Advertisement

Deep Neural Network Based Salient Object Detection with Image Enhancement

  • Lecheng Zhou
  • Xiaodong GuEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11304)

Abstract

Salient object detection aims to discover the most visually attractive regions from images. It allows more efficient follow-up processing of images without handling redundant information. In this paper, we propose a novel framework based on deep neural network to detect salient objects. The proposed framework introduces feature enhancement to input images to improve the performance of the fully convolutional neural network (FCN). Images are segmented and weighted through superpixel based pulse coupled neural networks. Low-level features including contrast and spatial features are extracted during this procedure by removing background disturbance in images. Subsequent neural network takes the enhanced images in and produces the saliency maps. Finally, some refinements are made afterwards to achieve better saliency results. Experimental results on five representative benchmarks show the superiority of our model than other state-of-the-art methods. Furthermore, comparisons are made to verify the effectiveness of image enhancement part in our model.

Keywords

Salient object detection Fully convolutional neural network Image enhancement 

Notes

Acknowledgments

This work was supported in part by National Natural Science Foundation of China under grant 61771145 and 61371148.

References

  1. 1.
    Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. Pattern Anal. Mach. Intell. 20(11), 1254–1259 (1998)CrossRefGoogle Scholar
  2. 2.
    Achanta, R., Hemami, S., Estrada, F., Susstrunk, S.: Frequency-tuned salient region detection. In: 22th IEEE Conference on Computer Vision and Pattern Recognition, pp. 1597–1604. IEEE Press, Miami (2009)Google Scholar
  3. 3.
    Cheng, M.M., Zhang, G.X., Mitra, N.J., Huang, X., Hu, S.M.: Global contrast based salient region detection. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 409–416 (2011)Google Scholar
  4. 4.
    Yang, C., Zhang, L., Lu, H., Ruan, X., Yang, M.H.: Saliency detection via graph-based manifold ranking. In: 26th IEEE Conference on Computer Vision and Pattern Recognition, pp. 3166–3173. IEEE Press, Portland (2013)Google Scholar
  5. 5.
    Li, X., Lu, H., Zhang, L., Xiang, R., Yang, M.H.: Saliency detection via dense and sparse reconstruction. In: 26th IEEE Conference on Computer Vision and Pattern Recognition, pp. 2976–2983. IEEE Press, Portland (2013)Google Scholar
  6. 6.
    Jiang, B., Zhang, L., Lu, H., Yang, C., Yang, M.H.: Saliency detection via absorbing markov chain. In: 14th IEEE International Conference on Computer Vision, pp. 1665–1672. IEEE Press, Sydney (2013)Google Scholar
  7. 7.
    Jiang, H., Wang, J., Yuan, Z., Wu, Y., Zheng, N., Li, S.: Salient object detection: a discriminative regional feature integration approach. In: 26th IEEE Conference on Computer Vision and Pattern Recognition, pp. 2083–2090. IEEE Press, Portland (2013)Google Scholar
  8. 8.
    Yan, Q., Xu, L., Shi, J., Jia, J.: Hierarchical saliency detection. In: 26th IEEE Conference on Computer Vision and Pattern Recognition, pp. 1155–1162. IEEE Press, Portland (2013)Google Scholar
  9. 9.
    Zhu, W., Liang, S., Wei, Y., Sun, J.: Saliency optimization from robust background detection. In: 27th IEEE Conference on Computer Vision and Pattern Recognition, pp. 2814–2821. IEEE Press, Columbus (2014)Google Scholar
  10. 10.
    Cheng, M.M., Warrell, J., Lin, W.Y., Zheng, S., Vineet, V., Crook, N.: Efficient salient region detection with soft image abstraction. In: 14th IEEE International Conference on Computer Vision, pp. 1529–1536. IEEE Press, Sydney (2013)Google Scholar
  11. 11.
    Chen, T., Lin, L., Liu, L., Luo, X., Li, X.: DISC: deep image saliency computing via progressive representation learning. IEEE Trans. Neural Networks Learn. Syst. 27(6), 1135–1149 (2016)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Li, X., Zhao, L., Wei, L., Yang, M.H.: DeepSaliency: multi-task deep neural network model for salient object detection. IEEE Trans. Image Process. 25(8), 3919–3930 (2016)MathSciNetCrossRefGoogle Scholar
  13. 13.
    He, S., Lau, R.H.W., Liu, W., Huang, Z., Yang, Q.: SuperCNN: a superpixelwise convolutional neural network for salient object detection. Int. J. Comput. Vision 115(3), 330–344 (2015)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Li, H., Chen, J., Lu, H., Chi, Z.: CNN for saliency detection with low-level feature integration. Neurocomputing 226(C), 212–220 (2017)CrossRefGoogle Scholar
  15. 15.
    Hou, Q., Cheng M.M., Hu, X., Borji, A., Tu, Z., Torr, P.H.S.: Deeply supervised salient object detection with short connections. In: 30th IEEE Conference on Computer Vision and Pattern Recognition, pp. 3203–3212. IEEE Press, Honolulu (2017)Google Scholar
  16. 16.
    Eckhorn, R., Reitboeck, H.J., Arndt, M., Dicke, P.: Feature linking via synchronization among distributed assemblies: simulations of results from cat visual cortex. Neural Comput. 2(3), 293–307 (1990)CrossRefGoogle Scholar
  17. 17.
    Gu, X.: Feature extraction using unit-linking pulse coupled neural network and its applications. Neural Process. Lett. 27(1), 25–41 (2008)CrossRefGoogle Scholar
  18. 18.
    Wei, W., Li, Z.: Automated image segmentation based on modified PCNN and mutual information entropy. Comput. Eng. 36(13), 199 (2010)Google Scholar
  19. 19.
    Anchanta, R., Shaji, A., Smith, K., Luchhi, A., Fua, P., Susstrunk, S.: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2274–2282 (2012)CrossRefGoogle Scholar
  20. 20.
    Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: 28th IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440. IEEE Press, Boston (2015)Google Scholar
  21. 21.
    Liu, T., Sun, J., Zheng, N., Tang, X., Shum, H.: Learning to detect a salient object. In: 20th IEEE Conference on Computer Vision and Pattern Recognition, pp. 353–367. IEEE Press, Minneapolis (2007)Google Scholar
  22. 22.
    Cheng, M.M., Mitra, N.J., Huang, X., Hu, S.M.: SalientShape: group saliency in image collections. Visual Comput. Int. J. Comput. Graphics 30(4), 443–453 (2014)Google Scholar
  23. 23.
    Alpert, S., Galun, M., Basri, R., Brandt, A.: Image segmentation by probabilistic bottom-up aggregation and cue integration. IEEE Trans. Pattern Anal. Mach. Intell. 34(2), 315–327 (2012)CrossRefGoogle Scholar
  24. 24.
    Li, Y., Hou, X., Koch, C., Rehg, J.M., Yuille, A.L.: The secrets of salient object segmentation. In: 27th IEEE Conference on Computer Vision and Pattern Recognition, pp. 280–287. IEEE Press, Columbus (2014)Google Scholar
  25. 25.
    Jia, Y., Shelhamer, E., Donahue, J., et al.: Caffe: convolutional architecture for fast feature embedding. In: 22nd ACM International Conference on Multimedia, pp. 675–678. ACM Press, Orlando (2014)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Department of Electronic EngineeringFudan UniversityShanghaiChina

Personalised recommendations