徐兵,李振德

• 1:广东海洋大学信息学院

摘要(Abstract)：

视觉显著性检测在图像分割中起着重要作用。提出一种新的检测算法,首先将图像划分成不相交的超像素集合,并以其作为结点构建闭环图;然后利用背景先验知识与流形排名方法计算图中结点的显著度,得到视觉显著图;再使用Sigmoid函数对视觉显著图进行非线性校正,抑制背景结点的显著度和增强目标结点的显著度。不同算法的对比实验表明,新算法具有更好的检测性能,更易于区分背景区域和目标区域,同时也提高了鲁棒性。

关键词(KeyWords)： 显著性检测;显著图;超像素;流形排名;Sigmoid函数

Abstract:

Keywords:

基金项目(Foundation): 广东省2012年现代信息服务专项资金项目(GDEID2012IS071);; 广东海洋大学人才科研启动项目(1312253)

作者(Author): 徐兵,李振德

参考文献(References)：

• [1]Goferman S,Zelnik-Manor L,Tal A.Context-aware saliency detection[J].Pattern Analysis and Machine Intelligence,IEEE Transactions on,2012,34(10):1 915-1 926.
• [2]Itti L.Automatic foveation for video compression using a neurobiological model of visual attention[J].IEEE Transactions on Image Processing,2004,13(10):1 304-1 318.
• [3]Chen Tao,Cheng Ming-ming,Tan Ping,et al.Sketch2photo:Internet image montage[J].ACM Transactions on graphics,2009,28(5):1-10
• [4]Wang Le,Xue Jian-ru,Zheng Nan-ning,et al.Automatic salient object extraction with contextual cue[C]//W.cleon anderson.IEEE international conference on computer vision.Piscataway:Institute of electrical and electronics engineers inc,2011:105-112.
• [5]Yang Chuan,Zhang Li-he,Lu Hu-chuang,et al.Saliency detection via graph-based manifold ranking[C]//W.Cleon anderson.IEEE conference on computer vision and pattern recognition.portland:IEEE computer society,2013:3 166-3 173.
• [6]Liu Tie,Sun Jian,Zheng Nan-ning,et al.Learning to detect a salient object[C]//W.Cleon anderson.IEEE Conference on computer vision and pattern recognition.Piscataway:IEEE computer society,2011:353-367.
• [7]Ng A,Jordan M,Weiss Y,et al.On spectral clustering:Analysis and an algorithm[J].Neural information processing systems,2001,(4):849-856.
• [8]Gopalakrishnan V,Hu Y,Rajan D.Random walks on graphs for salient object detection in images[J].IEEE Transactions on image processing2010,19(12):3 232-3 242.
• [9]Zhou D,Weston J,Gretton A,et al.Ranking on data manifolds[J].Neural information processing systems,2004:169-176.
• [10]Achanta R,Appu S,Smith K,et al.SLIC Superpixels compared to state-of-the-art superpixel methods[J].Pattern analysis and machine intelligence,2012,34(11):2 274-2 282.
• [11]Itti L,Koch C,Niebur E.A model of saliency-based visual attention for rapid scene analysis[J].Pattern analysis and machine intelligence,1998,20(11):1 254-1 259.
• [12]Hertz J,Plamer R.Introduction to the neural computation[M].Addison wesley,california,1991.
• [13]Achanta R,Estrada F,Wils P,et al.Salient region detection and segmentation[C]//W.Cleon anderson.International conference on computer vision systems.Heidelberg:Springer verlag,2008:66-75.