【摘要】 Gabor变换能有效抑制字符的噪声、变形、断裂、模糊、以及亮度不均等图象干扰,适合于象车牌字符这样的低质量字符特征提取。Gabor变换的难点是滤波器组参数优化设计,因此提出了一种快速参数优化设计方法,并提出了一种Gabor特征融合方法。实验表明,用此方法获取的Gabor滤波器组参数效果良好,已经运用于实际的车牌识别系统中,取得了满意的效果。更多还原

【Abstract】 Gabor transform performs excellently in image process with low noise、backgrounds or stroke distortions.It is suitable for low quality character recognition such as vehicle registration number recognition.However,choosing Gabor parameters in design is real a problem.The authors summarized a fast parameter choosing method.Experiment results show this method is effective.It has been used in actual systems and has got satisfied results.更多还原