Arbitrary-Oriented Scene Text Detection via Rotation Proposals

Abstract

This paper introduces a novel rotation-based framework for arbitrary-oriented text detection in natural scene images. We present the Rotation Region Proposal Networks (RRPN), which are designed to generate inclined proposals with text orientation angle information. The angle information is then adapted for bounding box regression to make the proposals more accurately fit into the text region in terms of the orientation. The Rotation Region-of-Interest (RRoI) pooling layer is proposed to project arbitrary-oriented proposals to a feature map for a text region classifier. The whole framework is built upon a region-proposal-based architecture, which ensures the computational efficiency of the arbitrary-oriented text detection compared with previous text detection systems. We conduct experiments using the rotation-based framework on three real-world scene text detection datasets and demonstrate its superiority in terms of effectiveness and efficiency over previous approaches.

Code is available at: https://github.com/mjq11302010044/RRPN

References in corpus (1)

• Evolving Boxes for Fast Vehicle Detection

Cited by in corpus (45)

• Cell Detection with Star-convex Polygons
• A Survey of Deep Learning-based Object Detection
• Gliding vertex on the horizontal bounding box for multi-oriented object detection
• Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges
• Automatic Ship Detection of Remote Sensing Images from Google Earth in Complex Scenes Based on Multi-Scale Rotation Dense Feature Pyramid Networks
• Anchor-free Oriented Proposal Generator for Object Detection
• MMRotate: A Rotated Object Detection Benchmark using PyTorch
• Deep Learning for UAV-based Object Detection and Tracking: A Survey
• TextField: Learning A Deep Direction Field for Irregular Scene Text Detection
• CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Images
• An Empirical Study of Remote Sensing Pretraining
• ${\mathbf{C}}^2$Former: Calibrated and Complementary Transformer for RGB-Infrared Object Detection
• ARS-DETR: Aspect Ratio-Sensitive Detection Transformer for Aerial Oriented Object Detection
• LookOut: Diverse Multi-Future Prediction and Planning for Self-Driving
• PolarDet: A Fast, More Precise Detector for Rotated Target in Aerial Images
• G-Rep: Gaussian Representation for Arbitrary-Oriented Object Detection
• A Novel CNN-based Method for Accurate Ship Detection in HR Optical Remote Sensing Images via Rotated Bounding Box
• Adaptive Period Embedding for Representing Oriented Objects in Aerial Images
• Arbitrary-Oriented Ship Detection through Center-Head Point Extraction
• Oriented Bounding Boxes for Small and Freely Rotated Objects
• A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning
• Gaussian Bounding Boxes and Probabilistic Intersection-over-Union for Object Detection
• Industrial Scene Text Detection with Refined Feature-attentive Network
• PETDet: Proposal Enhancement for Two-Stage Fine-Grained Object Detection
• Oriented object detection in optical remote sensing images using deep learning: a survey
• Detecting Multi-Oriented Text with Corner-based Region Proposals
• CT-Net: Arbitrary-Shaped Text Detection via Contour Transformer
• Stroke-Based Scene Text Erasing Using Synthetic Data for Training
• TextDCT: Arbitrary-Shaped Text Detection via Discrete Cosine Transform Mask
• Precise Temporal Action Localization by Evolving Temporal Proposals
• Improving the Detection of Small Oriented Objects in Aerial Images
• MUS-CDB: Mixed Uncertainty Sampling with Class Distribution Balancing for Active Annotation in Aerial Object Detection
• Multi-Grained Angle Representation for Remote Sensing Object Detection
• CBNet: A Plug-and-Play Network for Segmentation-Based Scene Text Detection
• Video Text Tracking With a Spatio-Temporal Complementary Model
• Orientation Aware Weapons Detection In Visual Data : A Benchmark Dataset
• Arbitrary-Shaped Text Detection withAdaptive Text Region Representation
• Rotation Equivariant Feature Image Pyramid Network for Object Detection in Optical Remote Sensing Imagery
• On the Robustness of Object Detection Models on Aerial Images
• Selective Distillation of Weakly Annotated GTD for Vision-based Slab Identification System
• Anchor Retouching via Model Interaction for Robust Object Detection in Aerial Images
• DUET: Detection Utilizing Enhancement for Text in Scanned or Captured Documents
• Measuring Laser Beams with a Neural Network
• Tracking Based Semi-Automatic Annotation for Scene Text Videos
• Enhancing Rotated Object Detection via Anisotropic Gaussian Bounding Box and Bhattacharyya Distance