Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Unified Chinese License Plate Detection and Recognition with High Efficiency

About

Recently, deep learning-based methods have reached an excellent performance on License Plate (LP) detection and recognition tasks. However, it is still challenging to build a robust model for Chinese LPs since there are not enough large and representative datasets. In this work, we propose a new dataset named Chinese Road Plate Dataset (CRPD) that contains multi-objective Chinese LP images as a supplement to the existing public benchmarks. The images are mainly captured with electronic monitoring systems with detailed annotations. To our knowledge, CRPD is the largest public multi-objective Chinese LP dataset with annotations of vertices. With CRPD, a unified detection and recognition network with high efficiency is presented as the baseline. The network is end-to-end trainable with totally real-time inference efficiency (30 fps with 640p). The experiments on several public benchmarks demonstrate that our method has reached competitive performance. The code and dataset will be publicly available at https://github.com/yxgong0/CRPD.

Yanxiang Gong, Linjie Deng, Shuai Tao, Xinchen Lu, Peicheng Wu, Zhiwei Xie, Zheng Ma, Mei Xie• 2022

Related benchmarks

TaskDatasetResultRank
License Plate RecognitionCCPD-Db
Accuracy98
10
License Plate RecognitionCCPD Challenge
Accuracy87.9
8
License Plate RecognitionCCPD Overall
AP96.57
8
License Plate RecognitionCCPD Fn
Accuracy97.2
8
License Plate RecognitionCCPD Tilt
Accuracy93.7
8
License Plate RecognitionCCPD Rotate
Accuracy92.5
8
License Plate RecognitionCCPD Weather
Accuracy90.7
8
License Plate RecognitionCCPD Base
Accuracy98.3
8
Showing 8 of 8 rows

Other info

Follow for update