臺灣博碩士論文加值系統

本論文提出一個結合直方圖均化與影像融合之影像強化方法 (Image Enhancement Based on Histogram Equalization and Image Fusion)稱為IE/HEIF。在IE/HEIF方法中，分為三個步驟：第一、將原始影像反轉取得反轉影像；第二、將原始影像與反轉影像透過線性內插進行融合並執行限制範圍性直方圖均化；第三、利用線性內插再次融合原始影像與第二步驟所獲得的均化影像。為了增進IE/HEIF方法強化的效果，我們以區塊影像標準差為基礎，提出一個適應性調整線性融合參數的方法，這個方法稱為IE/HEIF_std。期能進一步強化影像對比與改善影像品質。
為了驗證本論文所提的方法，我們以數個影像範例進行模擬，並且與以直方圖為基礎之影像強化方法進行比較。模擬結果顯示我們所提出的IE/HEIF與IE/HEIF_std方法均能有效改善影像品質。一般而言，IE/HEIF_std方法如所期待的具有較佳的影像強化效果。此外，本論文所提方法與以直方圖均化為基礎之方法比較，有較佳的視覺品質。在模擬的範例中，我們所提出的IE/HEIF與IE/HEIF_std方法能夠避免影像過度增強，並且能增強對比與細節，達到強化影像之目的。

This paper presents an image enhancement approach based on histogram equalization (HE) and image fusion, which is abbreviated as IE/HEIF. The proposed IE/HEIF consists of three stages: First, obtain the complement of original image. Second, fuse the original image and its complement by linear interpolation and apply limited range histogram equalization to the fused image. Third, apply linear interpolation once more to fuse the original image and that obtained in the second stage. To improve the performance of IE/HEIF further, an adaptive scheme based on standard deviation of image blocks is employed for parameter adjustment in the linear interpolation. The approach is called IE/HEIF_std. By this doing, it is expected to have better image contrast and visual quality.
To justify the proposed approaches, several examples are provided in the simulation where comparisons with other HE-based approaches are made as well. The results indicate that both IE/HEIF and IE/HEIF_std are able to enhance image contrast and visual quality and better results are generally for IE/HEIF_std as expected. Moreover, the proposed IE/HEIF and IE/HEIF_std have better enhanced images than those HE-based approaches which suffer from over-enhancement and un-natural looking in the resulted images in general.

索引目錄
中文摘要 I
Abstract II
致謝 III
索引目錄 IIV
圖目錄 VI
表目錄 VII
第一章簡介 1
第二章文獻回顧 4
2.1傳統直方圖均化 4
2.2相關直方圖均化文獻回顧 7
(a) 亮度保持二分直方圖均化方法[10] 7
(b) 權重門檻值直方圖均化方法[6] 7
(c) 範圍限制二分直方圖均化方法[8] 8
(d) 遞迴分割權重直方圖均化方法[1] 11
(e) 亮度保持權重分群方法[4] 11
(f) 亮度保持動態直方圖均化方法[2] 12
(g) 自動免參數分段線性轉換方法[3] 12
(h) 動態直方圖均化[5] 12
2.3影像融合文獻回顧 13
(a) 結合影像融合和移動穩定[11] 13
(b) 融合多張影像和色調再生[12] 13
(c) 依照質量計算進行影像融合方法[14] 14
(d) 解決缺陷的影像強化方法[15] 14
(e) 基於灰色多項式內插法之影像融合技術[16] 14
第三章IE/HEIF影像強化方法 15
3.1一次內插融合 16
3.2 限制範圍直方圖均化 20
3.3 二次內插融合 21
3.4針對彩色影像IE/HEIF之執行步驟 22
3.5以標準差為基礎之適應性IE/HEIF方法 24
第四章實驗結果與討論 27
4.1 灰階影像 27
4.2 彩色影像 36
4.3 客觀數據比較 46
第五章結論與未來研究方向 49
參考文獻 51

圖目錄
圖2.1 Plane影像 5
圖2.2 經限制範圍均化後之Plane影像 6
圖2.3 RSWHE 流程圖 11
圖3.1 IE/HEIF方法流程圖 16
圖3.2 Jet影像 18
圖3.3 Jet均化影像 21
圖3.4 Jet二次融合影像 22
圖3.5 針對彩色影像IE/HEIF之流程圖 24
圖3.6 計算 之流程圖 26
圖4.1 Truck影像 28
圖4.2 Plane影像 31
圖4.3 Baboon影像 33
圖4.4 Gate影像 37
圖4.5 Light影像 40
圖4.6 Flower影像 44



