logo

SCIENCE CHINA Information Sciences, Volume 59, Issue 3: 032104(2016) https://doi.org/10.1007/s11432-015-5420-9

Salient object detection via region contrast and graph regularization

More info
  • ReceivedApr 1, 2015
  • AcceptedJun 24, 2015
  • PublishedJan 18, 2016

Abstract

Detection of salient objects in an image is now gaining increasing research interest in computer vision community. In this study, a novel region-contrast based saliency detection solution involving three phases is proposed. First, a color-based super-pixels segmentation approach is used to decompose the image into regions. Second, three high-level saliency measures which could effectively characterize the salient regions are evaluated and integrated in an effective manner to produce the initial saliency map. Finally, we construct a pairwise graphical model to encourage that adjacent image regions with similar features take continuous saliency values, thus producing the more perceptually consistent saliency map. We extensively evaluate the proposed method on three public benchmark datasets, and show it can produce promising results when compared to 14 state-of-the-art salient object detection approaches.


Funded by

International Scientific and Technological Cooperation Projects of China(2015DFG12650)

National Natural Science Foundation of China(61573048)

National Natural Science Foundation of China(51475017)

Beijing Municipal Natural Science Foundation(4142033)


Acknowledgment

Acknowledgments

This work was supported by National Natural Science Foundation of China (Grant Nos. 61573048, 51475017), Beijing Municipal Natural Science Foundation (Grant No. 4142033), and International Scientific and Technological Cooperation Projects of China (Grant No. 2015DFG12650).


References

[1] Desimone R, Duncan J. Annu Rev Neurosci, 1995, 18: 193-222 Google Scholar

[2] Treisman A M, Gelade G. Cog Psychol, 1980, 12: 97-136 Google Scholar

[3] Achanta R, Hemami S, Estrada F, et al. Frequency-tuned salient region detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Miami, 2009. 1597--1604. Google Scholar

[4] Cheng M, Mitra N J, Huang X, et al. IEEE Trans Patt Anal Mach Intell, 2015, 37: 569-582 Google Scholar

[5] Yang C, Zhang L, Lu H, et al. Saliency detection via graph-based manifold ranking. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Portland, 2013. 3166--3173. Google Scholar

[6] Jiang H, Wang J, Yuan Z, et al. Salient object detection: a discriminative regional feature integration approach. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Portland, 2013. 2083--2090. Google Scholar

[7] Liu Y, Li X Q, Wang L, et al. Sci China Inf Sci, 2014, 57: 012104-582 Google Scholar

[8] Donoser M, Urschler M, Hirzer M, et al. Saliency driven total variation segmentation. In: Proceedings of IEEE International Conference on Computer Vision, Kyoto, 2009. 817--824. Google Scholar

[9] Hiremath P S, Pujari J. Int J Image Process, 2008, 2: 10-17 Google Scholar

[10] Feng J, Ma L, Bi F K, et al. Sci China Inf Sci, 2014, 57: 122302-17 Google Scholar

[11] Marchesotti L, Cifarelli C, Csurka G. A framework for visual saliency detection with applications to image thumbnailing. In: Proceedings of IEEE International Conference on Computer Vision, Kyoto, 2009. 2232--2239. Google Scholar

[12] Goferman S, Zelnik-Manor L, Tal A. IEEE Trans Patt Anal Mach Intell, 2012, 34: 1915-1926 Google Scholar

[13] Wei Y, Wen F, Zhu W, et al. Geodesic saliency using background priors. In: Proceedings of European Conference on Computer Vision, Florence, 2012. 29--42. Google Scholar

[14] Yan Q, Xu L, Shi J, et al. Hierarchical saliency detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Portland, 2013. 1155--1162. Google Scholar

[15] Itti L, Koch C, Niebur E. IEEE Trans Patt Anal Mach Intell, 1998, 11: 1254-1259 Google Scholar

[16] Alexe B, Deselaers T, Ferrari V. What is an object? In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, 2010. 73--80. Google Scholar

[17] Achanta R, Estrada F, Wils P, et al. Salient region detection and segmentation. In: Proceedings of 6th International Conference on Computer Vision Systems, Santorini, 2008. 66--75. Google Scholar

[18] Perazzi F, Krahenbuhl P, Pritch Y, et al. Saliency filters: contrast based filtering for salient region detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Providence, 2012. 733--740. Google Scholar

