【摘要】 提出了基于Zernike矩和小波变换特征相结合的车牌字符识别方法。利用Zernike矩描述字符全局特征,小波变换系数描述字符细节特征,采用神经网络进行车牌字符分类。测试结果表明,这种组合了两种特征优点的方法实用有效,识别效果优于两种特征独立使用的情况。更多还原

【Abstract】 This paper presents a method of license plate character recognition based on the combination of Zernike moment and wavelet transformation features.The Zernike moment is used to describe the global feature of the characters,and the wavelet transform coefficient for the detailed feature of the characters.A neural network is used to classify the license plate characters. Experimental results show the presented method achieves better recognition accuracy than using two features separately.更多还原