Adaptive Embedding Gate for Attention-Based Scene Text Recognition

08/26/2019
by   Xiaoxue Chen, et al.
3

Scene text recognition has attracted particular research interest because it is a very challenging problem and has various applications. The most cutting-edge methods are attentional encoder-decoder frameworks that learn the alignment between the input image and output sequences. In particular, the decoder recurrently outputs predictions, using the prediction of the previous step as a guidance for every time step. In this study, we point out that the inappropriate use of previous predictions in existing attention mechanisms restricts the recognition performance and brings instability. To handle this problem, we propose a novel module, namely adaptive embedding gate(AEG). The proposed AEG focuses on introducing high-order character language models to attention mechanism by controlling the information transmission between adjacent characters. AEG is a flexible module and can be easily integrated into the state-of-the-art attentional methods. We evaluate its effectiveness as well as robustness on a number of standard benchmarks, including the IIIT5K, SVT, SVT-P, CUTE80, and ICDAR datasets. Experimental results demonstrate that AEG can significantly boost recognition performance and bring better robustness.

READ FULL TEXT

page 2

page 3

page 4

page 5

page 6

page 7

page 8

page 10

research
07/15/2020

RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition

The attention-based encoder-decoder framework has recently achieved impr...
research
05/09/2018

Edit Probability for Scene Text Recognition

We consider the scene text recognition problem under the attention-based...
research
12/21/2019

Decoupled Attention Network for Text Recognition

Text recognition has attracted considerable research interests because o...
research
06/04/2018

NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition

Scene text recognition has attracted a great many researches for decades...
research
12/11/2017

Attention networks for image-to-text

The paper approaches the problem of image-to-text with attention-based e...
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
03/06/2019

A Character-Level Approach to the Text Normalization Problem Based on a New Causal Encoder

Text normalization is a ubiquitous process that appears as the first ste...

Please sign up or login with your details

Forgot password? Click here to reset