2D Attentional Irregular Scene Text Recognizer

TL;DR

This paper introduces a novel 2D attentional framework for recognizing irregular scene text directly from 2D layouts, improving robustness and accuracy over previous methods that rely on 1D transformations.

Contribution

The proposed method uniquely employs a 2D attentional scheme with relation and parallel attention modules to directly recognize irregular scene text from 2D features.

Findings

Outperforms previous methods in accuracy

Achieves higher speed in recognition

Effective on both regular and irregular text datasets

Abstract

Irregular scene text, which has complex layout in 2D space, is challenging to most previous scene text recognizers. Recently, some irregular scene text recognizers either rectify the irregular text to regular text image with approximate 1D layout or transform the 2D image feature map to 1D feature sequence. Though these methods have achieved good performance, the robustness and accuracy are still limited due to the loss of spatial information in the process of 2D to 1D transformation. Different from all of previous, we in this paper propose a framework which transforms the irregular text with 2D layout to character sequence directly via 2D attentional scheme. We utilize a relation attention module to capture the dependencies of feature maps and a parallel attention module to decode all characters in parallel, which make our method more effective and efficient. Extensive experiments on several public benchmarks as well as our collected multi-line text dataset show that our approach is effective to recognize regular and irregular scene text and outperforms previous methods both in accuracy and speed.