基于Gabor特征和协同神经网络的车牌识别方法

研究了车牌字符识别问题,针对车牌识别系统易受天气及光照变化影响的实际应用,将Gabor特征和协同神经网络应用在车牌字符识别中,提高了识别率.首先对车牌字符进行二值化和切分,然后利用Gabor滤波器提取车牌字符的特征参数;再利用协同模式训练特征参数,进而得出训练样本;最后根据协同神经网络进一步识别车牌字符.通过大量仿真实验表明,该方法在不同场景、光照条件下,与传统方法相比,识别率有了较大改进,该方法在车牌识别领域有较强的实用性.

A method for license plate recognition in vehicle based on Gabor feature and synergetic neural network

Vehicle license recognition has been studied under the climate and light conditions.The feature extraction of Gabor and synergetic neural network has been used to enhance the recognition rate.First,the characters of vehicle license go through the binarization and segmenting to extract the characteristic parameters of the license characters by Gabor filter.Then,the synergetic mode is used to train the characteristic parameters and work out the training sample.Finally,the synergetic neural network is utilized to recognize the license character.Under a variety of environments and light conditions, this approach achieves a much higher rate of recognition rate compared with the traditional mode suggesting that this new method is very effective in the field of vehicle license recognition.