臺灣博碩士論文加值系統

在本篇論文，我們提出一自動搜尋感興趣區塊並予以影像對比增強的方法AICE(Autofocus Image Contrast Enhancement)，可以增強醫學影像中可疑病灶的區域，並且把感興趣的區域在影像中點選出來並加以做影像對比增強，突顯細節。腫瘤或血塊及其他增生的組織，其主要特徵是灰階值與其他正常組織灰階值相異。因此針對此特性將感興趣區塊灰階值，單獨點選出來，並對點選出來的區域做對比增強。
首先利用區域生長和非本位平滑處理兩種不同的方式來尋找可疑病灶的區域，讓這些可疑的區塊可以很明顯的由影像中判讀出來。接著利用搜尋出來的感興趣區塊中的每一像素之間的灰階值，拓展放大這些像素值的差值，使對比做一增強，感興趣的區塊ROI(Range Of Interest)中的細節便會清晰明顯易見，幫助醫師在診斷時有明顯的參考依據。
本論文實驗結果使用熵值(Entropy)、影像灰階之標準差(Std)、ADSG、MDP、MDS五項指標來作為評估依據，藉此得知影像經過處理後的失真情形與對比增強後的效果如何，實驗證明透過此AICE方法處理過的影像於影像對比可以明顯的增強，並在失真度的表現達到零失真。
關鍵字:影像對比增強、區域生長、醫學影像、熵值、失真度

In this article, we propose an image enhancement technique named Autofocus Image Contrast Enhancement (AICE) for medical images. It can enhance the suspecting area and locate the Range of Interest (ROI) from medical images for diagnosis. The gray scale of tumors, hematomas and other granulation tissue are distinguished from other normal tissue. We can use the characteristic by marking the gray scalp of ROI, isolating it to help the medical diagnosis.
The lesion is figured by two different ways, range growing and non-standard smoothing method are used in the algorithm to capture the lesion from images. Amplifying and increasing the difference/index of gray scale of the lesion wound detail the ROI and make the diagnosis easier by physicians.
We assessed the effect of the enhanced method by Entropy, Std, ADSG, MDP, MDS. The evaluation results showed that we can increase the contrast and clear ROI of a medical image by AICE without distortion of images
Key Word: Image Contrast Enhancement、Range Growing、Medical Image、Entropy、Distortion.

誌　謝 I
摘　要 II
ABSTRACT III
目　錄 IV
圖目錄 VII
表目錄 X
第一章 緒論 1
1.1研究背景 1
1.2研究動機 3
1.3論文架構 5
第二章 影像對比增強技術分類 6
2.1空間域圖像增強 6
2.1.1空間域濾波處理時的圖像邊緣輪廓情況考量 7
2.1.2空域濾波流程 8
2.1.3平滑空間濾波處理器(Spatial filtering) 8
2.2頻率域圖像增強 11
2.2.1頻域濾波與空間域對應 12
2.3直方圖圖像增強 14
2.4 空間處理直方圖均衡化對比增強 17
第三章 自動局部影像搜尋對比增強 20
3.1局部影像增強流程 20
3.1.1程式流程 21
3.2制定ROI範圍 25
3.2.1空域法平滑處理－非本位影像平滑處理 26
3.2.2門檻值搜尋法 27
3.3影像對比增強 29
3.4專業修圖軟體比較 30
3.4.1 Magic wand 30
3.4.2 AICE與Magic wand比較 32
3.5演算法實驗 34
3.5.1實驗環境 34
3.5.2初步實驗結果 35
3.6非本位平滑處理－矩陣大小實驗 40
3.6.1以影像收斂矩陣為操縱變因分析結果 40
3.6.2以影像門檻值為操縱變因在各種不同矩陣分析結果 42
第四章 影像評估方法及評估結果 44
4.1絕對性指標 44
4.1.1熵值(Entropy) 44
4.1.2影像灰階平均值(Mean) 46
4.1.3影像灰階標準差(Std.) 46
4.2針對醫療影像的品質評估 46
4.3 AICE篩選 48
4.3.1影像內容過濾 49
4.4指標調整 50
4.4.1針對熵值(Entropy)之修正： 50
4.4.2針對平均灰階之修正 51
4.4.3影像灰階之標準差(Std)之修正 52
4.5對於資料豐富度改變的評估指標 52
4.5.1 ADSG ( AVERAGE DISTANCE IN SAME GRAY LEVEL.) 52
4.5.2 MDP(Max Distance after Processed) 53
4.5.3 MDS(Max Distance of Source) 54
4.6實驗成果及分析 54
4.6.1評估分析結果 55
4.7評估結論 58
第五章 結論 59
參考文獻： 61

[1] N. S. Heran, J. K. Song, K. Namba, W. Smith, Y.Niimi, and A. Berenstein, &;quot;The Utility of Dynact in Neuroendovascular Procedures,&;quot;AJNR Am J Neuroradiol, 27 (2006) 330-332.
