No-Reference Blur Assessment Based on Entropy and PCNN for Restoration Images

Abstract:

In practical problems, there are usually no clear counterparts as reference to evaluate restoration results. So no-reference blur assessment is very important and necessary. In this paper, we proposed an objective measure named as Edge Factor (EF) to appraise image blurring. The fundamental rationale was that blurring effect was much more perceptible in edge transition zones. The pixel number of edge transition zones would decrease when blurring occured. We defined the pixel number ratio of the edge transition zones to the whole image as EF. Experimental results show the monotonic consistency of EF and RMS. The proposed method is further compared with some common edge detection algorithms to demonstrate the effectiveness of combining point-based entropy with Pulse Coupled Neural Network.

• Periodical: Applied Mechanics and Materials (Volumes 303-306)
• Pages: 1599-1604
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.303-306.1599
• Online since: February 2013
• Authors: Jin Ping He, Jian Sheng Chen, Guang Da Su
• Keywords: Blur Assessment, Edge Detection, Point-Based Entropy, Pulse Coupled Neural Network

References

[1] Liu, D. B., Chen, Z. B., C., and Ma, H. D.: IEEE QoME ( 2009), p.75.

[2] Marziliano, P., Dufaux, F., and Winkler S.: IEEE Int. Conf. on Image Proc. (2002) , p.57.

[3] Tong, H. H., Li, M. J., and Zhang, H. J: IEEE ICME (2004), p.17.

[4] Huynh-Thu, Q. and Ghanbari, M.: Electronics letters Vol 44-13 (2008), p.800.

[5] Hamid, R. S. and Alan, C. B.: IEEE ICASSP (2004), p.709.

[6] Eckhorm, R., Reitboeck, H. J. and Arndt, M.: Neural Computation Vol. 2-3 (1990), p.293.

[7] Lindblad, T. and Kinser, J.M.: Springer-Verlag Berlin Heidelberg (2005).

[8] Jiansheng Chen, Jinping He and Guangda Su: IEEE ICIP (2010).

[9] Sang, H. K.,: ICGST GVIP, (2005).

[10] G. J. Wang, J. W. Tian and J. Liu: Infrared and Laser Engineering Vol. 29-4 (2000), p.26. (in chinese).