On-Device Text Image Super Resolution

TL;DR

This paper introduces a novel deep neural network for on-device text image super-resolution that improves OCR accuracy and runs efficiently on resource-limited devices like smartphones, reducing reliance on cloud processing.

Contribution

The paper presents a new neural network architecture optimized for edge devices, enhancing image sharpness and OCR performance while maintaining fast inference times.

Findings

Achieves higher PSNR than bicubic upsampling on benchmark datasets.

Runs with an average inference time of 11.7 ms per image.

Attains 75.89% OCR accuracy on ICDAR 2015 TextSR dataset.

Abstract

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%.