A Glyph-driven Topology Enhancement Network for Scene Text Recognition

03/07/2022
by   Tongkun Guan, et al.
0

Attention-based methods by establishing one-dimensional (1D) and two-dimensional (2D) mechanisms with an encoder-decoder framework have dominated scene text recognition (STR) tasks due to their capabilities of building implicit language representations. However, 1D attention-based mechanisms suffer from alignment drift on latter characters. 2D attention-based mechanisms only roughly focus on the spatial regions of characters without excavating detailed topological structures, which reduces the visual performance. To mitigate the above issues, we propose a novel Glyph-driven Topology Enhancement Network (GTEN) to improve topological features representations in visual models for STR. Specifically, an unsupervised method is first employed to exploit 1D sequence-aligned attention weights. Second, we construct a supervised segmentation module to capture 2D ordered and pixel-wise topological information of glyphs without extra character-level annotations. Third, these resulting outputs fuse enhanced topological features to enrich semantic feature representations for STR. Experiments demonstrate that GTEN achieves competitive performance on IIIT5K-Words, Street View Text, ICDAR-series, SVT Perspective, and CUTE80 datasets.

READ FULL TEXT

page 2

page 3

page 4

page 8

research
12/28/2019

TextScanner: Reading Characters in Order for Robust Scene Text Recognition

Driven by deep learning and the large volume of data, scene text recogni...
research
07/15/2020

RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition

The attention-based encoder-decoder framework has recently achieved impr...
research
11/22/2021

CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition

The attention-based encoder-decoder framework is becoming popular in sce...
research
05/10/2021

Primitive Representation Learning for Scene Text Recognition

Scene text recognition is a challenging task due to diverse variations o...
research
12/11/2017

Attention networks for image-to-text

The paper approaches the problem of image-to-text with attention-based e...
research
05/09/2018

Edit Probability for Scene Text Recognition

We consider the scene text recognition problem under the attention-based...
research
06/10/2020

Why is Attention Not So Attentive?

Attention-based methods have played an important role in model interpret...

Please sign up or login with your details

Forgot password? Click here to reset