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

access icon free CF-based optimisation for saliency detection

  • Author(s): Yuzhen Niu 1, 2, 3 ; Wenqi Lin 1 ; Xiao Ke 1, 2, 3
    • View affiliations
  • Source: Volume 12, Issue 4, June 2018, p. 365 – 376
    DOI:  10.1049/iet-cvi.2017.0512 , Print ISSN 1751-9632, Online ISSN 1751-9640
© The Institution of Engineering and Technology
Received 03/11/2017, Accepted 17/01/2018, Revised 08/01/2018, Published 19/01/2018

In view of the observation that saliency maps generated by saliency detection algorithms usually show similarity imperfection against the ground truth, the authors propose an optimisation algorithm based on clustering and fitting (CF) for saliency detection. The algorithm uses a fitting model to represent the quantitative relationship between ground truth and algorithm-generated saliency maps. The authors use the K-means method to cluster the images into k clusters according to the similarities among images. Image similarity is measured in terms of scene and colour by using the GIST and colour histogram features, after which the fitting model for each cluster is calculated. The saliency map of a new image is optimised by using one of the fitting models which correspond to the cluster to which the image belongs. Experimental results show that their CF-based optimisation algorithm improves the performance of various single image saliency detection algorithms. Moreover, the improvement achieved by their algorithm when using both CF strategies is greater than the improvement achieved by the same algorithm when not using the clustering strategy. In addition, their proposed optimisation algorithm can also effectively optimise co-saliency detection algorithms which already consider multiple similar images simultaneously to improve saliency of single images.

Inspec keywords: image colour analysis; image enhancement; optimisation

Other keywords: CF-based optimisation; image saliency detection algorithms; clustering and fitting; K-means method; saliency maps; colour histogram features; GIST; image similarity

