Detecting Local Illumination Using Skewness of Oriented Gradients from a Single Image

Abstract:

In this paper we present a simple and effective method for detecting illumination of a region from a single image. Our method is primarily based on skewness, which is a measure of asymmetry of a data set in statistics. We happen to find out that the skewness value of oriented gradients of an image can measure the directional characteristic of illumination. By choosing appropriate statistical area, we can analyze the subtle changes on the surface of an object. Theoretical analysis and experimental results show that our algorithm is accurate and effective. In the end, we give its application in image authenticity verification problem which is to distinguish real and “flat” objects in a photograph, and it shows excellent results.

• Periodical: Applied Mechanics and Materials (Volumes 58-60)
• Pages: 2381-2386
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.58-60.2381
• Online since: June 2011
• Authors: Fan Zhang, Bing Yin Zhou, Li Zhong Peng
• Keywords: Illumination Detection, Oriented Gradient, Skewness

References

[1] Y. Adini, Y. Moses and S. Ullman: Pattern Analysis and Machine Intelligence, Vol. 19 (1997), p.721.

[2] Y. Matsushita, K. Nishino, K. Ikeuchi and M. Sakauchi: Computer Vision and Pattern Recognition, Vol. 1 (2003), p.3.

[3] M. D. Levine and J. Bhattacharyya: Pattern Recogn. Lett., Vol. 26 (2005), p.251.

[4] S. Shan, W. Gao, B. Cao and D. Zhao: IEEE International Workshop on Analysis and Modeling of Faces and Gestures, (2003), p.157.

[5] C. Fredembach and G. Finlayson: Proceedings of the 18th International Conference on Pattern Recognition, (2006), p.832.

[6] J. Zhu, K. G. G. Samuel, S. Z. Masood and M. F. Tappen: Computer Vision and Pattern Recognition, (2010), p.223.

[7] M. F. Tappen, W. T. Freeman and E. H. Adelson: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 27 (2005), p.1459.

DOI: 10.1109/tpami.2005.185

[8] G. Finlayson, S. Hordley, C. Lu and M. Drew: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 28 (2006), p.59.

DOI: 10.1109/tpami.2006.18

[9] G. Finlayson, S. Hordley and M. Drew: Computer Vision - ECCV 2002, ser. Lecture Notes in Computer Science, Vol. 2353(2006), p.129.

[10] G. Finlayson, C. Fredembach and M. S. Drew: Proc. IEEE 11th Int. Conf. Computer Vision ICCV 2007, p.1.

[11] Y. Weiss: IEEE International Conference on Computer Vision, Vol. 2 (2001), p.68.

[12] R. O. Dror, T. K. Leung, E. H. Adelson and A. S. Willsky: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 2 (2001), p.164.

DOI: 10.1109/cvpr.2001.990948

[13] L. Sharan, Y. Li and E. H. Adelson: Journal of Vision, Vol. 6 (2006), p.101.

[14] I. Motoyoshi, S. Nishida, L. Sharan and E. H. Adelson: Nature, Vol. 447 (2007), p.206.

[15] L. Sharan, Y. Li, I. Motoyoshi, S. Nishida and E. H. Adelson: J. Opt. Soc. Am. A, Vol. 25 (2008), p.846.

[16] F. C. Crow: SIGGRAPH Comput. Graph., Vol. 18 (1984), p.207.

[17] B. T. Phong: Commun. ACM, Vol. 18 (1975), p.311.

[18] M. Oren and S. K. Nayar: Proceedings of the 21st annual conference on Computer graphics and interactive techniques, (1994), p.239.

[19] Information on http: /www. sciencemag. org/content/318/5852/893. 1. short.

[20] H. Yu, T. -T. Ng and Q. Sun: 15th IEEE International Conference on Image Processing, (2008), p.3140.

[21] H. Cao and A. C. Kot: IEEE International Conference on Acoustics, Speech, and Signal Processing, (2010), p.1790.