# Accurate Text Localization in Natural Image with Cascaded Convolutional Text Network

arXiv: https://arxiv.org/abs/1603.09423 · HTML: https://mlsanity.com/paper/1603.09423/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Mar 2016.

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

- [Industrial Scene Text Detection with Refined Feature-attentive Network](https://mlsanity.com/paper/2110.12663/) (2021)
- [Instruction-based Time Series Editing](https://mlsanity.com/paper/2508.01504/) (2025)
- [Weakly Supervised Scene Text Detection using Deep Reinforcement Learning](https://mlsanity.com/paper/2201.04866/) (2022)
- [ROSA: Addressing text understanding challenges in photographs via ROtated SAmpling](https://mlsanity.com/paper/2506.03665/) (2025)

## Abstract (arXiv)

We introduce a new top-down pipeline for scene text detection. We propose a novel Cascaded Convolutional Text Network (CCTN) that joints two customized convolutional networks for coarse-to-fine text localization. The CCTN fast detects text regions roughly from a low-resolution image, and then accurately localizes text lines from each enlarged region. We cast previous character based detection into direct text region estimation, avoiding multiple bottom- up post-processing steps. It exhibits surprising robustness and discriminative power by considering whole text region as detection object which provides strong semantic information. We customize convolutional network by develop- ing rectangle convolutions and multiple in-network fusions. This enables it to handle multi-shape and multi-scale text efficiently. Furthermore, the CCTN is computationally efficient by sharing convolutional computations, and high-level property allows it to be invariant to various languages and multiple orientations. It achieves 0.84 and 0.86 F-measures on the ICDAR 2011 and ICDAR 2013, delivering substantial improvements over state-of-the-art results [23, 1].