多雾霾天气车牌识别系统图像预处理算法

Image preprocessing algorithm for License Plate Recognition system under high frequent foggy weather

为提高车牌识别系统在雾霾环境下识别车牌的准确性,提出了一种新的图像预处理算法.首先,用主成分分析(PCA)和Fisher线性判别分析(LDA)方法对车牌图像进行雾霾检测;然后,用基于暗原色先验的方法对有雾图像进行去雾处理.仿真结果表明:该预处理算法不仅可以满足车牌识别系统实时性要求,而且可以提高系统在雾霾环境下识别车牌的准确性.

In order to improve the License Plate Recognition（LPR）system＇s accuracy in foggy conditions,a new preprocessing algorithm was proposed.Firstly,Principal Component Analysis（PCA）and Linear Discriminant Analysis（LDA）were used to detect the plate images whether they are foggy or not,then the Dark Channel Prior was used to remove the influence of fog and haze in the images which were distinguished to be foggy. The Simulation results showed this preprocessing algorithm can satisfy the real-time requirement of the LPR system and improve the accuracy of the LPR system.