An Efficient License Plate Location Algorithm Based on Deep Leaming

In order to improve the robustness of the license plate location algorithm in complex environments and reduce the impact of complex background on the performance of the algorithm, a license plate location algorithm based on corner detection and deep learning is proposed. The algorithm first uses color segmentation to select the operating area, then uses the corner detection and morphological operations to segment out the area of interest, and finally uses a convolutional neural network to extract the deep features of the area of interest and get license plate area. The experiment compares the proposed algorithm with other algorithms by using the data set collected in a complex environment, and the results show that the algorithm is more robust in complex environments, and has a higher accuracy while ensuring the detection speed rate.