CAJ | 학술논문

车牌识别（License Plate Recognition， LPR）是智能交通系统（Intelligent Transport System， ITS）需要解决的重点问题之一，目前的车牌识别系统基本上是以PC机为平台实现的，在成本、体积、灵活性等方面有很大局限性。针对这一问题，设计了一种基于ARM嵌入式平台的车牌识别系统，并针对嵌入式平台改进和优化了车牌识别相关算法，经试验证明本系统不仅准确性好，而且成本低、体积小、功能可扩展性强。
차패식별（License Plate Recognition， LPR）시지능교통계통（Intelligent Transport System， ITS）수요해결적중점문제지일，목전적차패식별계통기본상시이PC궤위평태실현적，재성본、체적、령활성등방면유흔대국한성。침대저일문제，설계료일충기우ARM감입식평태적차패식별계통，병침대감입식평태개진화우화료차패식별상관산법，경시험증명본계통불부준학성호，이차성본저、체적소、공능가확전성강。
License Plate Recognition (LPR) is one of the most important problems that need to be solved in the Intelligent Transport System (ITS). The current LPRs are mainly designed on the platform of personal computer, which have great limitations in terms of cost, volume and flexibility. Concerning this issue, a LPR is designed on the platform of embedded system based on ARM processor in this paper. And the relative algorithm about plate location and character recognition is improved. Experimental results show that this system is not only accurate, but also has these features such as low-cost, small size, height flexibility, and its function can be extended easily.