texture model and primitive estimation using mathematical morphology[C]∥Scandinavian Conference on Ima-ge Analysis.2003:178-185.
[21]LI L,ASANO A,ASANO C M,et al.Dual Primitive Estimation of Textures[J].IEICE Transactions on Fundamentals of Electronics,Communications and Computer Sciences,2011,94(4):1165-1169.
[22]YANG L,LI L,ASANO C M,et al.Primitive and grain estimation using flexible magnification for a morphological texture model[C]∥International Symposium on Memory Management.2011:190-199.
[1] 靳利贞, 李庆忠.
基于接缝一致性准则的结构纹理图像快速合成算法
Fast Structural Texture Image Synthesis Algorithm Based on Seam ConsistencyCriterion
计算机科学, 2022, 49(6): 262-268. https://doi.org/10.11896/jsjkx.210400039
[2] 王晓明,赵歆波.
阅读眼动追踪语料库的构建与应用研究综述
Survey of Construction and Application of Reading Eye-tracking Corpus
计算机科学, 2020, 47(3): 174-181. https://doi.org/10.11896/jsjkx.190800040
[3] 朱瑞超,钱文华,普园媛,徐丹.
自相似性匹配的纹理合成
Texture Synthesis Based on Self-similarity Matching
计算机科学, 2018, 45(6A): 215-219.
[4] 汤颖,林琦峰,肖廷哲,范菁.
基于GPU加速的保结构纹理合成
GPU-based Texture Synthesis with Preserved Structures
计算机科学, 2016, 43(4): 299-302. https://doi.org/10.11896/j.issn.1002-137X.2016.04.061
[5] 孙劲光,刘双九.
基于人工蜂群的D-Tile纹理合成算法
D-Tile for Texture Synthesis Based on Artificial Bee Colony
计算机科学, 2015, 42(2): 287-291. https://doi.org/10.11896/j.issn.1002-137X.2015.02.061
[6] 汤颖,肖廷哲,范菁.
基于GPU加速的快速图像相似区域查找
GPU-based Fast Search of Similar Patches in Images
计算机科学, 2014, 41(2): 290-296.
[7] 杜常青,钱文华.
二维纹理合成算法优化研究
Optimization Technique of 2D Texture Synthesis
计算机科学, 2013, 40(4): 314-323.
[8] 刘春英,房庆云,胡维华.
基于区别缺损对象的视频序列修复方法
Restoration Method for Video Sequences Based on Distinguishing Damaged Objects
计算机科学, 2012, 39(7): 267-269.
[9] 邹昆,韩国强,沃焱,张见威.
纹理合成中基于非标量距离度量的Graph Cut方法
Graph Cut Method Based on Non-scalar Distance Metric for Texture Synthesis
计算机科学, 2010, 37(2): 277-281.
[10] 瞿中,李楠.
混沌粒子群优化的纹理合成算法研究
Algorithm of Texture Synthesis Based on Chaos Particle Swarm Optimization
计算机科学, 2010, 37(10): 275-278.
[11] .
基于运行时纹理合成的纹理画刷

计算机科学, 2008, 35(6): 251-254.
[12] .
基于对偶树复小波和MRF模型的纹理图像分割

计算机科学, 2007, 34(1): 187-190.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!