基于深度学习的模糊车牌字符识别算法

Blurred License Plate Character Recognition Algorithm Based on Deep Learning

随着城市智慧停车场的建设和高速路口自动收费系统的普及,基于深度学习的车牌识别技术得到越来越广泛的应用。为了解决现实中模糊车牌的字符识别,提出一种基于改进CRNN+CTC(Convolutional Neural Network+Recurrent Neural Network+Connectionist Temporal Classification)的免字符分割车牌字符识别算法。首先将CRNN中的标准CNN改为深度可分离卷积网络的微改模型,RNN采用双向长短期记忆网络,并引入CTC损失函数对其进行训练;其次为了避免训练过程中的过拟合现象,损失函数中加入L2正则项,并增加训练数据集;最后引入批量归一化算法来加快训练过程中的学习速度。实验结果表明,与其他几种基于复杂环境中的方法相比,本文算法在三个实验测试集上的平均车牌识别准确率、识别精度和速度方面均有一定提升,网络的鲁棒性和泛化能力也更强。

With the construction of urban smart parking lots and the popularization of automatic toll collection systems at high-speed intersections,license plate recognition technology based on deep learning has been widely used.In order to solve a large number of blurred license plate character recognition in reality,a character free segmentation license plate character recognition algorithm based on improved CRNN+CTC(Recurrent Neural Network/Convolutional Neural Network+Connectionist Temporal Classification)is proposed.Firstly,the standard CNN in CRNN is changed into a micro-modified model of deeply separable convolutional network.Bi-directional long-term and short-term memory network is adopted in RNN,and CTC loss is introduced to train it.Secondly,in order to avoid the overfitting phenomenon in the training process,L2 regular term is added into the loss function and the training dataset is added.Finally,a batch normalization algorithm is introduced to accelerate the learning speed in the training process.Experimental results show that the proposed algorithm is applied to three experimental test sets.Experimental results show that compared with other methods based on complex environment,the proposed algorithm improves the average license plate recognition accuracy,recognition accuracy and speed on the three experimental test sets,and the robustness and generalization ability of the network are also stronger.