一种改进的马尔科夫吸收链显著性目标检测方法

被引:3
作者
吕建勇
唐振民
机构
[1] 南京理工大学计算机科学与工程学院
关键词
马尔科夫吸收链; 显著性目标检测; 查准率; 查全率; 平均吸收次数; 边界连通性; 背景节点; 目标粗略图;
D O I
10.14177/j.cnki.32-1397n.2015.39.06.007
中图分类号
TP391.41 [];
学科分类号
080203 ;
摘要
为了提高显著性目标检测的查准率和查全率,在传统的平均吸收次数作为显著性度量的基础上,提出了一种改进的显著性目标检测方法。利用边界连通性筛选出真正的背景节点以提高吸收节点的准确性。使用目标粗略图进行加权,以突出中央目标抑制背景。在MSRA-1000数据库上与7种流行算法特别是与基于马尔科夫吸收链的方法进行实验对比,该文方法的查准率和查全率较高。实验结果证明了所提算法的优越性。
引用
收藏
页码:674 / 679
页数:6
相关论文
共 19 条
[1]  
Saliency-seeded localizing region-based active contour for automatic natural object segmentation. Gao S,Yang J. International Conference on Pattern Recognition . 2012
[2]  
Frequency-tuned salient region detection. Achanta R,Hemami S,Estrada F,et al. IEEE International Conference on Computer Vision and Pattern Recognition . 2009
[3]   基于显著性分割的红外行人检测 [J].
杨阳 ;
杨静宇 .
南京理工大学学报, 2013, 37 (02) :251-256
[4]  
Random walks on graphs for salient object detection in images. Gopalakrishnan Viswanath,Hu Yiqun,Rajan Deepu. IEEE transactions on image processing : a publication of the IEEE Signal Processing Society . 2010
[5]   Lecture Notes in Computer Science [C]. 
The First International Conference on Web-Age Information Management
,1600
[6]  
Context-Aware Saliency Detection. Stas Goferman,Lihi Zelnik-Manor,Ayellet Tal. IEEE Transactions on Pattern Analysis and Machine Intelligence . 2012
[7]  
Saliency optimization from robust background detection. Zhu Wangjiang,Liang Shuang,Wei Yichen,et al. IEEE International Conference on Computer Vision and Pattern Recognition . 2014
[8]  
Automatic salient object segmentation based on context and shape prior. Jiang Huaizu,Wang Jingdong,Yuan Zejian,et al. http://www.researchgate.net/publication/267861070_Automatic_Salient_Object_Segmentation_Based_on_Context_and_Shape_Prior . 2015
[9]  
Saliency detection by muti-context deep learning. Zhao Rui,Ouyang Wangli,Li Hongsheng,et al. http://www.cv-foundation.org/openaccess/contentcvpr2015/ext/1B017ext.pdf . 2015
[10]  
Salient object detection:A discriminative regional feature integration approach. Jiang Huaizu,Wang Jingdong,Yuan Zejian,et al. IEEE Conference on Computer Vision and Pattern Recognition . 2014