2D Attentional Irregular Scene Text Recognizer

06/13/2019
by   Pengyuan Lyu, et al.
0

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.

READ FULL TEXT

page 5

page 8

page 10

page 11

research
09/18/2018

Scene Text Recognition from Two-Dimensional Perspective

Inspired by speech recognition, recent state-of-the-art algorithms mostl...
research
12/18/2018

Recurrent Calibration Network for Irregular Text Recognition

Scene text recognition has received increased attention in the research ...
research
02/10/2020

A New Perspective for Flexible Feature Gathering in Scene Text Recognition Via Character Anchor Pooling

Irregular scene text recognition has attracted much attention from the r...
research
02/04/2020

GTC: Guided Training of CTC Towards Efficient and Accurate Scene Text Recognition

Connectionist Temporal Classification (CTC) and attention mechanism are ...
research
11/02/2018

Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition

Recognizing irregular text in natural scene images is challenging due to...
research
07/21/2022

SGBANet: Semantic GAN and Balanced Attention Network for Arbitrarily Oriented Scene Text Recognition

Scene text recognition is a challenging task due to the complex backgrou...
research
03/25/2020

SCATTER: Selective Context Attentional Scene Text Recognizer

Scene Text Recognition (STR), the task of recognizing text against compl...

Please sign up or login with your details

Forgot password? Click here to reset