Scene Text Recognition from Two-Dimensional Perspective

TL;DR

This paper introduces CA-FCN, a two-dimensional fully convolutional network for scene text recognition that effectively handles arbitrary-shaped text by leveraging semantic segmentation and attention mechanisms, outperforming previous methods.

Contribution

The paper proposes a novel 2D perspective for scene text recognition using CA-FCN, which improves accuracy and robustness over traditional sequence-based methods.

Findings

Outperforms previous methods on regular and irregular text datasets.

More robust to imprecise localizations in text detection.

Effective recognition of arbitrary-shaped text.

Abstract

Inspired by speech recognition, recent state-of-the-art algorithms mostly consider scene text recognition as a sequence prediction problem. Though achieving excellent performance, these methods usually neglect an important fact that text in images are actually distributed in two-dimensional space. It is a nature quite different from that of speech, which is essentially a one-dimensional signal. In principle, directly compressing features of text into a one-dimensional form may lose useful information and introduce extra noise. In this paper, we approach scene text recognition from a two-dimensional perspective. A simple yet effective model, called Character Attention Fully Convolutional Network (CA-FCN), is devised for recognizing the text of arbitrary shapes. Scene text recognition is realized with a semantic segmentation network, where an attention mechanism for characters is adopted. Combined with a word formation module, CA-FCN can simultaneously recognize the script and predict the position of each character. Experiments demonstrate that the proposed algorithm outperforms previous methods on both regular and irregular text datasets. Moreover, it is proven to be more robust to imprecise localizations in the text detection phase, which are very common in practice.