Real-time Bangla License Plate Recognition System for Low Resource Video-based Applications

TL;DR

This paper presents a real-time Bangla license plate recognition system optimized for low-resource environments, combining a two-stage detection pipeline with a custom dataset, achieving high accuracy and speed in video applications.

Contribution

The authors developed a novel two-stage detection pipeline with a custom dataset for Bangla license plates, enabling real-time detection and recognition in video streams.

Findings

Achieved 86% AP(0.5) on the dataset.

Detected license plates at 27.2 fps in real-time.

Attained 60.8% OCR F1 score in video recognition.

Abstract

Automatic License Plate Recognition systems aim to provide a solution for detecting, localizing, and recognizing license plate characters from vehicles appearing in video frames. However, deploying such systems in the real world requires real-time performance in low-resource environments. In our paper, we propose a two-stage detection pipeline paired with Vision API that provides real-time inference speed along with consistently accurate detection and recognition performance. We used a haar-cascade classifier as a filter on top of our backbone MobileNet SSDv2 detection model. This reduces inference time by only focusing on high confidence detections and using them for recognition. We also impose a temporal frame separation strategy to distinguish between multiple vehicle license plates in the same clip. Furthermore, there are no publicly available Bangla license plate datasets, for which we created an image dataset and a video dataset containing license plates in the wild. We trained our models on the image dataset and achieved an AP(0.5) score of 86% and tested our pipeline on the video dataset and observed reasonable detection and recognition performance (82.7% detection rate, and 60.8% OCR F1 score) with real-time processing speed (27.2 frames per second).