统计与信息论坛
統計與信息論罈
통계여신식론단
STATISTICS & INFORMATION TRIBUNE
2015年
2期
9-14
,共6页
胡文婷%周献中%欣益行%刘浈
鬍文婷%週獻中%訢益行%劉湞
호문정%주헌중%흔익행%류정
眼动%视觉注意分配%模糊核聚类
眼動%視覺註意分配%模糊覈聚類
안동%시각주의분배%모호핵취류
eye movements%visual attention allocation%kernel-based fuzzy clustering
视觉注意分配探讨个体如何选择性地注意外界信息。本文根据人类视觉系统的感知特点,提出一种定量描述视觉注意分配的方法。首先,模拟人类视觉感知机制,描述视线映射到界面上注视点的注意程度;然后,利用模糊核聚类算法计算注视点属于不同界面对象的程度,将注视点的注意程度和隶属度相结合构建两种视觉注意计算模型,分别为KFCM‐A模型和KFCM‐U模型;最后,设计相关眼动实验来验证视觉注意计算模型的有效性。实验结果表明:视觉注意计算模型能够较好地描述被试者个体的注意分配策略,且KFCM‐U模型识别被试者搜索目标的准确率高达94.4%,较优于KFCM‐A模型。
視覺註意分配探討箇體如何選擇性地註意外界信息。本文根據人類視覺繫統的感知特點,提齣一種定量描述視覺註意分配的方法。首先,模擬人類視覺感知機製,描述視線映射到界麵上註視點的註意程度;然後,利用模糊覈聚類算法計算註視點屬于不同界麵對象的程度,將註視點的註意程度和隸屬度相結閤構建兩種視覺註意計算模型,分彆為KFCM‐A模型和KFCM‐U模型;最後,設計相關眼動實驗來驗證視覺註意計算模型的有效性。實驗結果錶明:視覺註意計算模型能夠較好地描述被試者箇體的註意分配策略,且KFCM‐U模型識彆被試者搜索目標的準確率高達94.4%,較優于KFCM‐A模型。
시각주의분배탐토개체여하선택성지주의외계신식。본문근거인류시각계통적감지특점,제출일충정량묘술시각주의분배적방법。수선,모의인류시각감지궤제,묘술시선영사도계면상주시점적주의정도;연후,이용모호핵취류산법계산주시점속우불동계면대상적정도,장주시점적주의정도화대속도상결합구건량충시각주의계산모형,분별위KFCM‐A모형화KFCM‐U모형;최후,설계상관안동실험래험증시각주의계산모형적유효성。실험결과표명:시각주의계산모형능구교호지묘술피시자개체적주의분배책략,차KFCM‐U모형식별피시자수색목표적준학솔고체94.4%,교우우KFCM‐A모형。
Visual attention allocation investigates how individuals focus on external information selectively .Based on perceptual properties of the human visual system , in this paper we propose a quantitative method that is applied to measure visual attention allocation .This paper begins by simulating human visual attention systems based on their physiological structure and describing the degree of attention on eye fixation points as the same as the strength of eye‐interface connection .Next ,we use the kernel‐based fuzzy clustering algorithm to calculate the degree of eye fixation points belonging to different components ,and then combine the degree of attention and membership on eye fixation points to present two computational models of visual attention :KFCM‐A model and KFCM‐U model .Finally ,the related eye‐movement experiments are developed to verify the effectiveness of the visual attention computational model .The results of experiments indicate that the proposed models can describe subjects'attention allocation strategies explicitly .Besides ,on the aspect of recognizing the subjects'searching targets ,the accuracy of KFCM‐U model is 94 .4% ,w hich is better than that of KFCM‐A model .