Text Prior Guided Scene Text Image Super-Resolution

Citations Over TimeTop 10% of 2023 papers

Abstract

Scene text image super-resolution (STISR) aims to improve the resolution and visual quality of low-resolution (LR) scene text images, while simultaneously boost the performance of text recognition. However, most of the existing STISR methods regard text images as natural scene images, ignoring the categorical information of text. In this paper, we make an inspiring attempt to embed text recognition prior into STISR model. Specifically, we adopt the predicted character recognition probability sequence as the text prior, which can be obtained conveniently from a text recognition model. The text prior provides categorical guidance to recover high-resolution (HR) text images. On the other hand, the reconstructed HR image can refine the text prior in return. Finally, we present a multi-stage text prior guided super-resolution (TPGSR) framework for STISR. Our experiments on the benchmark TextZoom dataset show that TPGSR can not only effectively improve the visual quality of scene text images, but also significantly improve the text recognition accuracy over existing STISR methods. Our model trained on TextZoom also demonstrates certain generalization capability to the LR images in other datasets. The source code of our work is available at: https://github.com/mjq11302010044/TPGSR.

Related Papers

• → Super-resolution approaches for resolution enhancement in magnetic particle imaging(2013)1 cited
• → Spatial Resolution Improvement of Digital and Thermographic Imaging Using an Automatic and Controllable Super-resolution Technique(2019)1 cited
• → Basic study of spatial resolution measurement for autoradiography systems(2006)1 cited
• Influences on spatial resolution of CR system(2004)
• → Investigation of continuous scintillator/SiPM detector for local extremely high spatial resolution PET(2011)