本論文提出一個基於邊緣方向預測之迭代超解析度演算法，藉由迭代反投影法的概念，來重建高解析度影像，此演算法主要可分成兩個部分：第一部分是根據原始影像的像素差值，取得內插時的權重，並且適當調整其權重預測未知的像素值，以得到放大的影像。透過這個包含邊緣資訊的內插方式，來取代傳統迭代反投影法中的雙立方內插法，藉此可以達到最佳的邊緣清晰效果；另一部分是適應性影像增強技術，透過影像高頻分析及高斯雜訊適當參雜，可以補償影像重建過程產生的高頻資訊失真，來還原失真的影像。經由客觀性的探討，使用此超解析度演算法的影像品質之峰值信號雜訊比平均值可達到28.564 dB，其結構相似度平均值可達到0.9176，並且擁有低運算複雜度的特質。

This thesis proposes an image super resolution algorithm based on iterative edge-directional predictions. The algorithm consists of two major components. The first one is an edge-dominate prediction method which applies the gradient between each pair of pixels to obtain the edge areas of the original image. The other is an adaptive image enhancement method to compensate the detailed information which is lost in the original image. A high-pass filter and an adaptive Gaussian noise are used to analyze and to enhance the texture in the high resolution image. PSNR and SSIM criteria are both adopted for the fair evaluation of the performance. Experimental results shows that the proposed algorithm achieves 28.564 dB in the average PSNR and 0.9176 in the average SSIM with the lowest computational complexity compared with existing methods.

[1] E. Maeland, “On the comparison of interpolation methods,” IEEE Trans. Medical Imaging, vol. 7, pp. 213–217, Sep. 1988.
[2] R. C. Gonzalez and R. E. Woods, Digital Image Processing. Reading, MA: Addison-Wesley, 1992.
[3] R. Y. Tsai and T. S. Huang, “Multi-frame image restoration and registration,” Advances in Comput. Vis. and Image Process., vol. 1, T. S. Huang, Ed. Greenwich, CT: in JAI Press Inc., 1984, pp. 317–339.
[4] H. S. Hou and H. Andrews, “Cubic splines for image interpolation and digital filtering,” IEEE Trans. Acoust., Speech, Signal Process., vol. 26, pp. 508–517, Dec. 1978.
[5] Y. Yun, J. Bae, and J. Kim “Adaptive multidirectional edge directed interpolation for selected edge regions,” in Proc. IEEE Ten Conf., Nov. 2011, pp. 385–388.
[6] D. Zhou, X. Shen, and W. Dong “Image zooming using directional cubic convolution interpolation,” IET Image Process., vol. 6, pp. 627–634, Aug. 2012.
[7] D. Zhang and X. Wu, “An edge-guided image interpolation algorithm via directional filtering and data fusion,” IEEE Trans. Image Process., vol. 15, pp. 2226–2238, Aug. 2006.
[8] X. Li and M. T. Orchard, “New edge-directed interpolation,” IEEE Trans. Image Process., vol. 10, pp. 1521–1527, Oct. 2001.
[9] J. Allebach and P. W. Wong, “Edge-directed interpolation,” in Proc. IEEE Int. Conf. Image Process., Sep. 1996, pp. 707–710.
[10] C. S. Wong and W. C. Siu, “Adaptive directional window selection for edge-directed interpolation,” in Proc. IEEE Int. Conf. Comput., Commun. and Netw., Aug. 2010, pp.1–6.
[11] X. Li and M. T. Orchard, “Edge-directed prediction for lossless compression of natural images,” IEEE Trans. Image Process., vol. 10, pp. 813–817, Jun. 2001.
[12] Y. Luo, S. Liu, and H. Zhu, “Edge-directed interpolation based on canny detector,” in Proc. IEEE Int. Conf. Mechatron., Autom., Aug. 2011, pp. 698–702.
[13] S. Yang, Y. Kim, and J. Jeong, “Fine edge preserving technique for display devices,” IEEE Trans. Consum. Electron., vol. 54, pp. 1761–1769, Nov. 2008.
