Please use this identifier to cite or link to this item:
標題: 提升 QR Code條碼在光線不均勻以及圖片變形下的正確辨識率
Improving Recognition Accuracy of QR Code with Un-even Illumination and Deformed Shape
作者: 黃家晟
Huang, Chia-Cheng
關鍵字: 2-D barcode
QR Code
QR Code
出版社: 資訊網路多媒體研究所
引用: [1] “International Organization for Standardization: Information Technology - Automatic Identification and Data Capture Techniques - Bar Code Symbology - QR Code. ISO/IEC 18004,” 2000. [2] “National standard of the people's Republic of China: Quick Response Code(in Chinese),” Issued by China State Bureau of Quality and Technical Supervision, GB/T ,2000. [3] Digital Image Processing, 2nd ed., R. C. Gonzalez and R. E. Woods, Prentice Hall Pub., ISBN :0130946508,2002 [4] Z. Chi, K.W. Wong, ”A two-stage Binarization approach for document images,” Proceedings of 2001 International Symposium on Intelligent Multimedia, Video and Speech Processing, May 2- 4, pp.275-278, 2001. [5] P.K Sahoo, S. Soltani, and A.K.C. Wong, “A survey of thresholding techniques,” Computer Vision, Graphics, and Image Processing, vol. 41, pp.233-260, 1988. [6] N. Otsu, “A threshold selection method from gray-level histograms,” IEEE Trans. System, Man and Cyernetics, vol. 9, no. 1, pp. 62-66, 1979. [7] Eisaku Ohbuchi, Hiroshi Hanaizumi, Lim Ah Hock, ” Barcode Readers using the Camera Device in Mobile Phones,” Proceedings of the 2004 International Conference on Cyberworlds, 2004. [8] Y. Liu and M. Liu, “Automatic recognition algorithm of Quick Response Code based on embedded system,” Proc. of the Sixth IEEE Int. conf. on Intelligent Systems Design and Application, vol. 2, pp. 783-788, Oct. 2006. [9] “Denso-Wave website of QR Code,”15:33,Oct. 2009 qrcode/index-e.html [10] “Barcode - From Wikipedia, the free encyclopedia,” 15:37,Oct. 2009 [11] “Reference library of QR Code,” 15:40,Oct. 2009 qrcode.aspx [12] “The Multi-Encoding website,” 15:41,Oct. 2009 generator/
摘要: 條碼遍及人類的生活中,從超商中的商品背後到掛號信的標籤,處處可見。條碼的使用可以讓商品更好管理,藉著專用的條碼機一掃,就可以得到內藏的資訊。由於科技的進步,使得每支手機都搭載著高畫素的相機鏡頭,藉由手機我們可以將條碼拍下來,利用程式進行解碼,如此一來,只要擁有搭載高畫素鏡頭的手機,再配合解碼程式,即可將手機變成條碼機,每個人都能夠輕易的讀取條碼裡的資料。 由於手機對手機的拍攝,常會因為手機LCD螢幕的反光,使得取到的影像無法良好的二值化,在本論文中提出了一個利用形態學方法並配合K-means分群法來消除影像的反光現象,再利用Otsu’s 法對各分組進行二值化的計算,對各組求得各自的門檻值並進行二值化。然後利用霍夫轉換(Hough Transform)求出QR Code的四條邊界線,求出四個交點座標,使用反透視轉換(Inverse Perspective Transformation)將QR Code進行矯正取樣,藉由解碼程式來驗證本論文所提出的方法確實能夠有效的解決反光現象。
The applications of barcode are existed everywhere in our surrounding life. It is widely used from the label supplies to the supermarket checkout system for products management in recent years. A barcode is an optical machine-readable representation of data made up of specific patterns. It can be read easily and quickly by using barcode reader or optical scanners. Nowadays, every mobile phone almost is equipped with high resolution camera. We can use mobile phone to instead of barcode reader by taking picture with camera and then decode barcode by using barcode recognition software system. Therefore, everyone can easily read the messages encoded in the barcode. Because of the reflection effect, a taken barcode image always suffers from the problems of uneven illumination and deformed shape and then fails to recognition. In this paper, we proposed a method to remove the effect of the reflection by combining the morphological operations and k-means clustering, and then calculate local threshold for each cluster to produce a well binarized barcode image. In order to resolve the problem of deformed shape, we firstly use hough transform to find the edge of QR Code and their intersections. Then, using inverse perspective transformation with four intersections reforms the deformed shape to a corrected shape.
其他識別: U0005-2210200916015600
Appears in Collections:資訊網路與多媒體研究所



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.