摘要
提出一个基于改进的Itti-Koch模型的感兴趣区域(Region of interest,ROI)提取算法,同时针对图像亮度特征对ROI提取的影响问题,从2个方面进行分析研究:一是根据不同亮度权重下提取的ROI,分析亮度特征对ROI提取的影响程度;二是对眼动数据提取图像的ROI和基于改进的Itti-Koch模型提取的图像ROI进行区域评价,计算两者之间的点对点区域相似度和位置区域相似度。研究结果表明:当亮度特征和颜色特征同时影响图像ROI提取时,亮度特征所占权重不宜超过0.5。
An extraction ROI algorithm was proposed based on improved Itti-Koch visual attention model.Aiming at the point of extraction region of interest（ROI） influenced by intensity feature in image,it was analyzed in two aspects.The influence degree of intensity feature on extraction ROI was calculated and analyzed with the experimental result of extraction ROI in different intensity weights.While the ROI of images was evaluated with fixation points of eye movement based on improved Itti-Koch visual attention model,and their point to point similarity and regional similarity was evaluated.The experimental results show that the weight of intensity feature should not exceed 0.5 as the intensity feature and color feature affect ROI extraction.
出处
《中南大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2012年第1期208-214,共7页
Journal of Central South University:Science and Technology
基金
国家自然科学基金资助项目(60970098
60903136
61173122)
中央高校基本科研业务费专项资金资助项目(201021200062)
湖南省自然科学基金资助项目(11JJ3067)
关键词
亮度特征
感兴趣区域
眼动
相似度
intensity feature
region of interest（ROI）
eye movement
similarity
