# STELA: A Real-Time Scene Text Detector with Learned Anchor

arXiv: https://arxiv.org/abs/1909.07549 · HTML: https://mlsanity.com/paper/1909.07549/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2019.

## Built on by (most cited first, 4 of 4)

- [Unified Chinese License Plate Detection and Recognition with High Efficiency](https://mlsanity.com/paper/2205.03582/) (2022)
- [Arbitrary Shape Text Detection using Transformers](https://mlsanity.com/paper/2202.11221/) (2022)
- [SamLP: A Customized Segment Anything Model for License Plate Detection](https://mlsanity.com/paper/2401.06374/) (2024)
- [Real-Time Text Detection with Similar Mask in Traffic, Industrial, and Natural Scenes](https://mlsanity.com/paper/2411.02794/) (2024)

## Abstract (arXiv)

To achieve high coverage of target boxes, a normal strategy of conventional one-stage anchor-based detectors is to utilize multiple priors at each spatial position, especially in scene text detection tasks. In this work, we present a simple and intuitive method for multi-oriented text detection where each location of feature maps only associates with one reference box. The idea is inspired from the twostage R-CNN framework that can estimate the location of objects with any shape by using learned proposals. The aim of our method is to integrate this mechanism into a onestage detector and employ the learned anchor which is obtained through a regression operation to replace the original one into the final predictions. Based on RetinaNet, our method achieves competitive performances on several public benchmarks with a totally real-time efficiency (26:5fps at 800p), which surpasses all of anchor-based scene text detectors. In addition, with less attention on anchor design, we believe our method is easy to be applied on other analogous detection tasks. The code will publicly available at https://github.com/xhzdeng/stela.