ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection

TL;DR

ContourNet advances scene text detection by addressing false positives and scale variance through a novel adaptive proposal network and texture-aware contour modeling, achieving state-of-the-art results.

Contribution

The paper introduces ContourNet, combining Adaptive-RPN and LOTM to improve accuracy in arbitrary-shaped scene text detection, especially under challenging conditions.

Findings

Achieves state-of-the-art performance on Total-Text, CTW1500, and ICDAR2015 datasets.

Effectively suppresses false positives caused by monotonous textures.

Handles large scale variance of scene texts with improved robustness.

Abstract

Scene text detection has witnessed rapid development in recent years. However, there still exists two main challenges: 1) many methods suffer from false positives in their text representations; 2) the large scale variance of scene texts makes it hard for network to learn samples. In this paper, we propose the ContourNet, which effectively handles these two problems taking a further step toward accurate arbitrary-shaped text detection. At first, a scale-insensitive Adaptive Region Proposal Network (Adaptive-RPN) is proposed to generate text proposals by only focusing on the Intersection over Union (IoU) values between predicted and ground-truth bounding boxes. Then a novel Local Orthogonal Texture-aware Module (LOTM) models the local texture information of proposal features in two orthogonal directions and represents text region with a set of contour points. Considering that the strong unidirectional or weakly orthogonal activation is usually caused by the monotonous texture characteristic of false-positive patterns (e.g. streaks.), our method effectively suppresses these false positives by only outputting predictions with high response value in both orthogonal directions. This gives more accurate description of text regions. Extensive experiments on three challenging datasets (Total-Text, CTW1500 and ICDAR2015) verify that our method achieves the state-of-the-art performance. Code is available at https://github.com/wangyuxin87/ContourNet.