Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Salient object detection via sparse representation and multi-layer contour zooming

© The Institution of Engineering and Technology
Received 23/04/2016, Accepted 19/12/2016, Revised 18/12/2016, Published 12/01/2017

Since image background is normally composed of congenial regions, it can be represented by a feature dictionary via sparse representation. Based on this theory, the authors propose a novel bottom-up saliency detection method that unites the syncretic merits of sparse representation and multi-hierarchical layers. In contrast to most pre-existing sparse-based approaches that only highlight the boundaries of a target, the proposed method highlights the entire object even if it is large. Given a source image, a multi-scale background dictionary is structured with the features form different layers. Each region of the image is then reconstructed by the dictionary to compute its reconstruction error as a saliency score. Although a reconstruction map can be generated by the saliency scores, it is not good enough to be the final result because of low resolution and high error detection rates. Therefore, in middle cue, they propose a multi-scale contour zooming approach to address the error detection across the hierarchical layers. To improve the resolution of the final detection, a pixel-level rectification based on the Bayesian observation likelihood is calculated as the bottom cue. Combining sparse representation and multi-scale correction, the precision of the final saliency map is significantly improved for the detection results.

Inspec keywords: image representation; image reconstruction; image resolution; object detection

Other keywords: multiscale background dictionary; multihierarchical layers; image reconstruction; congenial regions; source image; error detection rates; saliency score; image background; multiscale contour zooming approach; pixel-level rectification; feature dictionary; multiscale correction; reconstruction map; sparse representation; reconstruction error; multilayer contour zooming; bottom-up saliency detection method; hierarchical layers; Bayesian observation likelihood; sparse-based approaches; low image resolution

Subjects: Computer vision and image processing techniques; Optical, image and video signal processing

