臺灣博碩士論文加值系統

由於相機鏡頭的感光度限制，近年來對高動態範圍影像技術（HDRI）的需求非常熱絡。HDRI不僅是將影像從低動態範圍（LDR）提升至高動態範圍（HDR），也包含了從LDR影像轉變成高品質的LDR影像的技術。雖然HDRI在技術上越發成熟，例如全域及區域濾波、像素差異度計算及最佳化保留細節的技術等，然而科學家為了針對多重曝光影像融合的權重地圖尋找一個好的模型。另一方面，在人類視覺系統的研究上，科學家致力於找出影像細緻度，更精確一點地說明是，什麼樣的影像特徵對人類視覺而言才是好的。在此研究中，我們結合了HDRI和人類視覺系統雙方的觀念，將此用來決定影像融合時的權重地圖，換句話說，就是用決定視覺顯著圖的方式來決定影像融合的權重地圖。我們尋找好的色彩對比度線索以及曝光度線索，並透過線索來產生權重地圖，最後再透過金字塔融合不同曝光程度的影像成為高動態範圍影像，並達到保留對比度、色彩飽和度與細節的目的。

Due to the limitation of camera sensors, the high dynamic range imaging(HDRI) techniques are popular in recent years. Although HDRI is getting mathematically sophisticated, such as global filter or local filter of eliminating noise, pixel variation and optimization of preserving details, scientists are still looking for a good model of weight map generation for multiple-exposure image fusion which produces HDR images. In the research of human vision system, we also try to understand the fineness of image and what defines good image feature to human vision. In this study, we utilize the concept of salient region detection in weight map determination. We combine two points of view, which are the human vision perception and the image mathematical features, to find color-contrast cue and exposure cue. Through cues-formed weight map and pyramid fusion, the results appear fine contrast and saturation while preserving details in different scene of images.

中文摘要 ............................................................ i
英文摘要 ............................................................ ii
致謝 ................................................................ iii
目錄 ................................................................ iv
圖目錄 .............................................................. vi
第一章 緒論 ....................................................... 1
1.1研究背景與目的 .......................................... 1
1.2文獻回顧 ................................................ 3
1.3論文架構 ................................................ 5
第二章 相關演算法 .................................................. 6
2.1 擷取不同影像特徵產生權重地圖演算法 ........................ 6
2.2 影像融合相關演算法 ...................................... 8
2.2.1使用引導式濾波的多尺度影像融合 ........................ 9
2.2.2使用高斯金字塔的多尺度影像融合 ........................ 10
第三章 本文方法 .................................................... 11
3.1 權重地圖 ................................................ 11
3.1.1 色彩對比度線索（Color-contrast cue）...................... 12
3.1.2 曝光度線索（Exposure cue）.............................. 14
3.2 影像融合 ................................................ 15
第四章 實驗結果與分析 .............................................. 16
4.1 權重地圖 ................................................ 16
4.1.1 色彩對比度線索 ........................................ 16
4.1.2 修正因子 .............................................. 18
4.1.3 曝光度線索 ............................................ 21
4.1.4 權重地圖 .............................................. 22
4.2 結果比較 ................................................ 23
第五章 結論 ........................................................ 28
參考文獻 ............................................................ 29

1.T. Mertens, J. Kautz, and F. Van Reeth, “Exposure fusion: A simple and practical alternative to high dynamic range photography,” Comput. Graph. Forum, vol. 28, no. 1, pp. 161–171, 2009.
2.W. Zhang and W.-K. Cham, “Gradient-directed multi-exposure composition,” IEEE Trans. Image Process., vol. 21, no. 4, pp. 2318–2323, Apr. 2012
3.A T Celebi, R Duvar, O. Urhan, ‘‘Fuzzy fusion based high dynamic range imaging using adaptive histogram separation’’, IEEE Transactions on Consumer Electronics, vol. 61, no. 1, pp. 119-127, 2015.
4.J. Kim, D. Han, Y.-W. Tai, and J. Kim, ‘‘Salient region detection via highdimensional color transform,’’ in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Columbus, OH, USA, Jun. 2014, pp. 883–890.
5.N. Tong, H. Lu, L. Zhang, X. Ruan, ‘‘Saliency Detection with Multi-Scale Superpixels’’, IEEE Signal Processing Letters, vol. 21, no. 9, pp. 1035-1039, 2014.
6.M. Cheng, G. Zhang, N. J. Mitra, X. Huang, and S. Hu, “Global contrast based salient region detection,” in Proc. Comput. Vis. Pattern Recognit., 2011, pp. 409–416.
7.Y. Dong, M. T. Pourazad, P. Nasiopoulos, “Human visual system-based saliency detection for high dynamic range content”, IEEE Trans. Multimedia, vol. 18, no. 4, pp. 549-562, Apr. 2016.
8.J. Ma, Z. Zhou, B. Wang, H. Zong, “Infrared and visible image fusion based on visual saliency map and weighted least square optimization”, Infrared Phys. Technol. 2017, 82, 8–17.
9.S. Li, X. Kang, and J. Hu, “Image fusion with guided filtering,” IEEE Trans. Image Process., vol. 22, no. 7, pp. 2864–2875, Jul. 2013.
10.K. He, J. Sun, X. Tang, "Guided image filtering", IEEE Trans. Pattern Anal. Mach. Intell., vol. 35, no. 6, pp. 1397-1409, 2013.
11.Z. G. Li, Z. Wei, C. Y. Wen, J. H. Zheng, "Detail-enhanced multi-scale exposure fusion", IEEE Transactions on Image Processing, vol. 26, no. 3, pp. 1243-1252, Mar. 2017.
12.P. J. Burt and E. H. Adelson, “The Laplacian pyramid as a compact image code,” IEEE Trans. Commun., vol. 31, no. 4, pp. 532–540, Apr. 1983.
13.K. Ma, K. Zeng, and Z. Wang, “Perceptual quality assessment for multi-exposure image fusion,” IEEE Trans. Image Process., vol. 24, no. 11, pp. 3345–3356, Nov. 2015.
14.A. P. James, B. V. Dasarathy, "Medical image fusion: A survey of the state of the art", Inf. Fusion, vol. 19, pp. 4-19, Sep. 2014.
15.S. Li, X. Kang, J. Hu, "Image fusion with guided filtering", IEEE Trans. Image Process., vol. 22, no. 7, pp. 2864-2875, Jul. 2013.
16.Z. Li, J. Zheng, Z. Zhu, W. Yao, S. Wu, "Weighted guided image filtering", IEEE Trans. Image Process., vol. 24, no. 1, pp. 120-129, Jan. 2015.
17.H. Fu, X. Cao, Z. Tu, ‘‘Cluster-based co-saliency detection’’, IEEE Trans. Image Process., vol. 22, no. 10, pp. 3766-3778, Oct. 2013.