Forensic License Plate Recognition with Compression-Informed Transformers

Abstract

Forensic license plate recognition (FLPR) remains an open challenge in legal contexts such as criminal investigations, where unreadable license plates (LPs) need to be deciphered from highly compressed and/or low resolution footage, e.g., from surveillance cameras. In this work, we propose a side-informed Transformer architecture that embeds knowledge on the input compression level to improve recognition under strong compression. We show the effectiveness of Transformers for license plate recognition (LPR) on a low-quality real-world dataset. We also provide a synthetic dataset that includes strongly degraded, illegible LP images and analyze the impact of knowledge embedding on it. The network outperforms existing FLPR methods and standard state-of-the art image recognition models while requiring less parameters. For the severest degraded images, we can improve recognition by up to 8.9 percent points.

Published at ICIP 2022, Code: https://faui1-gitlab.cs.fau.de/denise.moussa/forensic-license-plate-transformer/

References in corpus (2)

• Transformers in Vision: A Survey
• 3D Rendering Framework for Data Augmentation in Optical Character Recognition

Cited by in corpus (5)

• Super-Resolution of License Plate Images Using Attention Modules and Sub-Pixel Convolution Layers
• Do We Train on Test Data? The Impact of Near-Duplicates on License Plate Recognition
• Toward Advancing License Plate Super-Resolution in Real-World Scenarios: A Dataset and Benchmark
• Enhancing License Plate Super-Resolution: A Layout-Aware and Character-Driven Approach
• Relaxed syntax modeling in Transformers for future-proof license plate recognition