结合吸收Markov链和流行排序的显著性区域检测

doi:10.13229/j.cnki.jdxbgxb20170769

摘要/Abstract

摘要：

针对现有显著性检测方法在复杂自然图像下鲁棒性不高的问题,提出了一种结合吸收Markov链和流行排序的显著性检测算法。首先计算灰度图像的熵值得到超像素分割数目,然后分两阶段进行显著性检测。在第1阶段,首先对边缘超像素进行预处理,再使用背景先验进行基于吸收Markov链随机游走的显著性检测;在第2阶段,使用第1阶段计算的区域显著值作为前景查询种子用于流行排序对检测结果进一步优化。在公开数据集ASD和ECSSD上的实验结果表明:与现有显著性检测算法对比,该算法可以准确地突出显著目标,并有效地抑制背景,同时在F-measure等指标上也有很大改善。

关键词: 信息处理技术, 显著性检测, 背景先验, 前景查询种子, 吸收Markov链, 流行排序

Abstract:

Considering the low robustness of existing saliency detection methods in detecting complex nature images, a new saliency detection algorithm is proposed by combining the absorbing markov chain and manifold ranking. First, the entropy of the gray image is calculated to obtain the number of superpixels. Secondly, a two-stage saliency detection is used. In the first stage, the image edge superpixels are pre-processed, and then the first saliency map based on random walk on Absorbing Markov chain was computed by using background prior. In the second stage, the saliency scores computed by the first stage are used as foreground query seeds for manifold ranking in order to further optimize the saliency detection results. Experiments on publicly ASD and ECSSD databases demonstrate that, compared with the existing saliency detection methods, the proposed method can accurately highlight the saliency target, and effectively suppress the background area, while improve the performance evaluation of precision, recall and F-measure values.

Key words: information procession technology, saliency region detection, background prior, foreground query seed, absorbing Markov chain, manifold ranking

中图分类号:

TN919.8

苏寒松,代志涛,刘高华,张倩芳. 结合吸收Markov链和流行排序的显著性区域检测[J]. 吉林大学学报(工学版), 2018, 48(6): 1887-1894.

SU Han-song,DAI Zhi-tao,LIU Gao-hua,ZHANG Qian-fang. Saliency region detection combining absorbing Markov chain and manifold ranking[J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(6): 1887-1894.

