TextRay: Contour-based Geometric Modeling for Arbitrary-shaped Scene Text Detection
arXiv:2008.04851
Abstract
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.
arXiv commentAccepted to ACM MM 2020
References in corpus (10)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- TextField: Learning A Deep Direction Field for Irregular Scene Text Detection
- Spatial As Deep: Spatial CNN for Traffic Scene Understanding
- Scene Text Detection via Holistic, Multi-Channel Prediction
- A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning
- PolarMask: Single Shot Instance Segmentation with Polar Representation
- ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network
- Dense RepPoints: Representing Visual Objects with Dense Point Sets
- Geometry Normalization Networks for Accurate Scene Text Detection