Accurate Text Localization in Natural Image with Cascaded Convolutional Text Network

TL;DR

This paper presents a cascaded convolutional network approach for accurate, efficient scene text detection in natural images, achieving high accuracy and robustness across languages and orientations.

Contribution

The novel CCTN framework combines coarse-to-fine localization with customized convolutions, improving robustness and efficiency over previous methods.

Findings

Achieves 0.84 and 0.86 F-measure on ICDAR 2011 and 2013 datasets.

Outperforms state-of-the-art results significantly.

Handles multi-shape, multi-scale, and multi-language text effectively.

Abstract

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].