Combining Attention Module and Pixel Shuffle for License Plate Super-Resolution
This work addresses a domain-specific problem for surveillance systems by enhancing license plate recognition in low-quality images, representing an incremental improvement.
The authors tackled license plate reconstruction from low-resolution, low-quality images by proposing a super-resolution method that combines attention modules with PixelShuffle layers and an improved loss function based on license plate recognition predictions, achieving quantitative and qualitative improvements over baselines.
The License Plate Recognition (LPR) field has made impressive advances in the last decade due to novel deep learning approaches combined with the increased availability of training data. However, it still has some open issues, especially when the data come from low-resolution (LR) and low-quality images/videos, as in surveillance systems. This work focuses on license plate (LP) reconstruction in LR and low-quality images. We present a Single-Image Super-Resolution (SISR) approach that extends the attention/transformer module concept by exploiting the capabilities of PixelShuffle layers and that has an improved loss function based on LPR predictions. For training the proposed architecture, we use synthetic images generated by applying heavy Gaussian noise in terms of Structural Similarity Index Measure (SSIM) to the original high-resolution (HR) images. In our experiments, the proposed method outperformed the baselines both quantitatively and qualitatively. The datasets we created for this work are publicly available to the research community at https://github.com/valfride/lpr-rsr/