[14] A. Temizel and T. Vlachos, “Wavelet domain image resolution enhancement using cycle-spinning,” IET Electron. Lett., vol. 41, pp. 119–121, Feb. 2005.
[15] S. C. Tai, T. M. Kuo, C. H. Lao, and T. W. Liao, “A fast algorithm for single image super resolution in both wavelet and spatial domain,” in Proc. IEEE Int. Symp. Comput., Consum., Control, Jun. 2012, pp. 702–705.
[16] M. Irani and S. Peleg, “Improving resolution by image registration,” CVGIP Graph. Models. Image Process., vol. 53, pp. 231–239, 1991.
[17] W. Dong, L. Zhang, G. Shi, and X. Wu, “Nonlocal back-projection for adaptive image enlargement,” in Proc. IEEE Int. Conf. Image Process., Nov. 2009, pp. 349–352.
[18] J. Patti, M. I. Sezan, and A. M. Tekalp, “Superresolution video reconstruction with arbitrary sampling lattices and nonzero aperture time,” IEEE Trans. Image Process., vol. 6, pp. 1064–1076, Aug. 1997.
[19] C. Fan, J. Zhu, J. Gong, and C. Kuang, “POCS super-resolution sequence image reconstruction based on improvement approach of Keren registration Method,” in Proc. IEEE Int. Conf. Int. Syst. Des. and Appl., Oct. 2006, pp. 333–337.
[20] S. P. Belekos, N. P. Galatsanos, and A. K. Katsaggelos, “Maximum a posteriori video super-resolution using a new multichannel image prior,” IEEE Trans. Image Process., vol. 19, pp. 1451–1464, Jun. 2010.
[21] H. Zhang, Y. Zhang, H. Li, and T. S. Huang, “Generative bayesian image super resolution with natural image prior,” IEEE Trans. Image Process., vol. 21, pp. 4054–4067, Sep. 2012.
[22] W. T. Freeman and E. C. Pasztor, “Learning low-level vision,” in Proc. IEEE Int. Conf. Comput.Vis., 1999, pp. 1182–1189.
[23] J. Yang, J. Wright, T. S. Huang, and Y. Ma, “Image super-resolution via sparse representation,” IEEE Trans. Image Process., vol. 19, pp. 2861–2873, Nov. 2010.
[24] S. Farsiu, M. D. Robinson, M. Elad, and P. Milanfar, “Fast and robust multiframe super resolution,” IEEE Trans. Image Process., vol. 13, pp.1327–1344, Oct. 2004.
[25] V. Patanavijit and S. Jitapunkul, “An iterative super-resolution reconstruction of image sequences using fast affine block-based registration with BTV regularization,” in Proc. IEEE Asia Pacific Conf. Circuits Syst., Dec. 2006, pp. 1717–1720.
[26] K. W. hung and W. C. Siu, “Single image super-resolution using iterative Wiener filter,” in Proc. IEEE Int. Conf. Acoust., Speed, Signal Process., Mar. 2012, pp. 1269–1272.
[27] S. Dai, M. Han, Y. Wu, and Y. Gong, “Bilateral back-projection for single image super resolution”, in Proc. IEEE Int. Conf. Multimedia and Expo, Jul. 2007, pp. 1039–1042.
[28] B. Zhao, Z. Gan, Y. Zhang, F. Liu, and H. Wang, “Novel back-projection framework for single image super-resolution,” in Proc. IEEE Int. Conf. signal Process., Oct. 2012, pp. 894–898.
[29] M. N. Bareja and C. K. Modi, “An effective iterative back projection based single image super resolution,” in Proc. IEEE Int. Conf. Commun. Syst., Network Technol., May 2012, pp. 95–99.
[30] A, J. Patti and Y. Altunbasak, “Artifact reduction for set theoretic super resolution image reconstruction with edge adaptive constraints and higher-order interpolants,” IEEE Trans. Image Process., vol. 10, pp.179–186, Jan. 2001.
[31] J. Yang, J. Wright, T. Huang, and Y. Ma, “Image super-resolution via sparse representation,” IEEE Trans. Image Process., vol 19, pp. 2861–2873, Nov. 2010.