On-Device Text Image Super Resolution
This work provides a solution for improving text recognition from low-resolution images on mobile devices, benefiting users concerned with privacy and environmental impact by enabling on-device processing.
This paper introduces a novel deep neural network for on-device text image super-resolution, addressing the need for information extraction from low-resolution text images on resource-constrained platforms. The proposed architecture achieves significant PSNR improvement over bicubic upsampling, runs with an average inference time of 11.7 ms per image, and outperforms state-of-the-art on the Text330 dataset.
Recent research on super-resolution (SR) has witnessed major developments with the advancements of deep convolutional neural networks. There is a need for information extraction from scenic text images or even document images on device, most of which are low-resolution (LR) images. Therefore, SR becomes an essential pre-processing step as Bicubic Upsampling, which is conventionally present in smartphones, performs poorly on LR images. To give the user more control over his privacy, and to reduce the carbon footprint by reducing the overhead of cloud computing and hours of GPU usage, executing SR models on the edge is a necessity in the recent times. There are various challenges in running and optimizing a model on resource-constrained platforms like smartphones. In this paper, we present a novel deep neural network that reconstructs sharper character edges and thus boosts OCR confidence. The proposed architecture not only achieves significant improvement in PSNR over bicubic upsampling on various benchmark datasets but also runs with an average inference time of 11.7 ms per image. We have outperformed state-of-the-art on the Text330 dataset. We also achieve an OCR accuracy of 75.89% on the ICDAR 2015 TextSR dataset, where ground truth has an accuracy of 78.10%.