License Plate Character Recognition Based on Convolutional Neural Network LeNet-5
The application of convolutional neural network LeNet-5 was proposed in license plate character recognition. To fit with the Chinese license plate character recognition problem, the traditional LeNet-5 was modified. The unit number of output layer was changed and the feature map number of C5 layer_was added. Experimental results show that the recognition rate of modified LeNet-5 reaches 98.68% and is better than that of LeNet-5. The results are also compared with the BP neural network, which indicates that the modified LeNet-5 is superior in both recognition rate and speed. This method has a great potential for license plate recognition.
character recognitionlicense plate recognitionconvolutional neural networkLeNet-5
NETL
NSTL
万方数据
维普
