[1]叶聪,沈金龙.一种显著性区域提取的新方法[J].南京师大学报(自然科学版),2012,35(03):134-137.
 Ye Cong,Shen Jinlong.A Novel Saliency Region Detection Algorithm[J].Journal of Nanjing Normal University(Natural Science Edition),2012,35(03):134-137.
点击复制

一种显著性区域提取的新方法()
分享到:

《南京师大学报(自然科学版)》[ISSN:1001-4616/CN:32-1239/N]

卷:
第35卷
期数:
2012年03期
页码:
134-137
栏目:
计算机科学
出版日期:
2012-09-20

文章信息/Info

Title:
A Novel Saliency Region Detection Algorithm
作者:
叶聪1沈金龙2
( 1. 苏州信息职业技术学院计算机科学与技术系,江苏苏州215200) ( 2. 南京邮电大学计算机科学与技术系,江苏南京210046)
Author(s):
Ye Cong1Shen Jinlong2
1.Department of Computer Science,Suzhou College of Information Technology,Suzhou 215200,China
关键词:
视觉显著性贝叶斯理论中心位置偏倚神经网络
Keywords:
visual saliencyBayes’theoremcentral biasneural network
分类号:
TP391.41
摘要:
提出一个基于贝叶斯理论和统计学习理论的显著性提取算法.该方法基于贝叶斯理论分别阐明图像中不同特征信息、自下而上显著性和全局显著性不同位置的先验信息.本文针对特征融合问题分别使用加权线性组合Logistic模型和基于加权的非线性组合方法的正则化的神经网络来学习权值并获得所有因子.2个定位数据集的受试者工作特征(ROC)曲线的实验结果表明,我们的方法得到的显著图比其他先进的显著性模型效果更好.扩展的定量评价也证明了非线性组合优于线性组合的策略.
Abstract:
A visual saliency detection method based on Bayes’theorem and statistical learning is proposed in this paper. The method clarifies different feature likelihood and different location prior for bottom-up saliency and overall saliency in static images based on Bayes’theorem. For feature integration problem,a weighted linear combination method using logistic model,and a weighted non-linear combination method using regularized neural network are used to learn the weight parameters to combine all factors. Experimental results demonstrate that our method’s bottom-up saliency maps perform better than other state-of-the-art saliency models in two fixation data sets by the metric receiver operator characteristic ( ROC) curve. And the extensive quantitative evaluation also demonstrates that the non-linear combination outperforms the linear combination strategy.

参考文献/References:

[1] 余映,王斌,张立明. 基于脉冲余弦变换的选择性视觉注意模型[J]. 模式识别与人工智能,2010,23( 5) : 616-623.
[2] 韩成美,吕皖丽,罗斌. 基于Tchebichef 矩的感兴趣区水印[J]. 计算机工程与设计,2011,32( 5) : 1 585-1 588.
[3] Itti L,Koch C,Niebur E. A model of saliency-based visual attention for rapid scene analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,22( 11) : 1 254-1 260.
[4] Harel J,Koch C,Perona P. Graph-based visual saliency[J]. Neural Information Processing Systems,2006, 19: 545-552.
[5] Bruce N D B,Tsotsos J K. Saliency,attention and visual search: An information theoretic approach[J]. Journal of Vision, 2009,9: 1-24.
[6] Gao D,Han S,Vasconcelos N. Discriminant saliency,the detection of suspicious coincidences,and applications to visual recognition.[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31( 6) : 989-1 005.
[7] Zhang L,Tong M H,Marks T K,et al. SUN: A bayesian framework for saliency using natural statistics[J]. Journal of Vison, 2008,8 ( 7) : 1-20.
[8] Torralba A,Oliva A,Castelhano M S,et al. Contextual guidance of eye movements and attention in real-world scenes: the role of global features in object search[J]. Psychological Review,2006,113( 4) : 766-86.
[9] Judd T,Ehinger K,Durand F,et al. Learning to predict where humans look[J]. ICCV,2009: 8.
[10] Goferman S,Zelnik-Manor L,Tal A. Context-aware saliency detection[J]. IEEE Conference on Computer Vision and Pattern Recognition,2010: 2 376-2 383.

备注/Memo

备注/Memo:
基金项目: 国家自然科学基金( 61100135) .通讯联系人: 叶聪,硕士,讲师,研究方向: 图形图修处理. E-mail: fengyun_2012@126. com
更新日期/Last Update: 2013-03-11