Abstract
License Plate Recognition (LPR) is of great significance due to its wide range of applications in the Intelligent Transportation System (ITS). It is an important and challenging research topic in image recognition fields. However, many of the current methods are still not robust in real-world complex scenario. The main contribution of this paper is to propose a multi-task convolutional neural network for license plate detection and recognition (MTLPR) with better accuracy and lower computational cost, and introduce a comprehensive data set of Chinese license plate. First, we train a Multi-task Convolutional Neural Networks (MTCNN) to detect license plate. Then we introduce an end-to-end method to recognize license plate information, which further improves the recognition precision. Last, We compare the experimental result with other state-of-the-art methods. The experimental result shows that our method achieves up to 98% recognition precision and is superior to other methods in the precision and speed of detection and recognition.
Highlights
License Plate Recognition (LPR) technology is an important component of modern intelligent transportation system, and it is a challenging and important task which is used in traffic management, digital security surveillance, vehicle recognition, parking management of large cities
The basic process of LPR is as follows: first, process and analyze the vehicle images or videos captured by the camera, use digital image processing, pattern recognition or other technologies to obtain the license plate number and color information
We propose a new robust real-time LPR method named multi-task convolutional neural network for license plate detection and recognition (MTLPR), which uses an end-to-end algorithm to recognize plate characters
Summary
License Plate Recognition (LPR) technology is an important component of modern intelligent transportation system, and it is a challenging and important task which is used in traffic management, digital security surveillance, vehicle recognition, parking management of large cities. We propose a new robust real-time LPR method named multi-task convolutional neural network for license plate detection and recognition (MTLPR), which uses an end-to-end algorithm to recognize plate characters. Li et al [17] proposed method to jointly solve license plate detection and recognition by a single deep neural network They adopt VGG to extract low level CNN features which has the disadvantages of slow training speed. All three networks adopt end-to-end multi-task framework including license plate classification task, border regression task, corner point regression task, and color recognition task after the last fully connected layer It utilizes the correlation between tasks to improve the network performance during the training process.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
