以CAM為基礎之樣式累加向量法在車牌字元辨識系統之應用

Abstract

車牌字元辨識系統，是交通執法系統、電子道路收費系統等眾多交通相關應用領域上的關鍵技術。然而，絕大多數已經研發完成的車牌辨識系統由於採用相當複雜的演算法，而不得不藉由電腦輔助環境來運作。

本論文將車牌字元辨識系統建構於DSP實驗板上(型號：EP20K1500EBC652-1X)，旨在驗證完全交由硬體系統來獨立完成之可能性。該系統不僅使用內容可定址記憶體來取代傳統記憶體，更採取所謂的樣式累加向量法來進行車牌字元辨識。透過模擬實驗，該系統不但可達到99.56% 之辨識率，所需時間也比使用傳統記憶體的對照組還要短。這證明了車牌字元辨識系統在硬體化上的可行性。

License plate character recognition system becomes the key to many traffic related applications such as the traffic enforcement systems and the electronic toll-collection systems. However, most of the developed license plate recognition systems are PC-based due to the use of complicated algorithms.

This thesis implements the license plate character recognition on the DSP board (SN: EP20K1500EBC652-1X) to verify the potential of a hardware system other than PC-based. The system adopts a specific storage called the Content Addressable Memories to replace the common RAM and recognizes the license plate characters by the so-called Pattern Accumulated Vector method. Through series of simulations and experiments, the recognition reaches a rate of 99.56% and is faster than the RAM-based system. This confirms that the proposed system has potential and is feasible in the future.