Text Flow: A Unified Text Detection System in Natural Scene Images

TL;DR

The paper introduces Text Flow, a unified scene text detection system using min-cost flow networks that reduces error accumulation and outperforms existing methods across multiple datasets.

Contribution

It proposes a novel unified detection framework that integrates multiple steps into one process using min-cost flow networks, improving accuracy and robustness.

Findings

Outperforms state-of-the-art methods on ICDAR datasets

Achieves higher recall and F-score in multilingual text detection

Effectively reduces error accumulation in text detection pipeline

Abstract

The prevalent scene text detection approach follows four sequential steps comprising character candidate detection, false character candidate removal, text line extraction, and text line verification. However, errors occur and accumulate throughout each of these sequential steps which often lead to low detection performance. To address these issues, we propose a unified scene text detection system, namely Text Flow, by utilizing the minimum cost (min-cost) flow network model. With character candidates detected by cascade boosting, the min-cost flow network model integrates the last three sequential steps into a single process which solves the error accumulation problem at both character level and text line level effectively. The proposed technique has been tested on three public datasets, i.e, ICDAR2011 dataset, ICDAR2013 dataset and a multilingual dataset and it outperforms the state-of-the-art methods on all three datasets with much higher recall and F-score. The good performance on the multilingual dataset shows that the proposed technique can be used for the detection of texts in different languages.