# Geometry Normalization Networks for Accurate Scene Text Detection

arXiv: https://arxiv.org/abs/1909.00794 · HTML: https://mlsanity.com/paper/1909.00794/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Sep 2019.

## Built on by (most cited first, 10 of 10)

- [Fourier Contour Embedding for Arbitrary-Shaped Text Detection](https://mlsanity.com/paper/2104.10442/) (2021)
- [MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding](https://mlsanity.com/paper/2108.06543/) (2021)
- [MOST: A Multi-Oriented Scene Text Detector with Localization Refinement](https://mlsanity.com/paper/2104.01070/) (2021)
- [Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detection](https://mlsanity.com/paper/2109.03426/) (2021)
- [Vision-Language Pre-Training for Boosting Scene Text Detectors](https://mlsanity.com/paper/2204.13867/) (2022)
- [Detection and Rectification of Arbitrary Shaped Scene Texts by using Text Keypoints and Links](https://mlsanity.com/paper/2103.00785/) (2021)
- [Attention-based Feature Decomposition-Reconstruction Network for Scene Text Detection](https://mlsanity.com/paper/2111.14340/) (2021)
- [Semi-supervised Large-scale Fiber Detection in Material Images with Synthetic Data](https://mlsanity.com/paper/2302.05541/) (2023)
- [Adaptive Segmentation Network for Scene Text Detection](https://mlsanity.com/paper/2307.15029/) (2023)
- [MENTOR: Multilingual tExt detectioN TOward leaRning by analogy](https://mlsanity.com/paper/2403.07286/) (2024)

## Abstract (arXiv)

Large geometry (e.g., orientation) variances are the key challenges in the scene text detection. In this work, we first conduct experiments to investigate the capacity of networks for learning geometry variances on detecting scene texts, and find that networks can handle only limited text geometry variances. Then, we put forward a novel Geometry Normalization Module (GNM) with multiple branches, each of which is composed of one Scale Normalization Unit and one Orientation Normalization Unit, to normalize each text instance to one desired canonical geometry range through at least one branch. The GNM is general and readily plugged into existing convolutional neural network based text detectors to construct end-to-end Geometry Normalization Networks (GNNets). Moreover, we propose a geometry-aware training scheme to effectively train the GNNets by sampling and augmenting text instances from a uniform geometry variance distribution. Finally, experiments on popular benchmarks of ICDAR 2015 and ICDAR 2017 MLT validate that our method outperforms all the state-of-the-art approaches remarkably by obtaining one-forward test F-scores of 88.52 and 74.54 respectively.