Scene Text Detection with Supervised Pyramid Context Network

TL;DR

This paper introduces SPCNET, a supervised pyramid context network based on FPN and instance segmentation, significantly improving scene text detection accuracy and reducing false positives in complex natural scenes.

Contribution

The paper proposes a novel supervised pyramid context network (SPCNET) that enhances scene text detection by integrating semantic guidance and FPN sharing, outperforming previous methods.

Findings

Achieves state-of-the-art F-measure scores on multiple datasets

Effectively reduces false positives in complex scenes

Maintains marginal additional computational cost

Abstract

Scene text detection methods based on deep learning have achieved remarkable results over the past years. However, due to the high diversity and complexity of natural scenes, previous state-of-the-art text detection methods may still produce a considerable amount of false positives, when applied to images captured in real-world environments. To tackle this issue, mainly inspired by Mask R-CNN, we propose in this paper an effective model for scene text detection, which is based on Feature Pyramid Network (FPN) and instance segmentation. We propose a supervised pyramid context network (SPCNET) to precisely locate text regions while suppressing false positives. Benefited from the guidance of semantic information and sharing FPN, SPCNET obtains significantly enhanced performance while introducing marginal extra computation. Experiments on standard datasets demonstrate that our SPCNET clearly outperforms start-of-the-art methods. Specifically, it achieves an F-measure of 92.1% on ICDAR2013, 87.2% on ICDAR2015, 74.1% on ICDAR2017 MLT and 82.9% on Total-Text.