Abstract

This Letter proposes a rapid method for automatic salient object detection inspired by the idea that an image consists of redundant information and novelty fluctuations. We believe object detection can be achieved by removing the nonsalient parts and focusing on the salient object. Considering the relation between the composition of the image and the aim of object detection, we constructed what we believe is a more reliable saliency map to evaluate the image composition. The local energy feature is combined with a simple biologically inspired model (color, intensity, orientation) to strengthen the integrity of the object in the saliency map. We estimated the entropy of the object via the maximum entropy method. Then, we removed pixels of minimal intensity from the original image and compute the entropy of the resulting images, correlating this entropy with the object entropy. Our experimental results show that the algorithm outperforms the state-of-the-art methods and is more suitable in real-time applications.

© 2013 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. Y. N. Xu, Y. Zhao, C. F. Jin, Z. F. Qu, and L. P. Liu, Opt. Lett. 35, 475 (2010).
    [CrossRef]
  2. C. X. Gao, N. Sang, and R. Huang, Opt. Lett. 37, 76 (2012).
    [CrossRef]
  3. J. R. Xue, C. Li, and N. N. Zheng, IEEE Trans. Image Process. 20, 1177 (2011).
    [CrossRef]
  4. A. Toet, IEEE Trans. Pattern Anal. Mach. Intell. 33, 2131 (2011).
    [CrossRef]
  5. L. Itti, C. Koch, and E. Niebur, IEEE Trans. Pattern Anal. Mach. Intell. 20, 1254 (1998).
    [CrossRef]
  6. G. Viswanath, Y. Q. Hu, and D. Rajan, IEEE Trans. Image Process. 19, 3232 (2010).
    [CrossRef]
  7. X. Hou and L. Zhang, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2007), pp. 1–8.
  8. L. Henriksson, A. Hyvarinen, and S. Vanni, J. Neurosci. 29, 14342 (2009).
    [CrossRef]
  9. J. D. Victor and M. M. Conte, J. Opt. Soc. Am. A 29, 1313 (2012).
    [CrossRef]
  10. T. Liu, J. Sun, N. N. Zheng, X. Tang, and H. Y. Shum, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2007), pp. 1–8.
  11. F. Ken, M. Kouji, K. Akisato, T. Shigeru, and Y. Junji, Proceedings of the IEEE International Conference on Multimedia and Expo (IEEE, 2009), p. 638.
  12. S. Goferman, L. Zelnik-Manor, and A. Tal, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2010), p. 2376.
  13. R. Achanta, S. Hemami, F. Estrada, and S. Süsstrunk, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2009), p. 1597.

2012

2011

J. R. Xue, C. Li, and N. N. Zheng, IEEE Trans. Image Process. 20, 1177 (2011).
[CrossRef]

A. Toet, IEEE Trans. Pattern Anal. Mach. Intell. 33, 2131 (2011).
[CrossRef]

2010

G. Viswanath, Y. Q. Hu, and D. Rajan, IEEE Trans. Image Process. 19, 3232 (2010).
[CrossRef]

Y. N. Xu, Y. Zhao, C. F. Jin, Z. F. Qu, and L. P. Liu, Opt. Lett. 35, 475 (2010).
[CrossRef]

2009

L. Henriksson, A. Hyvarinen, and S. Vanni, J. Neurosci. 29, 14342 (2009).
[CrossRef]

1998

L. Itti, C. Koch, and E. Niebur, IEEE Trans. Pattern Anal. Mach. Intell. 20, 1254 (1998).
[CrossRef]

Achanta, R.

R. Achanta, S. Hemami, F. Estrada, and S. Süsstrunk, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2009), p. 1597.

Akisato, K.

F. Ken, M. Kouji, K. Akisato, T. Shigeru, and Y. Junji, Proceedings of the IEEE International Conference on Multimedia and Expo (IEEE, 2009), p. 638.

Conte, M. M.

