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

by   Yuxin Wang, et al.

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


page 1

page 4

page 8


Arbitrary Shape Scene Text Detection with Adaptive Text Region Representation

Scene text detection attracts much attention in computer vision, because...

N-RPN: Hard Example Learning for Region Proposal Networks

The region proposal task is to generate a set of candidate regions that ...

What's Wrong with the Bottom-up Methods in Arbitrary-shape Scene Text Detection

The latest trend in the bottom-up perspective for arbitrary-shape scene ...

StrokeNet: Stroke Assisted and Hierarchical Graph Reasoning Networks

Scene text detection is still a challenging task, as there may be extrem...

Kernel Proposal Network for Arbitrary Shape Text Detection

Segmentation-based methods have achieved great success for arbitrary sha...

TextRay: Contour-based Geometric Modeling for Arbitrary-shaped Scene Text Detection

Arbitrary-shaped text detection is a challenging task due to the complex...

TextDCT: Arbitrary-Shaped Text Detection via Discrete Cosine Transform Mask

Arbitrary-shaped scene text detection is a challenging task due to the v...

Please sign up or login with your details

Forgot password? Click here to reset