# Binary Document Image Super Resolution for Improved Readability and OCR Performance

arXiv: https://arxiv.org/abs/1812.02475 · HTML: https://mlsanity.com/paper/1812.02475/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Dec 2018.

## Built on by (most cited first, 7 of 7)

- [Text Gestalt: Stroke-Aware Scene Text Image Super-Resolution](https://mlsanity.com/paper/2112.08171/) (2021)
- [C3-STISR: Scene Text Image Super-resolution with Triple Clues](https://mlsanity.com/paper/2204.14044/) (2022)
- [Improving Scene Text Image Super-resolution via Dual Prior Modulation Network](https://mlsanity.com/paper/2302.10414/) (2023)
- [SplitSR: An End-to-End Approach to Super-Resolution on Mobile Devices](https://mlsanity.com/paper/2101.07996/) (2021)
- [CoreDeep: Improving Crack Detection Algorithms Using Width Stochasticity](https://mlsanity.com/paper/2209.04648/) (2022)
- [HiREN: Towards Higher Supervision Quality for Better Scene Text Image Super-Resolution](https://mlsanity.com/paper/2307.16410/) (2023)
- [One Model for Two Tasks: Cooperatively Recognizing and Recovering Low-Resolution Scene Text Images by Iterative Mutual Guidance](https://mlsanity.com/paper/2409.14483/) (2024)

## Abstract (arXiv)

There is a need for information retrieval from large collections of low-resolution (LR) binary document images, which can be found in digital libraries across the world, where the high-resolution (HR) counterpart is not available. This gives rise to the problem of binary document image super-resolution (BDISR). The objective of this paper is to address the interesting and challenging problem of super resolution of binary Tamil document images for improved readability and better optical character recognition (OCR). We propose multiple deep neural network architectures to address this problem and analyze their performance. The proposed models are all single image super-resolution techniques, which learn a generalized spatial correspondence between the LR and HR binary document images. We employ convolutional layers for feature extraction followed by transposed convolution and sub-pixel convolution layers for upscaling the features. Since the outputs of the neural networks are gray scale, we utilize the advantage of power law transformation as a post-processing technique to improve the character level pixel connectivity. The performance of our models is evaluated by comparing the OCR accuracies and the mean opinion scores given by human evaluators on LR images and the corresponding model-generated HR images.