计算机科学 ›› 2014, Vol. 41 ›› Issue (10): 80-83.doi: 10.11896/j.issn.1002-137X.2014.10.018
樊强,齐春
FAN Qiang and QI Chun
摘要： 显著性检测是计算机视觉研究的一个重要问题。提出了一种由底向上的基于稀疏表示的显著性检测新算法。一般显著性检测主要包含两个部分,即图像特征提取和显著性度量。对于一幅给定的图像,首先利用独立成分分析(ICA)方法提取图像特征,然后用一个局部和全局模型对图像进行显著性度量。其中,利用一种低秩表示方法提取全局显著性,以及利用一种稀疏编码方法提取局部显著性。最后融合局部和全局显著图得到最终的显著图。在一个人眼关注数据库上与目前几种流行的方法进行了对比实验,实验结果显示所提出的方法能够得到更高的视觉关注预测准确率。
| [1] Avidan S,Shamir A．Seam carving for content-aware image resizing[J]．ACM Transactions on Graphics,2007,26(3):10 [2] Han J,Ngan K,Li M,et al．Unsupervised extraction of visual attention objects in color images[J]．IEEE Transactions on Circuits and Systems for Video Technology,2006,16(1):141-145 [3] Ko B,Nam J．Object-of-interest image segmentation based onhuman attention and semantic region clustering[J]．JOSA．A,2006,23(10):2462-2470 [4] Rutishauser U,Walther D,Koch C,et al.Is bottom-up attention useful for object recognition? [C]∥Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition．2004,2:37-44 [5] Itti U,Koch C,Niebur E．A model of saliency-based visual attention for rapid scene analysis[J]．IEEE Transaction on Pattern Analysis and Machine Intelligence,1998,20(11):1254-1259 [6] Judd T,Ehinger K,Durand F,et al．Learning to predict where humans look[C]∥IEEE International Conference on Computer Vision．2009:2106-2113 (下转第116页)(上接第83页) [7] Olshausen B,Field D．Emergence of simple-cell receptive fieldproperties by learning a sparse code for natural images[J]．Natural,1996,381(6583):607-609 [8] Bruce N,Tsotsos J．Saliency based on information maximization[C]∥Advances in neural information processing systems．2006,18:155-162 [9] Hou X,Zhang L．Dynamic visual attention:Searching for coding length increments[C]∥Advancesin Neural Information Proces-sing Systems．2008,21:681-688 [10] Yan J,Zhu M,Liu H．Visual saliency detection via sparsity pursuit[J]．IEEE Signal Processing Letters,2010,17(8):739-742 [11] Sun X,Yao H,Ji R.Saliency detection based on short-termsparse representation[C]∥Proceedings of 2010 IEEE 17th International Conference on Image Processing．2010:1101-1104 [12] Harel J,Koch C,Perona P．Graph-based visual saliency[C]∥Advances in Neural Information Processing System．2006:545-552 [13] Vinje W,Gallant J．Receptive fields and functional architecture in two nonstriate visual areas[J]．Journal of Nerophysiol,1965,28:229-289 [14] Liu G,Lin Z,Yu Y.Robust subspace segmentation by low-rank representation[C]∥International Conference on machine lear-ning．2010 [15] Liu G,Chen M,Ma Y．The augmented lagrange multiplier method for exact recovery of corrupted low-rank matrix[R]．UTUC Technical Report UILU-ENG-09-2215．2009 [16] Han B,Zhu H,Ding Y.Bottom up saliency based on weightedsparse coding residual[C]∥Proceedings of the 19th Annual ACM International Conference on Multimedia．2011:1117-1120 [17] Donoho D L.For most large underdetermined systems of linearequations the minimal[J]．Communications on pure and applied mathematics,2006,59(6):797-829 [18] Tibshirani R.Regression shrinkage and selection via the lasso[J]．Journal of the Royal Statistical Society Series B(Methodological),1996,58(1):267-288 [19] Mairal J,Bach F,Ponce J,et al．Online learning for matrix factorization and sparse coding[J]．The Journal of Machine Lear-ning Research,2010,11:19-60 [20] Borji A,Itti L．Exploiting local and global patch rarieties for saliency detection[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition．2012:478-485 [21] Davis J,Goadrich M．The relationship between Precision-Recall and ROC curves[C]∥Proceedings of the 23th International Conference on Machine Learning．2006:233-240 [22] Hou X,Zhang L．Saliency detection:A spectral residual ap-proach[C]∥IEEE International conference on Computer Vision and Pattern Recognition．2007:1-8 |
| No related articles found! |
|
||
首页