以直覺判斷法之車牌研究

在這汽機車普及的時代，車輛控管儼然成為一個重要的議題，為了解決人力的不足及成本問題，因此才有自動車牌辨識系統的產生。　　目前有關於識別的影樣處理技術已經非常成熟且普及，廣泛應用於偵測以及辨識的領域，本研究試圖以直覺化的方式來觀察車牌字元的特徵進而達到辨識車牌的效果。研究中首先是對影像做前置處理，包括影像灰階化、二值化，再將影像中非車牌的黑色像素區塊進行剃除，剩下來的影像再進行水平與垂直掃描以定位車牌位置，定位完成後進行切割車牌字元，最後以直覺判斷法來辨識車牌字元。

關鍵字

車牌辨識；灰階影像；二值化影像；直覺判斷法

並列摘要

In this era of mobile vehicles ubiquitous, managing vehicles has become an important issue. In order to solve the issues of shortage of manpower and cost, therefore, the automatic license plate recognition systems are invented. 　　At present, image processing technologies relative to recognition are very mature and popular and widely are used in the field of detection and identification. This thesis proposes an intuitive way to observe the characteristic of license plates and to recognize it. For recognizing license plates, the study adopts an image preprocessing, including making image grayscale and binary, removing the areas with any color except the area with black color, locating the position of the license plate and filtering out the symbols in the license plate. Next, using intuitive methods identify the characters on license plate.

並列關鍵字

license plate recognition ； grayscale image ； binary image

參考文獻

[6] 陳麗奾，"在未設限環境下車牌的定位與辨識"，國立臺灣師範大學資訊教育研究所碩士論文，2000。

[1] http://stat.motc.gov.tw/mocdb/stmain.jsp?sys=100&funid=a3301機動車輛登記數

Google Scholar

[2] http://140.134.32.129/scteach/scteach88/text1/3-1.htm方向碼比對

Google Scholar

[3] J.C.H. Poon, M. Ghadiali, G. M. T. Mao, and L. M. Sheung, “A robust visionsystem for vehicle license plate recognition using grey-scale morphology,”Proceedings of the IEEE International Symposium on Industrial Electronics(ISIE ‘95), Vol. 1, pp.394-399,1995.