图像亮度特征对ROI提取的影响

来源期刊:中南大学学报(自然科学版)2012年第1期

论文作者:陈再良 邹北骥 黄敏之 沈海澜 辛国江

文章页码:208 - 214

关键词:亮度特征;感兴趣区域;眼动;相似度

Key words:intensity feature; region of interest (ROI); eye movement; similarity

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。

Abstract:

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.

相关论文

  • 暂无!

相关知识点

  • 暂无!

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号