# Scene Text Detection via Holistic, Multi-Channel Prediction

arXiv: https://arxiv.org/abs/1606.09002 · HTML: https://mlsanity.com/paper/1606.09002/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jun 2016.

## Built on by (most cited first, 11 of 11)

- [Fourier Contour Embedding for Arbitrary-Shaped Text Detection](https://mlsanity.com/paper/2104.10442/) (2021)
- [Towards Robust Real-Time Scene Text Detection: From Semantic to Instance Representation Learning](https://mlsanity.com/paper/2308.07202/) (2023)
- [Emerging Practices for Large Multimodal Model (LMM) Assistance for People with Visual Impairments: Implications for Design](https://mlsanity.com/paper/2407.08882/) (2024)
- [CBNet: A Plug-and-Play Network for Segmentation-Based Scene Text Detection](https://mlsanity.com/paper/2212.02340/) (2022)
- [A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets](https://mlsanity.com/paper/2107.07927/) (2021)
- [Conceptual Text Region Network: Cognition-Inspired Accurate Scene Text Detection](https://mlsanity.com/paper/2103.09179/) (2021)
- [EpiSAM: Character Segmentation in Challenging Stone Inscriptions](https://mlsanity.com/paper/2606.28859/) (2026)
- [MT: Multi-Perspective Feature Learning Network for Scene Text Detection](https://mlsanity.com/paper/2105.05455/) (2021)
- [Towards Detecting, Recognizing, and Parsing the Address Information from Bangla Signboard: A Deep Learning-based Approach](https://mlsanity.com/paper/2311.13222/) (2023)
- [ROSA: Addressing text understanding challenges in photographs via ROtated SAmpling](https://mlsanity.com/paper/2506.03665/) (2025)
- [Designing Production-Scale OCR for India: Multilingual and Domain-Specific Systems](https://mlsanity.com/paper/2602.16430/) (2026)

## Abstract (arXiv)

Recently, scene text detection has become an active research topic in computer vision and document analysis, because of its great importance and significant challenge. However, vast majority of the existing methods detect text within local regions, typically through extracting character, word or line level candidates followed by candidate aggregation and false positive elimination, which potentially exclude the effect of wide-scope and long-range contextual cues in the scene. To take full advantage of the rich information available in the whole natural image, we propose to localize text in a holistic manner, by casting scene text detection as a semantic segmentation problem. The proposed algorithm directly runs on full images and produces global, pixel-wise prediction maps, in which detections are subsequently formed. To better make use of the properties of text, three types of information regarding text region, individual characters and their relationship are estimated, with a single Fully Convolutional Network (FCN) model. With such predictions of text properties, the proposed algorithm can simultaneously handle horizontal, multi-oriented and curved text in real-world natural images. The experiments on standard benchmarks, including ICDAR 2013, ICDAR 2015 and MSRA-TD500, demonstrate that the proposed algorithm substantially outperforms previous state-of-the-art approaches. Moreover, we report the first baseline result on the recently-released, large-scale dataset COCO-Text.