基于FPGA的车牌字符识别方法的研究

Research of License Plate Character Recognition Based on FPGA

设计了根据车牌的彩色特征对车牌位置进行粗定位,再利用车牌字符二值化特征来精确定位的双重车牌定位方法。在中值滤波和二值化等预处理后,提取出车牌中的字母和数字字符并建立相应的模板,通过字符归一化在NIOSII中采用最大相似度算法较好的识别了车牌号码。实验结果表明,该方法具有良好的实时性和较高的识别率。

Designed a combined method of localizing the License Plate according to the characteristic of colorful and binaryzation of captured License Plate image.After the median filtering is used to reduce the noise of the image,and the stage of image binaryzation,the characters are divided.Then the character detection is done with the module match designed with software in NIOS II.The test results indicate that the license plate character recognition system based on which can real-time recognize the character accurately.