Estrada, F.

R. Achanta, S. Hemami, F. Estrada, and S. Süsstrunk, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2009), p. 1597.

Gao, C. X.

Goferman, S.

S. Goferman, L. Zelnik-Manor, and A. Tal, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2010), p. 2376.

Hemami, S.

R. Achanta, S. Hemami, F. Estrada, and S. Süsstrunk, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2009), p. 1597.

Henriksson, L.

L. Henriksson, A. Hyvarinen, and S. Vanni, J. Neurosci. 29, 14342 (2009).
[CrossRef]

Hou, X.

X. Hou and L. Zhang, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2007), pp. 1–8.

Hu, Y. Q.

G. Viswanath, Y. Q. Hu, and D. Rajan, IEEE Trans. Image Process. 19, 3232 (2010).
[CrossRef]

Huang, R.

Hyvarinen, A.

L. Henriksson, A. Hyvarinen, and S. Vanni, J. Neurosci. 29, 14342 (2009).
[CrossRef]

Itti, L.

L. Itti, C. Koch, and E. Niebur, IEEE Trans. Pattern Anal. Mach. Intell. 20, 1254 (1998).
[CrossRef]

Jin, C. F.

Junji, Y.

F. Ken, M. Kouji, K. Akisato, T. Shigeru, and Y. Junji, Proceedings of the IEEE International Conference on Multimedia and Expo (IEEE, 2009), p. 638.

Ken, F.

F. Ken, M. Kouji, K. Akisato, T. Shigeru, and Y. Junji, Proceedings of the IEEE International Conference on Multimedia and Expo (IEEE, 2009), p. 638.

Koch, C.

L. Itti, C. Koch, and E. Niebur, IEEE Trans. Pattern Anal. Mach. Intell. 20, 1254 (1998).
[CrossRef]

Kouji, M.

F. Ken, M. Kouji, K. Akisato, T. Shigeru, and Y. Junji, Proceedings of the IEEE International Conference on Multimedia and Expo (IEEE, 2009), p. 638.

Li, C.

J. R. Xue, C. Li, and N. N. Zheng, IEEE Trans. Image Process. 20, 1177 (2011).
[CrossRef]

Liu, L. P.

Liu, T.

T. Liu, J. Sun, N. N. Zheng, X. Tang, and H. Y. Shum, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2007), pp. 1–8.

Niebur, E.

L. Itti, C. Koch, and E. Niebur, IEEE Trans. Pattern Anal. Mach. Intell. 20, 1254 (1998).
[CrossRef]

Qu, Z. F.

Rajan, D.

G. Viswanath, Y. Q. Hu, and D. Rajan, IEEE Trans. Image Process. 19, 3232 (2010).
[CrossRef]

Sang, N.

Shigeru, T.

F. Ken, M. Kouji, K. Akisato, T. Shigeru, and Y. Junji, Proceedings of the IEEE International Conference on Multimedia and Expo (IEEE, 2009), p. 638.

Shum, H. Y.

T. Liu, J. Sun, N. N. Zheng, X. Tang, and H. Y. Shum, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2007), pp. 1–8.

Sun, J.

T. Liu, J. Sun, N. N. Zheng, X. Tang, and H. Y. Shum, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2007), pp. 1–8.

Süsstrunk, S.

R. Achanta, S. Hemami, F. Estrada, and S. Süsstrunk, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2009), p. 1597.

Tal, A.

S. Goferman, L. Zelnik-Manor, and A. Tal, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2010), p. 2376.

Tang, X.

T. Liu, J. Sun, N. N. Zheng, X. Tang, and H. Y. Shum, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2007), pp. 1–8.

Toet, A.

A. Toet, IEEE Trans. Pattern Anal. Mach. Intell. 33, 2131 (2011).
[CrossRef]

Vanni, S.

