APSIPA Transactions on Signal and Information Processing > Vol 8 > Issue 1

A deep learning-based method for vehicle licenseplate recognition in natural scene

Industrial Technology Advances

Jianzong Wang, Federated Learning Technology Department of Ping An Technology Co., Ltd., China, Xinhui Liu, Ping An Technology Co., Ltd., China, Aozhi Liu, Ping An Technology Co., Ltd., China, liuaozhi1989@gmail.com , Jing Xiao, AI Center of Ping An Technology Co., Ltd., China
 
Suggested Citation
Jianzong Wang, Xinhui Liu, Aozhi Liu and Jing Xiao (2019), "A deep learning-based method for vehicle licenseplate recognition in natural scene", APSIPA Transactions on Signal and Information Processing: Vol. 8: No. 1, e16. http://dx.doi.org/10.1017/ATSIP.2019.8

Publication Date: 20 Jun 2019
© 2019 Jianzong Wang, Xinhui Liu, Aozhi Liu and Jing Xiao
 
Subjects
 
Keywords
Deep learningVehicle license plate recognitionNatural scene
 

Share

Open Access

This is published under the terms of the Creative Commons Attribution licence.

Downloaded: 2039 times

In this article:
I. INTRODUCTION 
II. RELATED WORK 
III. APPROACH 
IV. EXPERIMENTS 
V. CONCLUSION 

Abstract

Vehicle license platerecognition in natural scene is an important research topic in computer vision. The license plate recognition approach in the specific scene has become a relatively mature technology. However, license plate recognition in the natural scene is still a challenge since the image parameters are highly affected by the complicated environment. For the purpose of improving the performance of license plate recognition in natural scene, we proposed a solution to recognize real-world Chinese license plate photographs using the DCNN-RNN model. With the implementation of DCNN, the license plate is located and the features of the license plate are extracted after the correction process. Finally, an RNN model is performed to decode the deep features to characters without character segmentation. Our state-of-the-art system results in the accuracy and recall of 92.32 and 91.89% on the car accident scene dataset collected in the natural scene, and 92.88 and 92.09% on Caltech Cars 1999 dataset.

DOI:10.1017/ATSIP.2019.8