摘要： 针对低分辨率灰度车牌号码数字识别问题,提出了一种利用网格技术和Gabor变换直接从灰度图像进行特征提取的新方法,并设计了一种集成型神经网络模型来进行识别,对大量的实验数据进行识别实验得到99.26%的识别率,显示该方法是非常有效的。

关键词: Gabor特征提取, 车牌号码字符识别, 集成神经网络, 智能交通系统

Abstract: A new plate number character recognition method based on Gabor orientation feature and neural networks technologies is presented in this paper. Based on elastic meshing techniques and Gabor filter, a new feature extraction approach for low resolution plate number characters is proposed. An integrated neural networks model is designed as an intelligent classifier. Experiments on large data set produce the recognition rate of 99. 26%, show that the approach is very effective.

中图分类号: 

• TP391.41