A Single-Target License Plate Detection with Attention

TL;DR

This paper proposes a specialized single-target license plate detection method using attention mechanisms to improve efficiency and accuracy, especially for deployment on embedded devices.

Contribution

It introduces a novel attention-based approach tailored for license plate detection, reducing complexity and enhancing performance over general object detection models.

Findings

Achieves higher detection accuracy in complex scenarios

Reduces model size and computational requirements

Demonstrates effective deployment on embedded devices

Abstract

With the development of deep learning, Neural Network is commonly adopted to the License Plate Detection (LPD) task and achieves much better performance and precision, especially CNN-based networks can achieve state of the art RetinaNet[1]. For a single object detection task such as LPD, modified general object detection would be time-consuming, unable to cope with complex scenarios and a cumbersome weights file that is too hard to deploy on the embedded device.