End-to-End High Accuracy License Plate Recognition Based on Depthwise Separable Convolution Networks

TL;DR

This paper introduces a novel, efficient license plate recognition system using depthwise separable convolution networks, achieving high accuracy and speed in challenging real-world conditions.

Contribution

It presents a new segmentation-free framework and a diverse dataset, NP-ALPR, with a novel network architecture that outperforms previous methods in accuracy and efficiency.

Findings

Recognition accuracy over 99% on multiple datasets

Achieves over 70 fps in real-world scenarios

Requires less computational power than prior solutions

Abstract

Automatic license plate recognition plays a crucial role in modern transportation systems such as for traffic monitoring and vehicle violation detection. In real-world scenarios, license plate recognition still faces many challenges and is impaired by unpredictable interference such as weather or lighting conditions. Many machine learning based ALPR solutions have been proposed to solve such challenges in recent years. However, most are not convincing, either because their results are evaluated on small or simple datasets that lack diverse surroundings, or because they require powerful hardware to achieve a reasonable frames-per-second in real-world applications. In this paper, we propose a novel segmentation-free framework for license plate recognition and introduce NP-ALPR, a diverse and challenging dataset which resembles real-world scenarios. The proposed network model consists of the latest deep learning methods and state-of-the-art ideas, and benefits from a novel network architecture. It achieves higher accuracy with lower computational requirements than previous works. We evaluate the effectiveness of the proposed method on three different datasets and show a recognition accuracy of over 99% and over 70 fps, demonstrating that our method is not only robust but also computationally efficient.