[19] Han J, He S, Qian X, et al. IEEE Trans Circ Syst Video Technol, 2013, 23: 2009-2021 Google Scholar

[20] Zhu W, Liang S, Wei Y, et al. Saliency optimization from robust background detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Columbus, 2014. 2814--2821. Google Scholar

[21] Han J, Zhang D, Hu X, et al. IEEE Trans Circ Syst Video Technol, 2015, 25: 1309-1321 Google Scholar

[22] Ma L, Chen L, Zhang X J, et al. Sci China Inf Sci, 2015, 58: 089301-1321 Google Scholar

[23] Shen X, Wu Y. A unified approach to salient object detection via low rank matrix recovery. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Providence, 2012. 853--860. Google Scholar

[24] Liu R, Cao J, Lin Z, et al. Adaptive partial differential equation learning for visual saliency detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Columbus, 2014. 3866--3873. Google Scholar

[25] Chang K Y, Liu T L, Chen H T, et al. Fusing generic objectness and visual saliency for salient object detection. In: Proceedings of IEEE International Conference on Computer Vision, Barcelona, 2011. 914--921. Google Scholar

[26] Li Y, Hou X, Koch C, et al. The secrets of salient object segmentation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Columbus, 2014. 280--287. Google Scholar

[27] Khuwuthyakorn P, Robles-Kelly A, Zhou J. Object of interest detection by saliency learning. In: Proceedings of European Conference on Computer Vision, Heraklion, 2010. 636--649. Google Scholar

[28] Liu T, Yuan Z, Sun J, et al. IEEE Trans Patt Anal Mach Intell, 2011, 33: 353-367 Google Scholar

[29] Kou F, Li Z, Wen C, et al. Perceptual based content adaptive $L_0$ smoothing. In: Proceedings of 14th Pacific-Rim Conference on Multimedia, Nanjing, 2013. 299--307. Google Scholar

[30] Achanta R, Shaji A, Smith K, et al. Slic superpixels. EPFL-REPORT-149300. 2010. Google Scholar

[31] Gopalakrishnan V, Hu Y, Rajan D. IEEE Trans Multimedia, 2009, 11: 892-905 Google Scholar

[32] Cheng M M, Warrell J, Lin W Y, et al. Efficient salient region detection with soft image abstraction. In: Proceedings of IEEE International Conference on Computer Vision, Sydney, 2013. 1529--1536. Google Scholar

[33] Margolin R, Tal A, Zelnik-Manor L. What makes a patch distinct? In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Portland, 2013. 1139--1146. Google Scholar

[34] Yang C, Zhang L, Lu H. IEEE Signal Process Lett, 2013, 20: 637-640 Google Scholar

[35] Xu L, Li H, Zeng L, et al. J Vis Commun Image Represent, 2013, 24: 465-476 Google Scholar

[36] Lafferty J, McCallum A, Pereira F C N. Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the 18th International Conference on Machine Learning. San Francisco: Morgan Kaufmann Publishers Inc., 2001. 282--289. Google Scholar

[37] Zhai Y, Shah M. Visual attention detection in video sequences using spatiotemporal cues. In: Proceedings of the 14th Annual ACM International Conference on Multimedia. New York: ACM, 2006. 815--824. Google Scholar

[38] Achanta R, Süsstrunk S. Saliency detection using maximum symmetric surround. In: Proceedings of IEEE International Conference on Image Processing, Hong Kong, 2010. 2653--2656. Google Scholar

[39] Jiang B, Zhang L, Lu H, et al. Saliency detection via absorbing markov chain. In: Proceedings of IEEE International Conference on Computer Vision, Sydney, 2013. 1665--1672. Google Scholar

[40] Borji A, Cheng M M, Jiang H, et al. Salient object detection: a benchmark. ArXiv e-prints, 2015. Google Scholar

[41] Alpert S, Galun M, Brandt A, et al. IEEE Trans Patt Anal Mach Intell, 2012, 34: 315-327 Google Scholar

[42] Li Z, Zheng J, Zhu Z, et al. IEEE Trans Image Process, 2015, 24: 120-129 Google Scholar

Copyright 2019 Science China Press Co., Ltd. 《中国科学》杂志社有限责任公司 版权所有

京ICP备18024590号-1