# Pyramid Mask Text Detector

arXiv: https://arxiv.org/abs/1903.11800 · HTML: https://mlsanity.com/paper/1903.11800/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Mar 2019.

## Built on by (most cited first, 9 of 9)

- [LGPMA: Complicated Table Structure Recognition with Local and Global Pyramid Mask Alignment](https://mlsanity.com/paper/2105.06224/) (2021)
- [MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding](https://mlsanity.com/paper/2108.06543/) (2021)
- [Arbitrary Shape Text Detection via Segmentation with Probability Maps](https://mlsanity.com/paper/2208.12419/) (2022)
- [All You Need is a Second Look: Towards Arbitrary-Shaped Text Detection](https://mlsanity.com/paper/2106.12720/) (2021)
- [CORE-Text: Improving Scene Text Detection with Contrastive Relational Reasoning](https://mlsanity.com/paper/2112.07513/) (2021)
- [Text Detection & Recognition in the Wild for Robot Localization](https://mlsanity.com/paper/2205.08565/) (2022)
- [OSKDet: Towards Orientation-sensitive Keypoint Localization for Rotated Object Detection](https://mlsanity.com/paper/2104.08697/) (2021)
- [StrokeNet: Stroke Assisted and Hierarchical Graph Reasoning Networks](https://mlsanity.com/paper/2111.11718/) (2021)
- [Efficiently Leveraging Linguistic Priors for Scene Text Spotting](https://mlsanity.com/paper/2402.17134/) (2024)

## Abstract (arXiv)

Scene text detection, an essential step of scene text recognition system, is to locate text instances in natural scene images automatically. Some recent attempts benefiting from Mask R-CNN formulate scene text detection task as an instance segmentation problem and achieve remarkable performance. In this paper, we present a new Mask R-CNN based framework named Pyramid Mask Text Detector (PMTD) to handle the scene text detection. Instead of binary text mask generated by the existing Mask R-CNN based methods, our PMTD performs pixel-level regression under the guidance of location-aware supervision, yielding a more informative soft text mask for each text instance. As for the generation of text boxes, PMTD reinterprets the obtained 2D soft mask into 3D space and introduces a novel plane clustering algorithm to derive the optimal text box on the basis of 3D shape. Experiments on standard datasets demonstrate that the proposed PMTD brings consistent and noticeable gain and clearly outperforms state-of-the-art methods. Specifically, it achieves an F-measure of 80.13% on ICDAR 2017 MLT dataset.