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

References

    1. 1)
      • 20. Ye, L., Liu, Z., Li, J., et al: ‘Co-saliency detection via co-salient object discovery and recovery’, IEEE Signal Process. Lett., 2015, 22, (11), pp. 2073–2077.
    2. 2)
      • 8. Peng, H., Li, B., Ling, H., et al: ‘Salient object detection via structured matrix decomposition’. AAAI Conf. Artificial Intelligence, Palo Alto, USA, July 2013, pp. 1–14.
    3. 3)
      • 22. Bylinskii, Z., Judd, T., Oliva, A., et al: ‘What do different evaluation metrics tell us about saliency models?’ (Arxiv, 2016).
    4. 4)
      • 10. Scharfenberger, C., Wong, A., Fergani, K., et al: ‘Statistical textural distinctiveness for salient region detection in natural images’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, Washington, DC, USA, June 2013, pp. 979–986.
    5. 5)
      • 24. Ponomarenko, N., Silvestri, F., Egiazarian, K., et al: ‘On between-coefficient contrast masking of DCT basis functions’. Proc. Int. Workshop on Video Processing and Quality Metrics, Scottsdale, USA, 2007, pp. 25–26.
    6. 6)
      • 7. Kim, J., Han, D., Tai, Y., et al: ‘Salient region detection via high-dimensional color transform’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, OH, USA, June 2014, pp. 883–890.
    7. 7)
      • 37. Batra, D., Kowdle, A., Parikh, D., et al: ‘iCoseg: interactive co-segmentation with intelligent scribble guidance’. IEEE Conf. Computer Vision and Pattern Recognition, June 2010, pp. 3169–3176.
    8. 8)
      • 28. Sheikh, H.R., Bovik, A.C.: ‘Image information and visual quality’, IEEE Trans. Image Process., 2006, 15, (2), pp. 430–444.
    9. 9)
      • 2. Achanta, R., Susstrunk, S.: ‘Saliency detection for content aware image resizing’. IEEE Int. Conf. Image Processing, 2009, pp. 1005–1008.
    10. 10)
      • 11. Tu, W., He, S., Yang, Q., et al: ‘Real-time salient object detection with a minimum spanning tree’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, Las Vegas, NV, USA, June 2016, pp. 2334–234.
    11. 11)
      • 12. Zhu, W., Liang, S., Wei, Y., et al: ‘Saliency optimization from robust background detection’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, OH, USA, June 2014, pp. 2814–2821.
    12. 12)
      • 18. Chang, K., Liu, T., Lai, S.: ‘From co-saliency to co-segmentation: an efficient and fully unsupervised energy minimization model’. IEEE Conf. Computer Vision and Pattern Recognition, June 2011, pp. 2129–2136.
    13. 13)
      • 16. Fu, H., Cao, X., Tu, Z.: ‘Cluster-based co-saliency detection’, IEEE Trans. Image Process., 2013, 22, (10), pp. 3766–3778.
    14. 14)
      • 25. Ponomarenko, N., Eremeev, O., Lukin, V., et al: ‘Modified image visual quality metrics for contrast change and mean shift accounting’, 11th Int. Conf. The Experience of Designing and Application of CAD Systems in Microelectronics (CADSM), Zakarpattya Polyana-Svalyava, Ukraine, February 2011, pp. 305–311.
    15. 15)
      • 27. Wang, Z., Simoncelli, E.P., Bovik, A.C.: ‘Multi-scale structural similarity for image quality assessment’. Proc. IEEE ACSSC, Pacific Grove, CA, November 2004, pp. 09–12.
    16. 16)
      • 36. Cheng, M.M., Zhang, G.X., Mitra, N.J., et al: ‘Global contrast based salient region detection’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2011, pp. 409–416.
    17. 17)
      • 9. Yan, Q., Xu, L., Shi, J., et al: ‘Hierarchical saliency detection’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, Washington, DC, USA, June 2013, pp. 1155–1162.
    18. 18)
      • 19. Liu, Z., Zou, W., Li, L., et al: ‘Co-saliency detection based on hierarchical segmentation’, IEEE Signal Process. Lett., 2014, 21, (1), pp. 88–92.
    19. 19)
      • 5. Margolin, R., Tal, A., Zelnik-Manor, L.: ‘What makes a patch distinct?’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, Washington, DC, USA, June 2013, pp. 1139–1146.
    20. 20)
      • 30. Mitsa, T., Varkur, K.L.: ‘Evaluation of contrast sensitivity functions for the formulation of quality measures incorporated in half toning algorithms’. Proc. IEEE Int. Conf. ASSP, Minneapolis, MN, April 1993, pp. 301–304.
    21. 21)
      • 29. Gu, K., Liu, M., Zhai, G., et al: ‘Quality assessment considering viewing distance and image resolution. IEEE Trans. Broadcast., 2015, 61, (3), pp. 520–531.
    22. 22)
      • 32. Oliva, A., Torralba, A.: ‘Modeling the shape of the scene: a holistic representation of the spatial envelope’, Int. J. Comput. Vis., 2001, 42, (3), pp. 145–175.
    23. 23)
      • 13. Jiang, B., Zhang, L., Lu, H., et al: ‘Saliency detection via absorbing Markov chain’. Proc. IEEE Int. Conf. Computer Vision, Sydney, Australia, December 2013, pp. 1665–1672.
    24. 24)
      • 26. Larson, E.C., Chandler, D.M.: ‘Most apparent distortion: full-reference image quality assessment and the role of strategy’, J. Electron. Imaging, 2010, 19, (1), pp. 1–21.
    25. 25)
      • 33. Zhao, C., Liu, C., Lai, Z., et al: ‘Multi-scale GIST feature manifold for building recognition’, Neurocomputing, 2011, 74, (17), pp. 2929–2940.
    26. 26)
      • 4. Liu, T., Sun, J., Zheng, N.-N., et al: ‘Learning to detect a salient object’. IEEE Conf. Computer Vision and Pattern Recognition, June 2007, pp. 1–8.
    27. 27)
      • 21. Margolin, R., Zelnik-Manor, L., Tal, A.: ‘How to evaluate foreground maps’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, OH, USA, June 2014, pp. 248–255.
    28. 28)
      • 31. Ye, L., Liu, Z., Zhou, X., et al: ‘Saliency detection via similar image retrieval’, IEEE Signal Process. Lett., 2016, 23, (6), pp. 838–842.
    29. 29)
      • 23. Egiazarian, K., Astola, J., Ponomarenko, N., et al: ‘New full-reference quality metrics based on HVS’. Proc. Int. Workshop on Video Processing and Quality Metrics, Scottsdale USA, 2006.
    30. 30)
      • 3. Rubner, Y., Tomas, C.: ‘Perceptual metrics for image database navigation’ (Springer Science + Business Media, LLC, Boston, 2001).
    31. 31)
      • 38. Shotton, J., Winn, J., Rother, C., et al: ‘TextonBoost: joint appearance, shape and context modeling for multi-class object recognition and segmentation’. Proc. ECCV, May 2006, pp. 1–15.
    32. 32)
      • 15. Qin, Y., Lu, H., Xu, Y., et al: ‘Saliency detection via cellular automata’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, Boston, MA, USA, June 2015, pp. 110–119.
    33. 33)
      • 34. Sheikh, H.R., Sabir, M.F., Bovik, A.C.: ‘A statistical evaluation of recent full reference image quality assessment algorithms’, IEEE Trans. Image Process., 2006, 15, (11), pp. 3440–3451.
    34. 34)
      • 1. Toshev, J.S., Daniilidis, K.: ‘Image matching via saliency region correspondences’. IEEE Conf. Computer Vision and Pattern Recognition, June 2007, pp. 1–8.
    35. 35)
      • 14. Yang, C., Zhang, L., Lu, H., et al: ‘Saliency detection via graph-based manifold ranking’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, Washington, DC, USA, June 2013, pp. 3166–3173.
    36. 36)
      • 6. Wei, Y., Wen, F., Zhu, W., et al: ‘Geodesic saliency using background priors’. Proc. IEEE European Conf. Computer Vision, Firenze, Italy, October 2012, pp. 29–42.
    37. 37)
      • 35. Achanta, R., Hemami, S., Estrada, F., et al: ‘Frequency-tuned salient region detection’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, Miami, FL, USA, June 2009, pp. 1597–1604.
    38. 38)
      • 17. Joulin, A., Bach, F., Ponce, J.: ‘Discriminative clustering for image co-segmentation’. IEEE Conf. Computer Vision and Pattern Recognition, 2010, pp. 1943–1950.
    39. 39)
      • 39. Jiang, H., Wang, J., Yuan, Z., et al: ‘Salient object detection: a discriminative regional feature integration approach’, Comput. Vis. Pattern Recognit., 2013, 123, pp. 2083–2090.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2017.0512
Loading

Related content

content/journals/10.1049/iet-cvi.2017.0512
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address