臺灣博碩士論文加值系統

條碼技術是自動辨識和資料蒐集中十分重要的部分。而快速響應矩陣碼則是目前常被使用的二維條碼。如何有效且精確的解讀出快速響應矩陣碼的內容是一大挑戰。在本篇論文中，我們設計了一個新的解碼快速響應矩陣碼程序。這程序由四個步驟所組成，分別為影像二值化、擷取快速響應矩陣碼、視角轉換與重新取樣、錯誤修正。透過這些步驟，我們能辨識不同種類的快速響應碼影像。在實驗部分，我們與目前的條碼影像處理資料庫相互比較。實驗結果顯示我們的方法有較好的準確度。 此外，我們使用不同影像大小去測試執行時間。我們提出的方法都能即時解碼這些影像。

Barcode technology is one of the most important parts of Automatic Identification and Data Capture (AIDC). Quick Response Code (QR Code) is one of the most popular types of two-dimensional barcodes. How to decode various QR code images efficiently and accurately is a challenge. In this thesis, we design a new QR code decoding procedure. The decoding procedure consists of image binarization, QR code extraction, perspective transformation and resampling, and error correction. By these steps, we can recognize different types QR code images. The experiment results show our method has better accuracy than Google open-source 1D/2D barcode image processing library Zxing-2.1. Moreover, we evaluate the execution time for different-size images. Our method can decode these images in real time.

誌謝 i
口試委員會審定書 ii
中文摘要 iii
ABSTRACT iv
CONTENTS v
LIST OF FIGURES vii
LIST OF TABLES ix
Chapter 1 Introduction 1
1.1 QR Code Structure 3
1.1.1 Finder Patterns 3
1.1.2 Alignment Patterns 5
1.1.3 Format and Version Information 5
1.2 Thesis Framework 6
Chapter 2 Related Works 7
2.1 Image Denoising 8
2.2 Binarization of QR Code Image 11
2.3 Extracting QR Code from a Non-Uniform Background 16
Chapter 3 Background 20
3.1 Perspective Transformation 20
3.1.1 Square-to-Quadrilateral 21
3.1.2 Quadrilateral-to-Square 23
3.1.3 Quadrilateral-to-Quadrilateral 23
3.2 Reed-Solomon Error Correction 24
Chapter 4 Methodology 26
4.1 Overview 26
4.2 Binarization 27
4.3 QR Code Extraction 28
4.3.1 Searching Finder Patterns 28
4.3.2 Estimating Version 30
4.3.3 Searching Alignment Pattern 31
4.4 Perspective Transformation 32
Chapter 5 Experimental Results 35
5.1 Image Source 35
5.2 Accuracy Analysis 37
5.3 Efficiency Analysis 42
5.4 Comparison of Different Barcode Applications 44
Chapter 6 Conclusion and Future Work 47
Reference 49

[1]Y. H. Chang, C. H. Chu, and M. S. Chen, “A General Scheme for Extracting QR Code from a Non-Uniform Background in Camera Phones and Applications,” Master Thesis, Department of Electrical Engineering, National Taiwan University, 2007.
[2]C. H. Chu, D. N. Yang, and M. S. Chen, “Image Stabilization for 2D Barcode in Handheld Devices,” Proceedings of International Conference on Multimedia, Augsburg, Bavaria, pp. 697-706, 2007.
[3]A. Douglas, “Bakodo,” http://bako.do/, 2013.
[4]P. Giudicelli, “Barcode-Scanner,” https://itunes.apple.com/tw/app/barcode-scanner/id478602171?mt=8, 2013.
[5]P. S. Heckbert, “Fundamentals of Texture Mapping and Image Warping,” Master Thesis, Department of Electrical Engineering, University of California, Berkeley, CA, 1989.
[6]International Standards Organization, “ISO/IEC 18004,” http://raidenii.net/files/datasheets/misc/qr_code.pdf, 2000.
[7]Y. Kato, D. Deguchi, T. Takahashi, I. Ide, and H. Murase, “Low Resolution QR-code Recognition by Applying Super-Resolution Using the Property of QR-Codes,” Proceedings of International Conference on Document Analysis and Recognition, Beijing, China, pp. 992-996, 2011.
[8]C. Y. Lai and M. S. Chen, “Extracting QR Code from a Non-Uniform Background Image in Embedded Mobile Phones,” Master Thesis, Department of Electrical Engineering, National Taiwan University, 2007.
[9]C. C. Lin and M. S. Chen, “A General Scheme for QR-code Image Denoising on the Camera Phone,” Master Thesis, Department of Electrical Engineering, National Taiwan University, 2009.
[10]T. K. Moon, Error Correction Coding: Mathematical Methods and Algorithms, Wiley, New York, 2005.
[11]D. Munoz-Mejias, “A Low-Complexity Pre-Processing System for Restoring Low-Quality QR Code Images,” IEEE Transactions on Consumer Electronics, Vol. 57, No. 3, pp. 1320–1328, 2011.
[12]S. Owen, “Zxing ("Zebra Crossing"),” https://code.google.com/p/zxing/, 2013.
[13]Y. L. Pan and M. S. Chen, “Extracting 2D Barcodes from Images with Spatial Distortion,” Master Thesis, Department of Electrical Engineering, National Taiwan University, 2008.
[14]SimpleAct, “QuickMark,” http://www.quickmark.com.tw/, 2013.
[15]Wikipedia, “Reed–Solomon Error Correction,” http://en.wikipedia.org/wiki/Reed-Solomon_error_correction, 2013.
[16]J. J. Zhou, Y. F. Liu, and P. Li, “Research on Binarization of QR Code Image,” Proceedings of International Conference on Multimedia Technology, Ningbo, China, pp. 1-4, 2010.
[17]X. Zhou, C. He, G. Liu, and Z. Liang, “A Binarization Method of Quick Response Code Image,” Proceedings of International Conference on Signal Processing Systems, Dalian, China, Vol. 3, pp. 317–320, 2010.