臺灣博碩士論文加值系統

車輛牌照定位(Vehicle License Plate Localization)是以汽車牌照的資訊作為目標的計算機視覺系統，以應用在智慧型交通運輸系統中，如交通流量的檢測，交通控制與誘導，機場、港口、小型停車管理，贓車查緝，不停車收費等領域。而在車輛牌照識別系統中車牌定位至關重要，在車輛圖像中往往存在許多類似車牌的區域，準確地定位出車牌所在的區域，才能正確的攫取出所需的資訊。本文中提出以傅立葉轉換(Fourier Transform)作為基礎的方法，將影像轉換至頻域(Frequency Domain)處理後能正確的找出車輛牌照的位置，以利後續車牌辨識，進而到整個交通自動化其正確率的提升。經實驗分析證實本方法具有高成功偵測率。

Vehicle license plate localization is an important research topic for the application of computer vision on Intelligent Transport System. It can be applied widely in many situations. For example, it can detect traffic flow, help the control of transportation, help the management of parking lot, help the inspection of missing car, and enforce illegal passing in electronic toll system. The most important of the vehicle license plate recognition system is location. There are many possible areas of license plate within an image. Locating the area of vehicle license plate is the way to capture the information you need correctly. This study presents an approach that is based on the Fourier transform by transferring the spatial images into frequency domain images, and finds out the location of license correctly. Experimental results validate the feasibility of the proposed method.

中文摘要 i
英文摘要 ii
誌謝 iii
目 錄 iv
表目錄 vi
圖目錄 vii
第一章 導論 1
1.1 研究動機 1
1.2 研究目的 2
1.3 論文章節介紹 2
第二章 相關研究 4
2.1文獻探討 6
2.2傅立葉轉換(Fourier Transform) 9
2.2.1傅立葉定理的重要特性 10
2.2.2傅立葉轉換之公式 11
2.2.3傅立葉轉換架構 13
2.3頻域的低通濾波與高通濾波 13
2.3.3理想高通濾波器 15
2.3.4 Butterworth 高通濾波器 16
第三章 影像前處理 19
3.1空間色彩轉換 20
3.2直方圖展開 20
3.2.2 Histogram Equalization正規化 26
第四章 傅立葉定位系統 27
4.1系統架構 28
4.2影像增強 29
4.3高頻訊號取得 30
4.3.1影像的二值化 31
4.3.2中值濾波 33
4.3搜尋視窗 34
第五章 實驗結果 39
第六章 結論 43
參考文獻 44

[1] Intelligent Transportation System(ITS),http://www.iot.gov.tw/its/, 1999.
[2] Blayvas I., Bruckstein A. Kimmel R., “Efficient computation of adaptive threshold surfaces for image binarization, ” Pattern Recognition, vol. 39, no. 1, pp. 89-101, January 2006.
[3] Barroso J., Bulas-Cruz J., Dagless E. L., Rafael A., “Nnmber Plate Reading Using Computer Vision ,” Proceedings of the 1997 IEEE International Symposium on Industrial Electronics, vol. 3, pp. 761-766, 1997.
[4] He D. C., Wang L., “Textural filters based on the texture spectrum,” Pattern Recognition, vol. 24, no. 12, pp. 1187-1195, 1991.
[5] 余忠潔， 「A New Approach for Localization of Vehicle License Plates」，碩士論文，靜宜大學，2003。
[6] Zheng D., Zhao Y., Wang J., “An efficient method of license plate location,” Pattern Recognition Letters, vol. 26, no. 15, pp. 2431-2438, November 2005.
[7] Liu D., Xie M., “Detecting License-Plate based on Color Edge From Complex Scenes,” Proceeding of ACIT , Signal and Image Processing, 2005.
[8] Liu D., Xie M., “ Detecting License-Plate based on Wavelet Transform From Complex Scenes,” Proceeding of ACIT , Circuits, Signals, and Systems, 2004.
[9] 馬西聰，「利用灰色關聯度辨識車牌字母的研究」，碩士論文，國立台灣科技大學， 1997。
[10]郭晉銘，「Two-Dimensional Multilevel Thresholding Based on Decision Tree Construction」，碩士論文，南華大學，2003。
[11]Rodolfo Z., Stefano R., “ Vector quantization for license plate Location and image coding,” IEEE Trans. Industrial Electron, vol. 47, no. 1, pp. 159-167, 2000.
[12]Park S. H., Kim K. I., Jung K., Kim H. J., “ Locating car license plate using neural networks,” Electron Lett., vol. 35, no. 17, pp. 1475-1477, 1999.
[13]吳孟聰，「車輛牌照自動辨識系統」，碩士論文，淡江大學，1998。
[14]Ma Z. and Yang F., “Vehicle License Plate Detection based on Projection and Mathematical Morphology,” Proceeding of ACIT , Circuits, Signals, and Systems, 2004.
[15]Cooley J. W., “How the FFT gained acceptance,” Proceedings of the ACM conference on the history of scientific and numeric computation, Princeton, NJ, pp. 133-140, 1987.
[16]Komonvipaht P., Wongsritong K., Cheevasuvit F., Dejhan K., Chitwong S. and Mitatha S., “ Multi-model Histogram Linear Contrast Stretching For Image Enhancement,” Proceedings of the ACRS, vol. 3, 1998.
[17]Gonzalez R. C., Woods R. E., Digital Image Processing, Addison-Wesley, New York, 1992.