论文标题
将注意力板的注意模块和像素混合机组合到超级分辨率
Combining Attention Module and Pixel Shuffle for License Plate Super-Resolution
论文作者
论文摘要
车牌识别（LPR）领域在过去十年中取得了令人印象深刻的进步，这是由于新颖的深度学习方法以及培训数据的可用性增加。但是，它仍然存在一些开放问题，尤其是当数据来自低分辨率（LR）和低质量图像/视频时，如监视系统中时。这项工作着重于LR和低质量图像中的车牌（LP）重建。我们提出了一种单形图像超分辨率（SISR）方法，该方法通过利用像素弹套层的功能来扩展注意力/变压器模块概念，并且基于LPR预测具有改进的损耗函数。为了训练提出的体系结构，我们使用通过在结构相似性指数量度（SSIM）方面应用沉重的高斯噪声而产生的合成图像。在我们的实验中，提出的方法在定量和定性上都优于基准。我们为这项工作创建的数据集可向研究社区公开使用https://github.com/valfride/lpr-rsr/
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/
