# Towards Document Image Quality Assessment: A Text Line Based Framework and A Synthetic Text Line Image Dataset

## TL;DR

This paper introduces a text line based framework for assessing document image quality, utilizing a CNN model and a large synthetic dataset, significantly improving accuracy over existing methods.

## Contribution

It proposes a novel text line based assessment framework and provides a large synthetic dataset for training and evaluation.

## Key findings

- Framework outperforms state-of-the-art methods on benchmarks.
- Synthetic dataset enables effective training of quality prediction models.
- Text line quality prediction correlates well with overall document image quality.

## Abstract

Since the low quality of document images will greatly undermine the chances of success in automatic text recognition and analysis, it is necessary to assess the quality of document images uploaded in online business process, so as to reject those images of low quality. In this paper, we attempt to achieve document image quality assessment and our contributions are twofold. Firstly, since document image quality assessment is more interested in text, we propose a text line based framework to estimate document image quality, which is composed of three stages: text line detection, text line quality prediction, and overall quality assessment. Text line detection aims to find potential text lines with a detector. In the text line quality prediction stage, the quality score is computed for each text line with a CNN-based prediction model. The overall quality of document images is finally assessed with the ensemble of all text line quality. Secondly, to train the prediction model, a large-scale dataset, comprising 52,094 text line images, is synthesized with diverse attributes. For each text line image, a quality label is computed with a piece-wise function. To demonstrate the effectiveness of the proposed framework, comprehensive experiments are evaluated on two popular document image quality assessment benchmarks. Our framework significantly outperforms the state-of-the-art methods by large margins on the large and complicated dataset.