Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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

About

Arbitrary-shaped text detection is a challenging task due to the complex geometric layouts of texts such as large aspect ratios, various scales, random rotations and curve shapes. Most state-of-the-art methods solve this problem from bottom-up perspectives, seeking to model a text instance of complex geometric layouts with simple local units (e.g., local boxes or pixels) and generate detections with heuristic post-processings. In this work, we propose an arbitrary-shaped text detection method, namely TextRay, which conducts top-down contour-based geometric modeling and geometric parameter learning within a single-shot anchor-free framework. The geometric modeling is carried out under polar system with a bidirectional mapping scheme between shape space and parameter space, encoding complex geometric layouts into unified representations. For effective learning of the representations, we design a central-weighted training strategy and a content loss which builds propagation paths between geometric encodings and visual content. TextRay outputs simple polygon detections at one pass with only one NMS post-processing. Experiments on several benchmark datasets demonstrate the effectiveness of the proposed approach. The code is available at https://github.com/LianaWang/TextRay.

Fangfang Wang, Yifeng Chen, Fei Wu, Xi Li• 2020

Related benchmarks

TaskDatasetResultRank
Text DetectionCTW1500 (test)
Precision82.8
157
Text DetectionTotal-Text
Recall77.9
139
Text DetectionTotal-Text (test)
F-Measure80.6
126
Text DetectionCTW1500
F-measure81.6
70
Scene Text DetectionTotal-Text
Precision83.5
63
Scene Text DetectionArT ICDAR2019 (test)
Recall58.6
16
Text DetectionArT (test)
Recall58.6
4
Text DetectionCTW1500 highly-curved
Recall71.2
3
Showing 8 of 8 rows

Other info

Follow for update