CAJ | 학술논문

通过对车牌定位、车牌字符分割和车牌字符识别进行研究,提出了一种车牌识别系统的设计和实验仿真方法。该方法首先采用基于Canny算子边缘检测和数学形态学相结合的方法定位出车牌,进行二值化、滤波和形态学开运算后使用投影二分法分割出7个车牌字符,最后使用模板匹配和特征统计相结合的方法识别出车牌字符。试验表明该方法是有效的、可行的,与传统使用单一算法相比较,该方法大大提高了车牌识别系统的正确率。
통과대차패정위、차패자부분할화차패자부식별진행연구,제출료일충차패식별계통적설계화실험방진방법。해방법수선채용기우Canny산자변연검측화수학형태학상결합적방법정위출차패,진행이치화、려파화형태학개운산후사용투영이분법분할출7개차패자부,최후사용모판필배화특정통계상결합적방법식별출차패자부。시험표명해방법시유효적、가행적,여전통사용단일산법상비교,해방법대대제고료차패식별계통적정학솔。
This paper introduced a design and experimental simulation method of license plate recognition system based on the research of license plate location,license plate character segmentation and license plate character recognition.This method firstly located a license plate with the combining method of Canny operator edge detection and mathematical morphology.After binarization,filtering and morphological opening process,seven license plate characters were segmented by projection dichotomy.Finally,license plate character was recognized by the combining method of template matching and statistical characteristics.Experiment demonstrates that this method is feasible,effective and greatly improves the accuracy rate of license plate recognition system,compared with the traditional method of a single algorithm.