消除濃霧影響的影像還原過程稱為「去霧」。光線傳播率圖隱含了影像當中的深度資訊，因此求得光線傳播率圖的近似值是去霧方法中最重要的步驟。求得光線傳播率圖之最佳解的主要問題為結構性區域的不連續性。在本論文中，我們提出結構性區域限制項，處理結構性區域的光線傳播率圖不準確之問題。藉由引入結構性區域限制項，我們所推導的目標函數保證有全域最佳解，並且具備光線傳播率圖在結構性區域的連續性。我們的實驗結果顯示對於結構性區域之光線傳播率圖以及去霧結果的顯著改善。

Dehazing is an image restoration process to eliminate the hazy effect. Approximation of the transmission, which encodes the scene depth information, is the most significant step to tackle the dehazing problem. In this thesis, we propose a textured-region constraint to deal with inaccurate estimation on transmission within a textured region. The textured-region constraint assumes that transmission for pixels in a textured region should be similar. By including the textured-region constraint, the objective function guarantees to have a global optimal solution with constant textured-region transmission. Our experimental results show significant improvement in textured-region transmission and dehazed results.

8. References
[1] Y.S. Lai, Y.L. Chen and C.T. Hsu, “Single Image Dehazing with Optimal Transmission Map,” Proc. IEEE Conf. International Conference on Pattern Recognition, pp. 388–391, 2012.
[2] S.G. Narasimhan and S.K. Nayar, “Interactive Deweathering of an Image Using Physical Models,” Proc. IEEE Workshop on Color and Photometric Methods in Computer Vision, pp. 1387–1394, Oct. 2003.
[3] S.G. Narasimhan and S.K. Nayar, “Contrast Restoration of Weather Degraded Images,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 25, no. 6 pp. 713–724, June 2003.
[4] S. Narasimhan, S. Nayar, “Chromatic Framework for Vision in Bad Weather, ” IEEE Conference on Computer Vision and Pattern Recognition, 2000.
[5] R. Tan, “Visibility in Bad Weather from a Single Image,” IEEE Conf. Computer Vision and Pattern Recognition, pp.1–8, June 2008.
[6] K. He, J. Sun and X. Tang, “Single Image Haze Removal Using Dark Channel Prior,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol.33, No.12, pp.2341–2353, Aug. 2010.
[7] R. Fattal, “Single Image Dehazing,” ACM Trans. on Graphics, 2008.
[8] P. Lee and Y. Wu, “Nonlocal matting,” Proc. IEEE Conf. Computer Vision, pp.2193–2200, 2011.
[9] A. Buades,, B. Coll, and J.M. Morel, “Nonlocal image and movie denoising,” International journal of computer vision, pp. 123–139, 2008.
[10] A. Levin, D. Lischinski and Y. Weiss, “A Closed Form Solution to Natural Image Matting,” Proc. IEEE Conf. on Computer Vision and Pattern Recognition, vol. 1, pp. 61–68, June 2006.
[11] S. Parthasarathy and P. Sankaran, “A Retinex based Haze Removal Method,” IEEE Conf. on Industrial and Information Systems , pp. 1–6, Aug. 2012.