1. Chinese License Plate Recognition Using Machine and Deep Learning Models
- Author
-
Xu Ni, Yanbo Deng, Xiaoyu Zhang, Mina Maleki, and Changyu Jiang
- Subjects
Computer science ,business.industry ,Deep learning ,Pattern recognition ,Optical character recognition ,computer.software_genre ,Convolutional neural network ,Field (computer science) ,Long short term memory ,Recurrent neural network ,Chinese city ,Artificial intelligence ,business ,computer ,License - Abstract
The license plate detection and recognition (LPDR) system is one of the practical applications of optical character recognition (OCR) technology in the field of automobile transportation. This paper investigates several state-of-the-art machine and deep learning algorithms for the Chinese license plate recognition based on convolutional neural networks (CNN), long short term memory (LSTM), and k-nearest neighbors (KNN) models. Comparing the performance of these models on the Chinese City Parking Dataset (CCPD) demonstrates that the convolutional recurrent neural network (CRNN) model with an accuracy of 95% is the most accurate and performs better than other models to detect the license plates.
- Published
- 2021
- Full Text
- View/download PDF