[2] John Wiley, &;quot;The chemistry of contrast agents in medical magnetic resonance imaging,&;quot;John Wiley &; Sons, Ltd (2001).
[3] Jacob Beutel, and Harold L. Kundel,&;quot;Handbook of Medical Imaging: Physics and psychophysics,&;quot; The International Society for Optical Engineering (SPIE) ,1 (2000).
[4] M. Sonka, V. Hlavac, and R. Boyle, &;quot;Image Processing, Analysis, and Machine Vision&;quot;, PWS Pub. , New York, pp. 35-48, 1999.
[5]康曉東主編,&;quot;醫學影像圖像處理&;quot;,人民衛生出版社,2009年三月初版。
[6]楊武智編譯,&;quot;影像處理與辨認&;quot;,全華科技圖書股份有限公司,民國八十三年十二月初版。
[7] Hee-Chul Kim,Byong-Heon Kwon, and Myung-Ryul Choi, &;quot;An image interpolator with image improvement for LCD controller,&;quot; IEEE Transactions on Consumer Electronics, 47 [2] 263-271 (2001).
[8] Williams, Arthur B and Taylor, Fred J. “電子濾波器設計手冊” McGraw-Hill. 1995.
[9] D.Brigo,B.Hanzon, and F.LeGland, &;quot;A differential geometric approach to nonlinear filtering: the projection filter,&;quot; IEEE Transactions on Automatic Control,43[2]247-252 (1998).
[10] A.Halder, S.Shekhar, S.Kant, M.A.Mubarki, and A.Pandey, &;quot;A New Efficient Adaptive Spatial Filter for Image Enhancement,&;quot; 2010 Second International Conference on Computer Engineering and Applications (ICCEA), 1 (2010)244-246, 19-21.
[11] Chia-Chun Tsai, Huang-Chi Chou,Trong-Yen Lee, and Rong-Shue Hsiao, &;quot;A single chip image sensor embedded smooth spatial filter with A/D conversion,&;quot; 2006 IEEE International Symposium on ISCAS Proceedings Circuits and Systems, pp. 21-24 (2006).
[12] K.Hirata, and E. Kasutani, Y.Hara, &;quot;On image segmentation for object-based image retrieval,&;quot; 16th International Conference on Pattern Recognition Proceedings, 3 [3]1031-1034 (2002).
[13] J.Ahmed, J.Bosworth, and S.T.Acton, &;quot;Image segmentation techniques for object-based coding,&;quot; Image Analysis and Interpretation, 2000. Proceedings. 4th IEEE Southwest Symposium ,pp.41-45 (2000).
[14] S. C. Pei and J. J. Ding, “Fractional Fourier transform, Wigner distribution, and filter design for stationary and non-stationary random processes,” IEEE Trans. Signal Processing, vol. 58, no. 8, pp. 4079-4092, Aug. 2010
[15] Pei-Yung Hsiao, Shin-Shian Chou, and Feng-Cheng Huang, &;quot;Generic 2-D gaussian smoothing filter for noisy image processing,&;quot; TENCON 2007 - 2007 IEEE Region 10 Conference, pp.1-4 (2007).
[16] R. Boyle and R. Thomas Computer Vision,&;quot;A First Course, Blackwell Scientific Publications,&;quot; pp. 32-34 (1988).
[17] Soo-Chang Pei, and Jian-Jiun Ding, &;quot;Relations between fractional operations and time-frequency distributions, and their applications,&;quot; Signal Processing, IEEE Transactions on, 49 [8] 1638-1655 (2001).
[18] Y. Wang, S. Wang, J. J. Ding, and C. J. Fong,, “Trending and time-frequency analysis of telemetry data using Visual Signal,” Remote Sensing Satellite Technology Workshop, Hsinchu, Taiwan, Nov. 2012
[19] C.Valens, &;quot;The Fast Lifting Wavelet Transform,&;quot; The Mindless company, (1999).
