# DeepText: A Unified Framework for Text Proposal Generation and Text Detection in Natural Images

arXiv: https://arxiv.org/abs/1605.07314 · HTML: https://mlsanity.com/paper/1605.07314/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 May 2016.

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

- [Towards Weakly-Supervised Text Spotting using a Multi-Task Transformer](https://mlsanity.com/paper/2202.05508/) (2022)
- [Research on Fast Text Recognition Method for Financial Ticket Image](https://mlsanity.com/paper/2101.01310/) (2021)
- [Weakly Supervised Scene Text Detection using Deep Reinforcement Learning](https://mlsanity.com/paper/2201.04866/) (2022)
- [GloTSFormer: Global Video Text Spotting Transformer](https://mlsanity.com/paper/2401.03694/) (2024)

## Abstract (arXiv)

In this paper, we develop a novel unified framework called DeepText for text region proposal generation and text detection in natural images via a fully convolutional neural network (CNN). First, we propose the inception region proposal network (Inception-RPN) and design a set of text characteristic prior bounding boxes to achieve high word recall with only hundred level candidate proposals. Next, we present a powerful textdetection network that embeds ambiguous text category (ATC) information and multilevel region-of-interest pooling (MLRP) for text and non-text classification and accurate localization. Finally, we apply an iterative bounding box voting scheme to pursue high recall in a complementary manner and introduce a filtering algorithm to retain the most suitable bounding box, while removing redundant inner and outer boxes for each text instance. Our approach achieves an F-measure of 0.83 and 0.85 on the ICDAR 2011 and 2013 robust text detection benchmarks, outperforming previous state-of-the-art results.