# R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection

arXiv: https://arxiv.org/abs/1706.09579 · HTML: https://mlsanity.com/paper/1706.09579/

## Key facts

- Cited by 51 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jun 2017.

## Built on by (most cited first, 30 of 51)

- [Oriented R-CNN for Object Detection](https://mlsanity.com/paper/2108.05699/) (2021)
- [Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss](https://mlsanity.com/paper/2101.11952/) (2021)
- [Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence](https://mlsanity.com/paper/2106.01883/) (2021)
- [MMRotate: A Rotated Object Detection Benchmark using PyTorch](https://mlsanity.com/paper/2204.13317/) (2022)
- [Anchor-free Oriented Proposal Generator for Object Detection](https://mlsanity.com/paper/2110.01931/) (2021)
- [An Empirical Study of Remote Sensing Pretraining](https://mlsanity.com/paper/2204.02825/) (2022)
- [Oriented RepPoints for Aerial Object Detection](https://mlsanity.com/paper/2105.11111/) (2021)
- [The KFIoU Loss for Rotated Object Detection](https://mlsanity.com/paper/2201.12558/) (2022)
- [C2Former: Calibrated and Complementary Transformer for RGB-Infrared Object Detection](https://mlsanity.com/paper/2306.16175/) (2023)
- [ARS-DETR: Aspect Ratio-Sensitive Detection Transformer for Aerial Oriented Object Detection](https://mlsanity.com/paper/2303.04989/) (2023)
- [CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Images](https://mlsanity.com/paper/2101.06849/) (2021)
- [Optimization for Arbitrary-Oriented Object Detection via Representation Invariance Loss](https://mlsanity.com/paper/2103.11636/) (2021)
- [LR-FPN: Enhancing Remote Sensing Object Detection with Location Refined Feature Pyramid Network](https://mlsanity.com/paper/2404.01614/) (2024)
- [Oriented Object Detection with Transformer](https://mlsanity.com/paper/2106.03146/) (2021)
- [G-Rep: Gaussian Representation for Arbitrary-Oriented Object Detection](https://mlsanity.com/paper/2205.11796/) (2022)
- [A Multiplexed Network for End-to-End, Multilingual OCR](https://mlsanity.com/paper/2103.15992/) (2021)
- [RSDet++: Point-based Modulated Loss for More Accurate Rotated Object Detection](https://mlsanity.com/paper/2109.11906/) (2021)
- [Rethinking Boundary Discontinuity Problem for Oriented Object Detection](https://mlsanity.com/paper/2305.10061/) (2023)
- [Synthetic Map Generation to Provide Unlimited Training Data for Historical Map Text Detection](https://mlsanity.com/paper/2112.06104/) (2021)
- [MPDIoU: A Loss for Efficient and Accurate Bounding Box Regression](https://mlsanity.com/paper/2307.07662/) (2023)
- [Arbitrary-Oriented Ship Detection through Center-Head Point Extraction](https://mlsanity.com/paper/2101.11189/) (2021)
- [FIction: 4D Future Interaction Prediction from Video](https://mlsanity.com/paper/2412.00932/) (2024)
- [Anchor Retouching via Model Interaction for Robust Object Detection in Aerial Images](https://mlsanity.com/paper/2112.06701/) (2021)
- [AlphaRotate: A Rotation Detection Benchmark using TensorFlow](https://mlsanity.com/paper/2111.06677/) (2021)
- [Graph Fusion Network for Multi-Oriented Object Detection](https://mlsanity.com/paper/2205.03562/) (2022)
- [Learning Calibrated-Guidance for Object Detection in Aerial Images](https://mlsanity.com/paper/2103.11399/) (2021)
- [TS4Net: Two-Stage Sample Selective Strategy for Rotating Object Detection](https://mlsanity.com/paper/2108.03116/) (2021)
- [Multi-Grained Angle Representation for Remote Sensing Object Detection](https://mlsanity.com/paper/2209.02884/) (2022)
- [A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets](https://mlsanity.com/paper/2107.07927/) (2021)
- [Task Grouping for Multilingual Text Recognition](https://mlsanity.com/paper/2210.07423/) (2022)

## Abstract (arXiv)

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.