基于交叉覆盖神经网络的车牌识别研究

The characters recognition of car plate based on alternative covering algorithm

汽车牌照的自动识别在智能交通系统中占有重要地位,应用前景广阔。本文基于交叉覆盖学习算法和附加样本技术,给出了一种车牌字符识别的方法,实验结果表明该方法能有效识别各种车牌中的字符,识别率高,具有较强的实用价值。

Recognition of vehicle license plate plays a very important role in intelligence transportation system, It can be used in expansive application ranges and has a promising future. Based on alternative covering algorithm and additional sample technology, this article presents a method of characters recognition. The results of the experiments prove that this method can recognize characters of car plate effectively with a high recognition rate, so it have a practical usage.