Cascaded Detail-Preserving Networks for Super-Resolution of Document Images

TL;DR

This paper introduces a cascaded, detail-preserving super-resolution network for document images that enhances OCR accuracy by gradually upscaling low-resolution images with a perceptually guided loss function.

Contribution

It proposes a novel cascaded network architecture with perceptual loss for progressive super-resolution of document images, improving OCR performance over existing methods.

Findings

Outperforms recent super-resolution methods on document datasets

Significant OCR recognition improvements when combined with standard OCR systems

Effective gradual upscaling through cascaded detail-preserving networks

Abstract

The accuracy of OCR is usually affected by the quality of the input document image and different kinds of marred document images hamper the OCR results. Among these scenarios, the low-resolution image is a common and challenging case. In this paper, we propose the cascaded networks for document image super-resolution. Our model is composed by the Detail-Preserving Networks with small magnification. The loss function with perceptual terms is designed to simultaneously preserve the original patterns and enhance the edge of the characters. These networks are trained with the same architecture and different parameters and then assembled into a pipeline model with a larger magnification. The low-resolution images can upscale gradually by passing through each Detail-Preserving Network until the final high-resolution images. Through extensive experiments on two scanning document image datasets, we demonstrate that the proposed approach outperforms recent state-of-the-art image super-resolution methods, and combining it with standard OCR system lead to signification improvements on the recognition results.