本研究依照國際標準ISO/IEC 24778，以工業電腦視覺系統開發平台，設計與實現一種可自動修正非線性畸變(Non-Linear Distortion)之工業級Aztec二維條碼解碼系統。此法將條碼的非線性畸變，分別在垂直或水平方向上，以二次抛物線近似，取條碼影像上下緣或左右緣為基準進行四次抛物線擬合，並基於由上至下或由左至右的抛物線曲率為線性變化的合理假設，得出所有像素於失真前後的近似非線性關係，並據此進行反轉換。此法僅需四條抛物線的擬合及二次多項式中的簡單乘除運算，免除傳統上需系統校正及求解多元高次方程式的複雜運算。系統測詴結果顯示，此法可即時修正實際應用時常發生的非線性畸變問題，且免除系統校正的困擾，增加此二維條碼解碼器的強固性及效率。

In this study, we follow international standard ISO/IEC 24778 to design and implement, under an industrial vision development platform, a high-performance Aztec 2D barcode decoder with a new calibrationless correction method for non-linear distortion.
The proposed correction method horizontally and vertically fits the edges of a non-linear distorted barcode images to two sets of trajectory equations, respectively. References of the trajectory behaviors are those four distorted barcode boundary lines, which were straight before distortion. These best-fit trajectory equations can thereafter be used to reverse the distortion.
To simplify the derivation of the sets of the trajectory equations, a reasonable and practical assumption is given: curvature of horizontal or vertical sets of trajectories are changing linearly from top to bottom and from left to right boundaries of the given barcode image. By this assumption, these trajectory equations can be obtained by simple mathematics.
In this method, conventional computation-intensive equation solving, e.g. multivariate nonlinear optimizations, is avoided. Thus, an industrial class of barcode reader system with computation-efficient, calibrationless, and real-time non-linear correction can be achieved.

第一章 緒論 ............................................. 1
1-1 前言 .............................................. 1
1-2 文獻回顧 .......................................... 4
1-3 研究動機與目的 ..................................... 9
1-4 論文結構 ......................................... 14
第二章 方法 ............................................ 15
2-1 方法流程 ......................................... 15
2-2 膨脹運算和侵蝕運算 ................................ 16
2-3 影像二值化 ....................................... 18
2-4 區塊分析 ......................................... 23
2-4-1 四連結法(4-Connectivity) ...................... 23
2-4-2 八連結法(8-Connectivity) ...................... 25
2-4-3 區塊分析用途 .................................. 26
2-5 非線性畸變修正法 .................................. 27
2-5-1 抛物線擬合 .................................... 28
2-5-2 抛物線曲率線性變化 ............................ 28
2-5-3 反轉換 ........................................ 30
第三章 視窗化界面系統實作 .............................. 31
3-1 實驗環境 ......................................... 31
3-2 系統架構 ......................................... 32
3-3 系統建置 ......................................... 34
3-3-1 定位 ......................................... 34
3-3-2 方位校正和外觀尺寸 ............................ 36
3-3-3 取得條碼影像四周邊緣點 ........................ 37
3-3-4 非線性畸變修正法 .............................. 39
3-3-5 Aztec解碼 .................................... 40
第四章 結論 ............................................ 45
4-1 本研究之貢獻...................................... 45
4-2 本研究優點 ....................................... 46
4-3 本研究缺點 ....................................... 47
4-4 未來研究方向...................................... 48
參考文獻 ............................................... 50

[1]. Smith, W.E., Vakil, N., and Maislin, S.A., “Correction of Distortion in Endoscope Images,” IEEE Transactions on Medical Imaging, Vol. 11, No. 1, pp. 117–122, 1992.
[2]. Haneishi, H., Yagihashi, Y., and Miyake, Y., “A New Method for Distortion Correction of Electronic Endoscope Images,” IEEE Transactions on Medical Imaging, Vol. 14, No. 3, pp. 548–555, 1995.
[3]. Asari, K.V., Kumar, S., and Radhakrishnan, D., “A New Approach for Nonlinear Distortion Correction in Endoscopic Images Based on Least Squares Estimation,” IEEE Transactions on Medical Imaging, Vol. 18, No. 4, pp. 345-354, 1999.
[4]. Helferty, J.P., Zhang C., McLennan, G., and Higgins, W.E., “Videoendoscopic Distortion Correction and Its Application to Virtual Guidance of Endoscopy”, IEEE Transactions on Medical Imaging, Vol. 20, NO. 7, pp. 605-617, 2001.
[5]. Sun, H., Zhang, Y., and Luo, F., “A Novel Approach for Nonlinear Distortion Correction of Industrial Endoscope Images,” World Conference on Nondestructive Testing, pp. 25-28, 2008.
[6]. Otsu, N., “A Threshold Selection Method from Gray-Level Histograms”, IEEE Transactions on Systems, Man and Cybernetics, Vol. 9, No. 1, pp. 62-66, 1979.
[7]. Kapur, J.N., Sahoo, P.K., and Wang, A.K.C., “A New Method for Gray-Level Picture Thresholding Using The Entropy of The Histogram”, Computer Vision, Graphics, and Image Processing, Vol. 29, No. 3, pp. 273-285, 1985.
[8]. Weng, J., Cohen, P., and Herniou, M., “Calibration of Stereo Cameras Using A Nonlinear Distortion Model”, International Conference on Pattern Recognition, Vol. 1, pp. 246-253, 1990.
[9]. Tsai, R.Y., “An Efficient and Accurate Camera Calibration Technique for 3D Machine Vision”, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 1, pp. 364-374, 1986.
[10]. Faugeras, O.D., and Toscani, G., “Camera Calibration for 3D Computer Vision”, International Workshop on Industrial Applications of Machine Vision and Machine, pp. 240-247, 1987.
[11]. ISO/IEC24778, “Information Technology — Automatic Identification and Data Capture Techniques — Aztec Code Bar Code Symbology Specification,” International Standard, 2007.
[12]. Atkinson, K.B., “Developments in Close Range Photogrammetry“, Elsevier Science & Technology, 1980.
[13]. General Reed-Solomon Encoder/Decoder v1.04, Retrieved May 31, 2011, from http://www.masys.url.tw/.
[14]. ZebraTech Posts and Points-of-View from Zebra Technologies, Retrieved May 31, 2011, from http://blogs.zebra.com/blog/?Tag=healthcare.
[15]. 劉 俊 延, “內視鏡影像序列之形變校正與三維重構”, 國立成功大學資訊工程學系碩士論文，2003.
[16]. 簡大淵, “內視鏡影像序列之自動校正、重構與病灶量測”, 國立成功大學資訊工程學系碩士論文，2002.
[17]. 馬頌德，張正友，“計算機視覺-計算理論與算法基礎,科學出版社，1998.
[18]. 相機校正, 2011年05月31號, 取自http://image.cse.nsysu.edu.tw/research/camera_calib/calibration.htm.