图/表 9

图1

图2

图3

图4

图5

图6

图7

图8

表1

参考文献 27

[1]	Borji A, Itti L . State-of-the-art in visual attention modeling[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013,35:185-207. doi: 10.1109/TPAMI.2012.89 pmid: 22487985
[2]	Borji A, Cheng M M, Jiang H , et al. Salient object detection:a survey[J]. Eprint Arxiv, 2014,16(7):3118-3121.
[3]	Li Y, Hou X D, Koch C. The secrets of salient object segmentation [C]//IEEE International Conference on Computer Vision and Pattern Recognition, Columbus, 2014: 280-287.
[4]	Christopoulos C, Skodras A, Ebrahimi T . The JPEG2000 still image coding system: an overview[J]. IEEE Transaction on Consumer Electronics, 2000,46(4):1103-1127. doi: 10.1109/30.920468
[5]	Chen T, Cheng M M, Tan P , et al. Sketch2Photo:internet image montage[J]. ACM Transactions on Graphics, 2009,28(5):1-10.
[6]	Achanta R, Hemami S, Estrada F. Frequency-tuned salient region detection [C]//IEEE International Conference on Computer Vision and Pattern Recognition,Miami, 2009: 1597-1604.
[7]	Yan Q, Xu L, Shi J P, et al. Hierarchical saliency detection [C]//IEEE International Conference on Computer Vision and Pattern Recognition, Portland, 2013: 1155-1162.
[8]	Li X, Li Y, Shen C, et al, Contextual hypergraph modeling for salient object detection [C]//IEEE International Conference on Computer Vision, Sydney, 2013: 3328-3335.
[9]	Shen X, Wu Y. A unified approach to salient object detection via low rank matrix recovery [C]//IEEE International Conference on Computer Vision and Pattern Recognition, Providence, RI, USA, 2012: 853-860.
[10]	Perazzi F, Krahenbuhl P, Pritch Y, et al. Saliency filters: contrast based filtering for salient region detection [C]//IEEE International Conference on Computer Vision and Pattern Recognition, Providence, RI, USA, 2012: 733-740.
[11]	Cheng M M, Mitra N J, Huang X L , et al. Global contrast based salient region detection[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2015,37(3):569-582. doi: 10.1109/TPAMI.2014.2345401 pmid: 26353262
[12]	Wei Y C, Wen F, Zhu W J, et al. Geodesic saliency using background priors [C]//European Conference on Computer Vision, Berlin, 2012: 29-42.
[13]	Yang C, Zhang L, Lu H, et al. Saliency detection via graph-based manifold ranking [C]//IEEE International Conference on Computer Vision and Pattern Recognition, Portland, 2013,9(4):3166-3173.
[14]	Jiang B, Zhang L H, Lu H C , et al. Saliency detection via absorbing Markov chain[J/OL].[2017-07-15]..
[15]	Zhang Jian-ming, Sclaroff Stan, Lin Zhe, et al. Minimum barrier salient object detection at 80 FPS [C]//IEEE International Conference on Computer Vision,Santiago, Chile, 2015: 1404-1412.
[16]	Zhu W, Liang S, Wei Y, et al. Saliency optimization from robust background detection [C]//IEEE International Conference on Computer Vision and Pattern Recognition, Columbus, 2014: 2814-2821.
[17]	Hou X D, Zhang L Q. Saliency detection: a spectral residual approach [C]//IEEE International Conference on Computer Vision and Pattern Recognitions, Minneapolis, 2007: 1-8.
[18]	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, 1998,20(11):1254-1259. doi: 10.1109/34.730558
[19]	Harel J, Koch C, Perona P . Graph-based visual saliency[J]. Advances in Neural Information Processing System, 2006,19:545-552.
[20]	Cheng M M, Warrell J, Lin W Y , et al. Efficient salient region detection with soft image abstraction[DB/OL].[2017-07-16]..
[21]	Tong N, Lu H, Xiang R, et al. Salient object detection via bootstrap learning [C]//IEEE International Conference on Computer Vision and Pattern Recognition,Washington DC,USA, 2015: 1884-1892.
[22]	Yang J, Yang M H. Top-down visual saliency via joint crf and dictionary learning [C]//IEEE International Conference on Computer Vision and Pattern Recognition, Providence, RI, 2012: 2296-2303.
[23]	Radhakrishna A, Appu S, Kevin S , et al. SLIC superpixels compared to state-of-the-art superpixel methods[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012,34(11):2274-2282. doi: 10.1109/TPAMI.2012.120 pmid: 22641706
[24]	Tatler B W . The central fixation bias in scene viewing: selecting an optimal viewing position independently of motor biases and image feature distributions[J]. Journal of Vision, 2007,7(14):1-17.
[25]	谢畅, 朱恒亮, 林晓 , 等. 基于对比度优化流行排序的显著性目标检测算法[J]. 计算机应用, 2017,37(3):684-690.
	Xie Chang, Zhu Heng-liang, Lin Xiao , et al. Salient target detection algorithm based on contrast optimized manifold ranking[J]. Journal of Computer Applications, 2017,37(3):684-690.
[26]	曹向海, 邓湖明, 黄波 . 背景感知的显著性检测算法[J]. 系统工程与电子设计, 2014,36(8):1668-1672. doi: 10.3969/j.issn.1001-506X.2014.08.35
	Cao Xiang-hai, Deng Hu-ming, Huang Bo . Background aware saliency detection[J]. Systems Engineering and Electronics, 2014,36(8):1668-1672. doi: 10.3969/j.issn.1001-506X.2014.08.35
[27]	吕建勇, 唐振民 . 一种改进的马尔科夫吸收链显著性目标检测方法[J]. 南京理工大学学报:自然科学版, 2015,39(6):674-679. doi: 10.14177/j.cnki.32-1397n.2015.39.06.007
	Lv Jian-yong, Tang Zhen-min . Improved salient object detection based on absorbing Markov chain[J]. Journal of Nanjing University of Science and Technology(Natural Sciences), 2015,39(6):674-679. doi: 10.14177/j.cnki.32-1397n.2015.39.06.007

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

算法	代码	平均运行时间/s
SR	Matlab	0.615
IT	Matlab	0.611
GB	Matlab+C	0.735
FT	C	0.072
SF	C	0.202
LR	Matlab+C	0.40
RC	Matlab	0.752
GC	C	0.037
GS	C	2.0
AMC	Matlab+C	0.195
GMR	C	0.149
SO	Matlab+C	0.38
本文	Matlab+C	0.235