License Plate Detection and Recognition Using Deeply Learned Convolutional Neural Networks

TLDR

The study presents Sighthound’s fully automated license plate detection and recognition system. The core technology employs a sequence of deep CNNs interlaced with efficient algorithms, trained and fine‑tuned to be robust to pose, lighting, occlusion, and diverse plate templates. Quantitative analysis shows the system outperforms leading ALPR technologies on several benchmarks and is available via the Sighthound Cloud API.

Abstract

This work details Sighthounds fully automated license plate detection and recognition system. The core technology of the system is built using a sequence of deep Convolutional Neural Networks (CNNs) interlaced with accurate and efficient algorithms. The CNNs are trained and fine-tuned so that they are robust under different conditions (e.g. variations in pose, lighting, occlusion, etc.) and can work across a variety of license plate templates (e.g. sizes, backgrounds, fonts, etc). For quantitative analysis, we show that our system outperforms the leading license plate detection and recognition technology i.e. ALPR on several benchmarks. Our system is available to developers through the Sighthound Cloud API at https://www.sighthound.com/products/cloud