[20] A.Said, and W.A. Pearlman, &;quot;A new, fast, and efficient image codec based on set partitioning in hierarchical trees, &;quot;IEEE Transactions on Circuits and Systems for Video Technology, 6 [3] 243-250 (1996).
[21] S. Yang, J. and Oh, Y. Park, &;quot;Contrast Enhancement Using Histogram with Bin Underflow and Bin Overflow,&;quot; IEEE International Conference on Image Processing, Vol.1, pp. 881-884, September, 2003.
[22] H-J Kim, J-M Lee, J-A Lee, S-G Oh and W-Y Kim, &;quot;Contrast Enhancement Using Adaptively Modified Histogram Equalization,&;quot; Lecture Notes in Computer Science, Vol.4319, pp.1150-1158, Dec. 2006.
[23] Qing Wang and Ward R.K. &;quot;Fast Image/Video Contrast Enhancement Based on Weighted Thresholded Histogram Equalization,&;quot; IEEE Transactions on Consumer Electronics, Vol.53, No.2, pp.757-764, April, 2007.
[24] Ching-Hsi Lu, Hong-Yan Hsu, and Lei Wang, &;quot;A New Contrast Enhancement Technique Implemented on FPGA for Real Time Image Processing,&;quot; The Fifth International Conference on Intelligent Information Hiding and Multimedia Signal Processing, Vol.1, pp. I - 881-4, 2003.
[25] Kuen-Jan He, Chien-Chih Chen, Ching-Hsi Lu and Lei Wang , &;quot;Implementation of a new contrast enhancement method for video images,&;quot; 2010 the 5th IEEE Conference on Industrial Electronics and Applications (ICIEA), pp.1982 – 1987, 2010
[26] T. L. Ji, M. K. Sundareshan, and H. Roehrig, “Adaptive Image Contrast Enhancement Based on Human Visual Properties”, IEEE Trans Med Imaging, 13 (1994) 573-586.
[27] 謬紹綱, &;quot;數位影像處理-活用MATLAB&;quot;, 全華科技圖書股份有限公司, 2001.
[28] 連國珍, &;quot;數位影像處理MATLAB&;quot;, 儒林科技圖書股份有限公司 , 2007.
[29] Lawler, Eugene L., and David E. Wood. &;quot;Branch-and-bound methods: A survey.&;quot; Operations research 14.4 (1966): 699-719.
[30] Michael Codish,&;quot;Analyzing logic programs using prop-ositional logic programs and a magic wand”,The Journal of Logic Programming,25 [3]249-274 (1995).
[31] G. M. Dahab, M. M. Kheriza, H. M. El-Beltagi, A. M. Fouda, and O. A. El-Din, &;quot;Digital Quantification of Fibrosis in Liver Biopsy Sections: Description of a New Method by Photoshop Software,&;quot; J GastroenterolHepatol, 19 (2004) 78-85.
[32] T Gong, R Liu, CL Tan, N Farzad, and CK Lee,&;quot;Rule-based labeling of CT head image,&;quot;Computer Science,1211 (1997) 453-456.
[33] Computer Tomography Hausfeld Unit,
http://www.fpnotebook.com/Rad/CT/HnsfldUnt.htm, (2012/12)
[34] D. C. Chang, and W. R. Wu, “Image Contrast Enhancement Based on a Histogram Transformation of Local Standard Deviation”, IEEE Trans Med Imaging, 17 (1998) 518-31.
[35] J.N. Kapur,”A new method for gray-level picture thresholding using the entropy of the histogram”,ComputerVision,Graphics,and Image Processing, 29[3] 273-285 (1985).
[36] Zhou Wang , and Bovik, A.C., &;quot;A universal image quality index,&;quot; Signal Processing Letters, IEEE ,9 [3] 81-84 (2002).
[37] Yu Wang, Qian Chen,and Baomin Zhang, &;quot;Image enhancement based on equal area dualistic sub-image histogram equalization method,&;quot; IEEE Transactions on Consumer Electronics, 45 [1] 68-75 (1999).
[38] Lei Wang, Wenta Hsieh, “A Practical Evaluation Model for the Improvement of the Quality of Image Contrast”, Journal of Computers,23(3), 28-36,2012-10.