License Plate Super-Resolution Using Diffusion Models

TL;DR

This paper introduces a diffusion model-based approach for license plate super-resolution, significantly outperforming existing CNN and GAN methods in image quality metrics and human preference, enhancing surveillance recognition accuracy.

Contribution

The study demonstrates the effectiveness of diffusion models for license plate super-resolution, achieving superior PSNR and SSIM improvements over state-of-the-art methods like SwinIR and ESRGAN.

Findings

12.55% PSNR improvement over SwinIR

37.32% PSNR improvement over ESRGAN

92% human evaluators preferred our images

Abstract

In surveillance, accurately recognizing license plates is hindered by their often low quality and small dimensions, compromising recognition precision. Despite advancements in AI-based image super-resolution, methods like Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs) still fall short in enhancing license plate images. This study leverages the cutting-edge diffusion model, which has consistently outperformed other deep learning techniques in image restoration. By training this model using a curated dataset of Saudi license plates, both in low and high resolutions, we discovered the diffusion model's superior efficacy. The method achieves a 12.55\% and 37.32% improvement in Peak Signal-to-Noise Ratio (PSNR) over SwinIR and ESRGAN, respectively. Moreover, our method surpasses these techniques in terms of Structural Similarity Index (SSIM), registering a 4.89% and 17.66% improvement over SwinIR and ESRGAN, respectively. Furthermore, 92% of human evaluators preferred our images over those from other algorithms. In essence, this research presents a pioneering solution for license plate super-resolution, with tangible potential for surveillance systems.