References

    1. 1)
      • 15. Gao, H.Y., Lam, K.M.: ‘Salient object detection using octonion with Bayesian inference’. Int. Conf. on Image Processing (ICIP), Paris, October 2014, pp. 3292–3296.
    2. 2)
      • 9. Zhang, L., Zhao, S., Liu, W., et al: ‘Saliency detection via sparse reconstruction and joint label inference in multiple features’, Neurocomputing, 2015, 155, pp. 1–11.
    3. 3)
      • 19. Cheng, M.M., Mitra, N.J., Huang, X., Torr, P.H., et al: ‘Global contrast based salient region detection’, IEEE Trans. Pattern Anal. Mach. Intell., 2015, 37, (3), pp. 569–582.
    4. 4)
      • 30. Tavakoli, H.R., Rahtu, E., Heikkila, J.: ‘Fast and efficient saliency detection using sparse sampling and kernel density estimation’, SCIA, 2011, 6688, (2), pp. 666–675.
    5. 5)
      • 36. Cheng, M.M., Warrell, J., Lin, W.Y., et al: ‘Efficient salient region detection with soft image abstraction’. Int. Conf. on Computer Vision (ICCV), Sydney, VIC, December 2013, pp. 1529–1536.
    6. 6)
      • 13. Shaker, F., Monadjemi, A.: ‘A new symmetry measure based on Gabor filters’. Iranian Conf. on Electrical Engineering (ICEE), Tehran, May 2015, pp. 705–710.
    7. 7)
      • 17. Yan, Q., Xu, L., Shi, J., et al: ‘Hierarchical saliency detection’. Computer Vision and Pattern Recognition (CVPR), Portland, OR, June 2013, pp. 1155–1162.
    8. 8)
      • 32. Murray, N., Vanrell, M., Otazu, X., et al: ‘Saliency estimation using a non-parametric low-level vision model’. Computer Vision and Pattern Recognition (CVPR), Colorado, Springs, June 2011, pp. 433–440.
    9. 9)
      • 1. Lang, C., Feng, J., Liu, G., et al: ‘Improving bottom-up saliency detection by looking into neighbors’, Circuits Syst. Video Technol., 2013, 23, (6), pp. 1016–1028.
    10. 10)
      • 37. Perazzi, F., Krahenbuhl, P., Pritch, Y., et al: ‘Saliency filters: contrast based filtering for salient region detection’. Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA, June 2012, pp. 733–740.
    11. 11)
      • 16. Achanta, R., Shaji, A., Smith, K., et al: ‘Slic superpixels’ (EPFL, 2010).
    12. 12)
      • 26. Wang, Z., Li, B.: ‘A two-stage approach to saliency detection in images’. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), Las Vegas, NV, March 2008, pp. 965–968.
    13. 13)
      • 35. Zhang, L., Tong, M.H., Marks, T.K., et al: ‘Sun: a Bayesian framework for saliency using natural statistics’, J. Vis., 2008, 8, (7), pp. 1–20.
    14. 14)
      • 23. Ksantini, R., Boufama, B., Memar, S.: ‘A new efficient active contour model without local initializations for salient object detection’, J. Image Video Process., 2013, 2013, (1), pp. 1687–5281.
    15. 15)
      • 21. Kim, J.S., Sim, J.Y., Kim, C.S.: ‘Multi scale saliency detection using random walk with restart’, IEEE Trans. Circuits Syst. Video Technol., 2014, 24, (2), pp. 198–210.
    16. 16)
      • 3. Itti, L., Koch, C., Niebur, E.: ‘A model of saliency-based visual attention for rapid scene analysis’, IEEE Trans. Pattern Anal. Mach. Intell., 1998, 20, (11), pp. 1254–1259.
    17. 17)
      • 10. Li, X., Lu, H., Zhang, L., et al: ‘Saliency detection via dense and sparse reconstruction’. Int. Conf. on Computer Vision (ICCV), Sydney, NSW, December 2013, pp. 2976–2983.
    18. 18)
      • 22. Sun, J., Lu, H., Liu, X.: ‘Saliency region detection based on Markov absorption probabilities’, Trans. Image Process, 2015, 24, (5), pp. 1639–1649.
    19. 19)
      • 29. Hou, X., Zhang, L.: ‘Saliency detection: A spectral residual approach’. Computer Vision and Pattern Recognition (CVPR), Minneapolis, MN, USA, June 2007, pp. 1–8.
    20. 20)
      • 18. Zhao, C., Liu, C., Lai, Z., et al: ‘Sparse embedding visual attention system combined with edge information’, AEU-IJEC, 2011, 65, (12), pp. 1061–1068.
    21. 21)
      • 28. Shi, Y.Q., Xu, L., Jia, J.: ‘Hierarchical image saliency detection on extended CSSD’, Trans. Pattern Anal. Mach. Intell., 2016, 38, (4), pp. 717–729.
    22. 22)
      • 31. Yang, C., Zhang, L., Lu, H.: ‘Graph-regularized saliency detection with convex-hull-based center prior’, SPL, 2013, 20, (7), pp. 637–640.
    23. 23)
      • 34. Seo, H.J., Milanfar, P.: ‘Static and space-time visual saliency detection by self-resemblance’, J. Vis., 2009, 9, (12), pp. 1–27.
    24. 24)
      • 24. Gao, H.Y., Lam, K.M.: ‘Salient object detection using octonion with Bayesian inference’. Int. Conf. on Image Processing (ICIP), Paris, October 2014, pp. 3282–3286.
    25. 25)
      • 4. Lai, Z., Wong, W.K., Xu, Y., et al: ‘Approximate orthogonal sparse embedding for dimensionality reduction’, IEEE Trans. Neural Netw. Learn. Syst., 2015, 27, (4), pp. 723–735.
    26. 26)
      • 11. Yuna, S., Chang, D.Y.: ‘Salient object detection based on sparse representation with image-specific prior’. Int. Symp. on Consumer Electronics (ISCE), JeJu Island, June 2014, pp. 1–2.
    27. 27)
      • 14. Olshausen, B., Field, D.: ‘Emergence of simple-cell receptive field properties by learning a sparse code for natural images’, Nature, 1996, 381, pp. 607–609.
    28. 28)
      • 20. Jiang, B., Zhang, L., Lu, H., et al: ‘Saliency detection via absorbing Markov chain’. Int. Conf. on Computer Vision (ICCV), Sydney, NSW, December 2013, pp. 1665–1672.
    29. 29)
      • 7. Shen, X., Wu, Y.: ‘A unified approach to salient object detection via low rank matrix recovery’. Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA, June 2012, pp. 853–860.
    30. 30)
      • 25. Wang, J., Lu, H., Li, X., et al: ‘Saliency detection via background and foreground seed selection’, Neurocomputing, 2015, 152, (25), pp. 359–368.
    31. 31)
      • 5. Lai, Z., Xu, Y., Chen, Q., et al: ‘Multilinear sparse principal component analysis’, IEEE Trans. Neural Netw. Learn. Syst., 2014, 25, (10), pp. 1942–1950.
    32. 32)
      • 39. Ma, X., Xie, X., Lam, K.M., et al: ‘Saliency detection based on singular value decomposition’, JVCI, 2015, 32, pp. 95–106.
    33. 33)
      • 2. Borji, A., Cheng, M.M., Jiang, H., et al: ‘Salient object detection: a benchmark’, Trans. Image Process., 2015, 24, (12), pp. 5706–5722.
    34. 34)
      • 38. Chen, T., Lin, L., Liu, L., et al: ‘DISC: deep image saliency computing via progressive representation learning’. TNNLS, 2016, pp. 1–15.
    35. 35)
      • 12. Thakur, U.S., Chubach, O.: ‘Texture analysis and synthesis using steerable pyramid decomposition for video coding’. Int. Conf. on Systems, Signals and Image Processing (IWSSIP), London, September 2015, pp. 204–207.
    36. 36)
      • 27. Achanta, R., Hemami, S., Estrada, F., et al: ‘Frequency-tuned salient region detection’. Computer Vision and Pattern Recognition (CVPR), Miami, FL, June 2009, pp. 1597–1604.
    37. 37)
      • 6. Lai, Z., Wong, W.K., Xu, Y., et al: ‘Sparse alignment for robust tensor learning’, IEEE Trans. Neural Netw. Learn. Syst., 2014, 25, (10), pp. 1779–1792.
    38. 38)
      • 33. Xie, Y., Lu, H.: ‘Visual saliency detection based on Bayesian model’. Int. Conf. on Image Processing (ICIP), Brussels, September 2011, pp. 645–648.
    39. 39)
      • 8. Chau, H.M., Deepu, R.: ‘Sparse likelihood saliency detection’. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), Kyoto, March 2012, pp. 897–900.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2016.0123
Loading

Related content

content/journals/10.1049/iet-cvi.2016.0123
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address