VRAE: Vertical Residual Autoencoder for License Plate Denoising and Deblurring

2025-09-10

AI Summary

To address noise and blur in license plate images caused by adverse weather, low illumination, and high-speed motion in traffic surveillance, this paper proposes the Vertical Residual Autoencoder (VRAE), a lightweight, real-time enhancement model tailored for license plate regions. VRAE introduces an input-aware feature injection mechanism at each encoding layer to preserve structural details and facilitate gradient flow, and employs vertical residual connections to improve multi-scale feature reuse efficiency. Evaluated on a vehicle image dataset, VRAE achieves approximately 20% higher PSNR, 50% lower NMSE, and 1% improvement in SSIM compared to conventional autoencoders, GANs, and flow-based methods—while increasing parameter count by only 1%. These results demonstrate VRAE’s superior balance between restoration accuracy and computational efficiency for real-time license plate enhancement.

Technology Category

• Computer Vision: Large Vision Models
• Machine Learning: Deep Generative Models & Autoencoders
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Security and Privacy: Privacy-enhancing technologies
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

In real-world traffic surveillance, vehicle images captured under adverse weather, poor lighting, or high-speed motion often suffer from severe noise and blur. Such degradations significantly reduce the accuracy of license plate recognition systems, especially when the plate occupies only a small region within the full vehicle image. Restoring these degraded images a fast realtime manner is thus a crucial pre-processing step to enhance recognition performance. In this work, we propose a Vertical Residual Autoencoder (VRAE) architecture designed for the image enhancement task in traffic surveillance. The method incorporates an enhancement strategy that employs an auxiliary block, which injects input-aware features at each encoding stage to guide the representation learning process, enabling better general information preservation throughout the network compared to conventional autoencoders. Experiments on a vehicle image dataset with visible license plates demonstrate that our method consistently outperforms Autoencoder (AE), Generative Adversarial Network (GAN), and Flow-Based (FB) approaches. Compared with AE at the same depth, it improves PSNR by about 20%, reduces NMSE by around 50%, and enhances SSIM by 1%, while requiring only a marginal increase of roughly 1% in parameters.

Problem

• Restoring license plate images degraded by noise and blur
• Enhancing recognition accuracy in traffic surveillance systems
• Improving real-time image preprocessing for small license plate regions

Innovation

• Vertical Residual Autoencoder architecture for enhancement
• Auxiliary block injects input-aware features at encoding stages
• Improves PSNR by 20% with minimal parameter increase