L. Henriksson, A. Hyvarinen, and S. Vanni, J. Neurosci. 29, 14342 (2009).
[CrossRef]

Victor, J. D.

Viswanath, G.

G. Viswanath, Y. Q. Hu, and D. Rajan, IEEE Trans. Image Process. 19, 3232 (2010).
[CrossRef]

Xu, Y. N.

Xue, J. R.

J. R. Xue, C. Li, and N. N. Zheng, IEEE Trans. Image Process. 20, 1177 (2011).
[CrossRef]

Zelnik-Manor, L.

S. Goferman, L. Zelnik-Manor, and A. Tal, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2010), p. 2376.

Zhang, L.

X. Hou and L. Zhang, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2007), pp. 1–8.

Zhao, Y.

Zheng, N. N.

J. R. Xue, C. Li, and N. N. Zheng, IEEE Trans. Image Process. 20, 1177 (2011).
[CrossRef]

T. Liu, J. Sun, N. N. Zheng, X. Tang, and H. Y. Shum, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2007), pp. 1–8.

IEEE Trans. Image Process.

J. R. Xue, C. Li, and N. N. Zheng, IEEE Trans. Image Process. 20, 1177 (2011).
[CrossRef]

G. Viswanath, Y. Q. Hu, and D. Rajan, IEEE Trans. Image Process. 19, 3232 (2010).
[CrossRef]

IEEE Trans. Pattern Anal. Mach. Intell.

A. Toet, IEEE Trans. Pattern Anal. Mach. Intell. 33, 2131 (2011).
[CrossRef]

L. Itti, C. Koch, and E. Niebur, IEEE Trans. Pattern Anal. Mach. Intell. 20, 1254 (1998).
[CrossRef]

J. Neurosci.

L. Henriksson, A. Hyvarinen, and S. Vanni, J. Neurosci. 29, 14342 (2009).
[CrossRef]

J. Opt. Soc. Am. A

Opt. Lett.

Other

T. Liu, J. Sun, N. N. Zheng, X. Tang, and H. Y. Shum, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2007), pp. 1–8.

F. Ken, M. Kouji, K. Akisato, T. Shigeru, and Y. Junji, Proceedings of the IEEE International Conference on Multimedia and Expo (IEEE, 2009), p. 638.

S. Goferman, L. Zelnik-Manor, and A. Tal, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2010), p. 2376.

R. Achanta, S. Hemami, F. Estrada, and S. Süsstrunk, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2009), p. 1597.

X. Hou and L. Zhang, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2007), pp. 1–8.

Cited By

OSA participates in CrossRef's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (4)

Fig. 1.
Fig. 1.

Framework of the proposed salient object detection method.

Fig. 2.
Fig. 2.

Comparison of Itti’s saliency map, local energy feature map, and our method.

Fig. 3.
Fig. 3.

Saliency maps: (a) original image, (b) saliency tool box (STB) [5], (c) spectral residual (SR) [7], (d) frequency-tuned (FT) [13], (e) context-aware visual saliency (CA) [12], and (f) our method.

Fig. 4.
Fig. 4.

Comparison of salient object detection using Itti’s method, Akamine’s method, and our method with different values of k.

Tables (2)

Tables Icon

Table 1. AUC of Different Models

Tables Icon

Table 2. Comparison of Detection Performance of Itti’s Method, Akamine’s Method, and Our Method with Different Values of k

Equations (8)

Equations on this page are rendered with MathJax. Learn more.

E(x)=[I2(x)+H2(x)]1/2,
HO(t)=lnitPiPO(t)lnPiPO(t)i
HB(t)=lni=t+1255PiPB(t)lnPiPB(t)i,
HO(t*)=lni=0tPiPO(t*)lnPiPO(t*).
fj(M)=(fgj)(x),
Hj(M)=ln0255PilnPi,
Pest=4k(M1)1/2/M,
Fmeasure=(1+α)*Precision*Recallα±*Precision+Recall,

Metrics