TextTubes for Detecting Curved Text in the Wild
arXiv:1912.08990
Abstract
We present a detector for curved text in natural images. We model scene text instances as tubes around their medial axes and introduce a parametrization-invariant loss function. We train a two-stage curved text detector, and evaluate it on the curved text benchmarks CTW-1500 and Total-Text. Our approach achieves state-of-the-art results or improves upon them, notably for CTW-1500 by over 8 percentage points in F-score.
References in corpus (14)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- TextBoxes++: A Single-Shot Oriented Scene Text Detector
- Robust Text Detection in Natural Scene Images
- R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection
- Feature Pyramid Networks for Object Detection
- TextBoxes: A Fast Text Detector with a Single Deep Neural Network
- YOLO9000: Better, Faster, Stronger
- The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale
- COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images
- Detecting Curve Text in the Wild: New Dataset and New Solution
- Multi-Oriented Text Detection with Fully Convolutional Networks
- IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection
- Sliding Line Point Regression for Shape Robust Scene Text Detection
- Fused Text Segmentation Networks for Multi-oriented Scene Text Detection