表目錄
表4-1 不同方法之 AAMBE比較結果(灰階影像) 47
表4-2 不同方法之 AAMBE比較結果(彩色影像) 47
表4-3 不同方法之執行時間比較結果 48

[1]Mary Kim and Min Gyo Chung, “Recursively Separated and Weighted Histogram Equalization for Brightness Preservation and Contrast Enhancement,” IEEE Transactions on Consumer Electronics,” Vol. 54, No. 3, pp. 1389–1397, August 2008.
[2]Haidi Ibrahim, and Nicholas Sia Pik Kong, “Brightness Preserving Dynamic Histogram Equalization for Image Contrast Enhancement,” IEEE Transactions on Consumer Electronics, Vol. 53, No. 4, pp. 1752–1758, November 2007.
[3]Chun-Ming Tsai and Zong-Mu Yeh, “Contrast Enhancement by Automatic and Parameter-Free Piecewise Linear Transformation for Color Images,” IEEE Transactions on Consumer Electronics, Vol. 54, No. 2, pp. 213–219, May 2008.
[4]Nyamlkhagva Sengee and Heung Kook Choi, “Brightness Preserving Weight Clustering Histogram Equalization,” IEEE Transactions on Consumer Electronics, Vol. 54, No. 3, pp. 1329–1337, August 2008.
[5]How-Lung Eng and Kai-Kuang Ma, ”A Dynamic Histogram Equalization for Image Contrast Enhancement,” IEEE Transactions on Consumer Electronics, Vol. 53, No. 2, pp. 593–600, May 2007.
[6]Qing Wang, Rabab Ward, “Fast Image/Video Contrast Enhancement Based on Weighted Thresholded Histogram Equalization,” IEEE Transactions on Consumer Electronics, Vol.53, No. 2, pp. 757–764, May 2007.
[7]Haidi Ibrahim and Nicholas Sia Pik Kong, “Image Sharpening Using Sub-Regions Histogram Equalization,” IEEE Transactions on Consumer Electronics, Vol.55, No. 2, pp. 891–895, May 2009.
[8]Chen Hee Ooi, Pik Kong, Nicholas Sia, Ibrahim, Haidi, “Bi-Histogram Equalization with a Plateau Limit for Digital Image Enhancement,” IEEE Transactions on Consumer Electronics, Vol. 55, No. 4, pp. 2072–2080, November 2009.
[9]Nicholas Sia Pik Kong and Haidi Ibrahim, “Color Image Enhancement Using Brightness Preserving Dynamic Histogram Equalization” IEEE Transactions on Consumer Electronics, Vol.54, No.4, pp. 1962–1968, November 2008.
[10]Yeong-Taeg Kim, ”Contrast Enhancement Using Brightness Preserving Bi-Histogram Equalization” IEEE Transactions on Consumer Electronics, Vol.43, No.1, pp. 1– 8, November 1997.
[11]Wen-Chung Kao, Chien-Chih Hsu, Lien-Yang Chen, Chih-Chung Kao, Shou-Hung Chen, “Integrating Image Fusion and Motion Stabilization for Capturing” IEEE Transactions on Consumer Electronics, Vol.52, No.3, pp. 735–741, November 2006.
[12]Wen-Chung Kao, “High Dynamic Range Imaging by Fusing Multiple Raw Images and Tone Reproduction” IEEE Transactions on Consumer Electronics, Vol.54, No.1, pp. 10–15, November 2008.
[13]Wen-Chung Kao, Chien-Chih Hsu, Chih-Chung Kao, and Shou-Hung Chen, “Adaptive Exposure Control and Real-Time Image Fusion for Surveillance Systems” IEEE International Symposium on Circuit and Systems, pp. 21–24, May 2006.
[14]Tom Mertens, Jan Kautz and Frank Van Reeth, ”Exposure Fusion: A Simple and Practical Alternative to High Dynamic Range Photography” Computer Graphics Forum, Vol. 28, No.1, pp. 161–171, 2009.
[15]Qiang Chen, Xin Xu, Quansen Sun, Deshen Xia, ”A Solution to the Deficiencies of Image Enhancement” Signal Processing, Vol. 90 , No. 1, pp. 44–56, January 2010.
[16]Cheng-Hsiung Hsieh, Pei-Wen Chen, Chia-Wei Lan, and Kuan-Chieh Hsiung, “Image Fusion Based on Grey Polynomial Interpolation” Eighth International Conference on Intelligent Systems Design and Applications, Vol. 1, pp. 19–22, November 2008.