基于伪zernike矩车牌字符识别.pdf

2012 年 8 月 电 子 测 试 Aug. 2012 第 8 期 ELECTRONIC TEST No.8 基于伪zernike矩的车牌字符识别 1 1 2 王 峰 ， 孟立凡 ， 李 艳 （1 中北大学电子测试技术国家重点实验室， 太原 030051； 2 山东省滕州市第二中学， 滕州 277500） 摘要：基于伪zernike矩的不变性，提出了基于伪zernike矩特征提取的车牌字符识别方法。在车牌区域定 位的基础上，通过对图像的二值化过程和字符图像分割等一系列处理，在进行归一化处理后分别提取伪 zernike的高阶矩。将提取的伪zernike矩作为字符的特征描述输入到BP神经网络进行训练，最后进行车牌 字符分类识别。通过实验证明了该方法的的可行性。测试结果表明，这种方法实用有效，识别效果优于HU 矩和zernike矩。而且可以计算出错误率和可识别的最佳矩，减小了计算量且增强了字符识别的实时性。 关键词：车牌字符识别；伪zernike矩；BP神经网络；特征提取 中图分类号: TP389 文献标识码: A Recognition of license plate characters based on Pseudo-zernike moments 1 1 2 Wang Feng ， Meng Lifan ， Li Yan （1 National Key Laboratory of Electronic Measurement Technology, North University of China, Taiyuan 030051; 2 The second middle school of Tengzhou, Tengzhou 277500） Abstract: Based on the invariance of the Pseudo-zernike Moments, this paper presents a novel method of lisence plate character recognition based on Pseudo-zernike Moments(PZM) . On the basis of plate area having been positived, affter a serisr of processing including binarization, segmengtion, normalization we extracted high- level Peudo-Prnike Mments these we take as the description of character feature to make the BP neural network training. Finally the license plate characters can be classified and recognised. The feasibility of the method can be proved by the experiments. Expriments results show that the presented approach achieves better recogn