Skip to main content
SpringerLink
Log in

Cosaliency Detection in Images Using Structured Matrix Decomposition and Objectness Prior

  • Conference paper
  • First Online:
Book cover Proceedings of 3rd International Conference on Computer Vision and Image Processing

Part of the book series: Advances in Intelligent Systems and Computing ((AISC,volume 1022))

  • 716 Accesses

Abstract

Cosaliency detection methods typically fail to perform in the situation where the foreground has multiple components. This paper proposes a novel framework, Cosaliency via Structured Matrix Decomposition (CSMD), for efficient detection of cosalient objects. This paper addresses the issue of saliency detection for images with multiple components in the foreground, by proposing a superpixel level, objectness prior. In this paper, we further propose a novel fusion technique to combine objectness prior to the cosaliency object detection framework. The proposed model is evaluated on challenging benchmark cosaliency dataset that has multiple components in the foreground. It outperforms prominent state-of-the-art methods in terms of efficiency.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 129.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 169.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Chang, K.-Y., Liu, T.-L., Lai, S.-H.: From co-saliency to co-segmentation: an efficient and fully unsupervised energy minimization model. In: CVPR, pp. 2129–2136 (2011)

    Google Scholar 

  2. Huazhu, F., Cao, X., Zhuowen, T.: Cluster-based co-saliency detection. IEEE Trans. Image Process. 22(10), 3766–3778 (2013)

    Article  MathSciNet  Google Scholar 

  3. Tan, Z., Wan, L., Feng, W., Pun, C.-M.: Image co-saliency detection by propagating superpixel affinities. In: ICASSP, pp. 2114–2118 (2013)

    Google Scholar 

  4. Cao, X., Tao, Z., Zhang, B., Huazhu, F., Feng, W.: Self-adaptively weighted co-saliency detection via rank constraint. IEEE Trans. Image Process. 23(9), 4175–4186 (2014)

    MathSciNet  MATH  Google Scholar 

  5. Chen, H.-T.: Preattentive co-saliency detection. In: ICIP, pp. 1117–1120 (2010)

    Google Scholar 

  6. Li, H., Meng, F., Ngan, K.: Co-salient object detection from multiple images. IEEE Trans. Multimed. 15(8), 1896–1909 (2013)

    Google Scholar 

  7. Li, H., Ngan, K.: A co-saliency model of image pairs. IEEE Trans. Image Process. 20(12), 3365–3375 (2011)

    Article  MathSciNet  Google Scholar 

  8. Ye, L., Liu, Z., Li, J., Zhao, W.-L., Shen, L.: Co-saliency detection via co-salient object discovery and recovery. Signal Process. Lett. 22(11), 2073–2077 (2015)

    Article  Google Scholar 

  9. Li, L., Liu, Z., Zou, W., Zhang, X., and Le Meur, O.: Co-saliency detection based on region-level fusion and pixel-level refinement. In: ICME, pp. 1–6 (2014)

    Google Scholar 

  10. Chen, Y.L., Hsu, C.-T.: Implicit rank-sparsity decomposition: applications to saliency/co-saliency detection. In: ICPR, pp. 2305–2310 (2014)

    Google Scholar 

  11. Yan, J., Zhu, M., Liu, H., Liu, Y.: Visual saliency detection via sparsity pursuit. IEEE Signal Process. Lett. 17(8), 739–742 (2010)

    Article  Google Scholar 

  12. X. Shen and Y. Wu: A unified approach to salient object detection via low rank matrix recovery. In: CVPR, 2012, 2296–2303

    Google Scholar 

  13. Lang, C., Liu, G., Yu, J., Yan, S.: Saliency detection by multitask sparsity pursuit. IEEE Trans. Image Process. 21(3), 1327–1338 (2012)

    Article  MathSciNet  Google Scholar 

  14. Zou, W., Kpalma, K., Liu, Z., Ronsin, J.: Segmentation driven low-rank matrix recovery for saliency detection. In: BMVC, pp. 1–13 (2013)

    Google Scholar 

  15. Candès, E., Li, X., Ma, Y., Wright, J.: Robust principal component analysis. J. ACM 58(3), 1–39 (2011)

    Google Scholar 

  16. Liu, G., Lin, Z., Yan, S., Sun, J., Yu, Y., Ma, Y.: Robust recovery of subspace structures by low-rank representation. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 171–184 (2013)

    Article  Google Scholar 

  17. Peng, H., Li, B., Ji, R., Hu, W., Xiong, W., Lang, C.: Salient object detection via low-rank and structured sparse matrix decomposition. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 818–832 (2017)

    Article  Google Scholar 

  18. Li, Y., Fu, K., Liu, Z., Yang, J.: Efficient saliency-model-guided visual co-saliency detection. IEEE Signal Process. Lett. 22(5), 588–592 (2014)

    Article  Google Scholar 

  19. Zhang, D., Fu, H., Han, J., Wu, F.: A review of co-saliency detection technique: fundamentals, applications, and challenge 1–16 (2016). arXiv:1604.07090

