R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection

Abstract

In this paper, we propose a novel method called Rotational Region CNN (R2CNN) for detecting arbitrary-oriented texts in natural scene images. The framework is based on Faster R-CNN [1] architecture. First, we use the Region Proposal Network (RPN) to generate axis-aligned bounding boxes that enclose the texts with different orientations. Second, for each axis-aligned text box proposed by RPN, we extract its pooled features with different pooled sizes and the concatenated features are used to simultaneously predict the text/non-text score, axis-aligned box and inclined minimum area box. At last, we use an inclined non-maximum suppression to get the detection results. Our approach achieves competitive results on text detection benchmarks: ICDAR 2015 and ICDAR 2013.

arXiv comment8 pages, 6 figures, 3 tables

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Robust Text Detection in Natural Scene Images
• TextBoxes: A Fast Text Detector with a Single Deep Neural Network
• EAST: An Efficient and Accurate Scene Text Detector
• DeepText: A Unified Framework for Text Proposal Generation and Text Detection in Natural Images
• Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection
• Deep Direct Regression for Multi-Oriented Scene Text Detection
• TextProposals: a Text-specific Selective Search Algorithm for Word Spotting in the Wild

Cited by in corpus (80)

• TextBoxes++: A Single-Shot Oriented Scene Text Detector
• Automatic Ship Detection of Remote Sensing Images from Google Earth in Complex Scenes Based on Multi-Scale Rotation Dense Feature Pyramid Networks
• Object Detection in 20 Years: A Survey
• Anchor-free Oriented Proposal Generator for Object Detection
• MMRotate: A Rotated Object Detection Benchmark using PyTorch
• CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Images
• Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence
• An Empirical Study of Remote Sensing Pretraining
• Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss
• ${\mathbf{C}}^2$Former: Calibrated and Complementary Transformer for RGB-Infrared Object Detection
• R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object
• SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated Objects
• ARS-DETR: Aspect Ratio-Sensitive Detection Transformer for Aerial Oriented Object Detection
• Optimization for Arbitrary-Oriented Object Detection via Representation Invariance Loss
• Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks
• Scene Text Detection and Recognition: The Deep Learning Era
• PolarDet: A Fast, More Precise Detector for Rotated Target in Aerial Images
• LO-Det: Lightweight Oriented Object Detection in Remote Sensing Images
• Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation
• Learning Modulated Loss for Rotated Object Detection
• Character Region Awareness for Text Detection
• Pyramid Mask Text Detector
• UnrealText: Synthesizing Realistic Scene Text Images from the Unreal World
• Detecting Multi-Oriented Text with Corner-based Region Proposals
• Shape Robust Text Detection with Progressive Scale Expansion Network
• IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection
• Objects detection for remote sensing images based on polar coordinates
• Task-wise Sampling Convolutions for Arbitrary-Oriented Object Detection in Aerial Images
• Improving the Detection of Small Oriented Objects in Aerial Images
• Pixel-Anchor: A Fast Oriented Scene Text Detector with Combined Networks
• Sliding Line Point Regression for Shape Robust Scene Text Detection
• Text Detection and Recognition in the Wild: A Review
• Dynamic Anchor Learning for Arbitrary-Oriented Object Detection
• Towards Unconstrained End-to-End Text Spotting
• FGSD: A Dataset for Fine-Grained Ship Detection in High Resolution Satellite Images
• A pooling based scene text proposal technique for scene text reading in the wild
• Linear Gaussian Bounding Box Representation and Ring-Shaped Rotated Convolution for Oriented Object Detection
• Quantifying Legibility of Indoor Spaces Using Deep Convolutional Neural Networks: Case Studies in Train Stations
• Multi-Grained Angle Representation for Remote Sensing Object Detection
• TextMountain: Accurate Scene Text Detection via Instance Segmentation
• Dense Label Encoding for Boundary Discontinuity Free Rotation Detection
• PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments
• Arbitrary-Shaped Text Detection withAdaptive Text Region Representation
• Dynamic Refinement Network for Oriented and Densely Packed Object Detection
• Geometry Normalization Networks for Accurate Scene Text Detection
• A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets
• Oriented RepPoints for Aerial Object Detection
• Mask R-CNN with Pyramid Attention Network for Scene Text Detection
• Convolutional Character Networks
• Oriented Object Detection in Aerial Images with Box Boundary-Aware Vectors
• Oriented Boxes for Accurate Instance Segmentation
• FOTS: Fast Oriented Text Spotting with a Unified Network
• MRDet: A Multi-Head Network for Accurate Oriented Object Detection in Aerial Images
• SynthText3D: Synthesizing Scene Text Images from 3D Virtual Worlds
• You Only Recognize Once: Towards Fast Video Text Spotting
• 3D Object Detection From LiDAR Data Using Distance Dependent Feature Extraction
• Sketch2code: Generating a website from a paper mockup
• AlphaRotate: A Rotation Detection Benchmark using TensorFlow
• RRPN++: Guidance Towards More Accurate Scene Text Detection
• Oriented R-CNN for Object Detection
• TextNet: Irregular Text Reading from Images with an End-to-End Trainable Network
• X-LineNet: Detecting Aircraft in Remote Sensing Images by a pair of Intersecting Line Segments
• Learning Orientation-Estimation Convolutional Neural Network for Building Detection in Optical Remote Sensing Image
• Tracking Based Semi-Automatic Annotation for Scene Text Videos
• AON: Towards Arbitrarily-Oriented Text Recognition
• Object Detection based on OcSaFPN in Aerial Images with Noise
• Location-Aware Feature Selection Text Detection Network
• Oriented Objects as pairs of Middle Lines
• Probabilistic Oriented Object Detection in Automotive Radar
• TextTubes for Detecting Curved Text in the Wild
• Towards Spatio-Temporal Video Scene Text Detection via Temporal Clustering
• Scene Text Detection with Selected Anchor
• STELA: A Real-Time Scene Text Detector with Learned Anchor
• DGST : Discriminator Guided Scene Text detector
• A DCNN-based Arbitrarily-Oriented Object Detector for Quality Control and Inspection Application
• Learning to Predict More Accurate Text Instances for Scene Text Detection
• Towards Pure End-to-End Learning for Recognizing Multiple Text Sequences from an Image
• TextContourNet: a Flexible and Effective Framework for Improving Scene Text Detection Architecture with a Multi-task Cascade
• Accurate Scene Text Detection through Border Semantics Awareness and Bootstrapping
• A Multiplexed Network for End-to-End, Multilingual OCR