Detecting Curve Text in the Wild: New Dataset and New Solution

TL;DR

This paper introduces a new dataset for curve text detection and proposes a novel polygon-based detector that effectively captures curved text in natural scenes, outperforming existing methods.

Contribution

The paper presents the first large-scale curve text dataset CTW1500 and a new end-to-end polygon-based detection method with context-aware learning for curved text.

Findings

The proposed method outperforms state-of-the-art approaches on CTW-1500.

The CTD + TLOC achieves high accuracy on both curve and non-curve text subsets.

The approach is adaptable to rectangular and quadrilateral bounding boxes.

Abstract

Scene text detection has been made great progress in recent years. The detection manners are evolving from axis-aligned rectangle to rotated rectangle and further to quadrangle. However, current datasets contain very little curve text, which can be widely observed in scene images such as signboard, product name and so on. To raise the concerns of reading curve text in the wild, in this paper, we construct a curve text dataset named CTW1500, which includes over 10k text annotations in 1,500 images (1000 for training and 500 for testing). Based on this dataset, we pioneering propose a polygon based curve text detector (CTD) which can directly detect curve text without empirical combination. Moreover, by seamlessly integrating the recurrent transverse and longitudinal offset connection (TLOC), the proposed method can be end-to-end trainable to learn the inherent connection among the position offsets. This allows the CTD to explore context information instead of predicting points independently, resulting in more smooth and accurate detection. We also propose two simple but effective post-processing methods named non-polygon suppress (NPS) and polygonal non-maximum suppression (PNMS) to further improve the detection accuracy. Furthermore, the proposed approach in this paper is designed in an universal manner, which can also be trained with rectangular or quadrilateral bounding boxes without extra efforts. Experimental results on CTW-1500 demonstrate our method with only a light backbone can outperform state-of-the-art methods with a large margin. By evaluating only in the curve or non-curve subset, the CTD + TLOC can still achieve the best results. Code is available at https://github.com/Yuliang-Liu/Curve-Text-Detector.