  20. Li, L., Liu, Z., Zou, W., Zhang, X., Le Meur, O.: Co-saliency detection based on region-level fusion and pixel-level refinement. In: ICME, pp. 1–6 (2014)

    Google Scholar 

  21. Liu, Z., Zou, W., Li, L., Shen, L., LeMeur, O.: Co-saliency detection based on hierarchical segmentation. IEEE Signal Process. Lett. 21(1), 88–92 (2014)

    Article  Google Scholar 

  22. Feichtinger, H.G., Strohmer, T.: Gabor analysis and algorithms: theory and applications. Springer, Berlin (1998)

    Google Scholar 

  23. Simoncelli, E.P., Freeman, W.T.: The steerable pyramid: a flexible architecture for multi-scale derivative computation. In: ICIP, pp. 444–447 (1995)

    Google Scholar 

  24. Shen, X., Wu, Y.: A unified approach to salient object detection via low rank matrix recovery. In: CVPR, pp. 2296–2303 (2012)

    Google Scholar 

  25. Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., S̈usstrunk, S.: Slic superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2274–2282 (2012)

    Google Scholar 

  26. Felzenszwalb, P., Huttenlocher, D.: Efficient graph-based image segmentation. Int. J. Comput. Vision 59(2), 167–181 (2004)

    Article  Google Scholar 

  27. Zhu, W., Liang, S., Wei, Y., Sun, J.: Saliency optimization from robust background detection. In: CVPR, pp. 2814–2821 (2014)

    Google Scholar 

  28. Xu, B., Bu, J., Chen, C., Cai, D., He, X., Liu, W., Luo, J.: Efficient manifold ranking for image retrieval. In: ACM SIGIR, pp. 525–534 (2011)

    Google Scholar 

  29. Alexe, B., Deselaers, T., Ferrari, V.: Measuring the objectness of image windows. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2189–2202 (2012)

    Article  Google Scholar 

  30. Sun, J., Ling, H.: Scale and object aware image thumbnailing. Int. J. Comput. Vision 104(2), 135–153 (2013)

    Article  MathSciNet  Google Scholar 

  31. Li, Y., Fu, K., Zhou, L., Qiao, Y., Yang, J., Li, B.: Saliency detection based on extended boundary prior with foci of attention. In: ICASSP, pp. 2798–2802 (2014)

    Google Scholar 

  32. Roy, S., Das, S.: Multi-criteria energy minimization with boundedness, edge-density and rarity, for object saliency in natural images. In: ICVGIP 2014, 55:1–55:8 (2014)

    Google Scholar 

  33. Batra, D., Kowdle, A., Parikh, D., Luo, J., Chen, T.: Icoseg: interactive co-segmentation with intelligent scribble guidance. In: CVPR, pp. 3169–3176 (2010)

    Google Scholar 

  34. Roy, S., Das, S.: Saliency detection in images using graph-based rarity, spatial compactness and background prior. In: VISAPP, pp. 523–530 (2014)

    Google Scholar 

Download references

Acknowledgements

The authors thank the faculty and members of Visualization and Perception Lab, Department of Computer Science and Engineering, IIT-Madras, for the constant guidance and support for this work. The authors would also like to acknowledge Marine Sensor Systems Lab, NIOT and Director, NIOT for their support.

Author information

Authors and Affiliations

  1. Visualization and Perception Lab, Department of Computer Science and Engineering, Indian Institute of Technology Madras, Chennai, India

    Sayanti Bardhan

  2. Marine Sensor Systems, National Institute of Ocean Technology, Chennai, India

    Sayanti Bardhan & Shibu Jacob

Authors
  1. Sayanti Bardhan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shibu Jacob
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sayanti Bardhan .

Editor information

Editors and Affiliations

  1. Computer Vision and Pattern Recognition Unit, Indian Statistical Institute, Kolkata, India

    Bidyut B. Chaudhuri

  2. Department of Advanced Information Technology and Computer Sciences, Tokyo Institute of Agriculture and Technology, Koganei, Tokyo, Japan

    Masaki Nakagawa

  3. Department of Computer Science, Indian Institute of Information Technology, Design and Manufacturing, Jabalpur, Jabalpur, Madhya Pradesh, India

    Pritee Khanna

  4. Department of Mathematics, Indian Institute of Technology Roorkee, Roorkee, Uttarakhand, India

    Sanjeev Kumar

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Bardhan, S., Jacob, S. (2020). Cosaliency Detection in Images Using Structured Matrix Decomposition and Objectness Prior. In: Chaudhuri, B., Nakagawa, M., Khanna, P., Kumar, S. (eds) Proceedings of 3rd International Conference on Computer Vision and Image Processing. Advances in Intelligent Systems and Computing, vol 1022. Springer, Singapore. https://doi.org/10.1007/978-981-32-9088-4_25

Download citation

  • DOI: https://doi.org/10.1007/978-981-32-9088-4_25

  • Published:

  • Publisher Name: Springer, Singapore

  • Print ISBN: 978-981-32-9087-7

  • Online ISBN: 978-981-32-9088-4

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics

Search

Navigation