Alchemy: Techniques for Rectification Based Irregular Scene Text Recognition

08/30/2019
by   Shangbang Long, et al.
Carnegie Mellon University
Peking University
4

Reading text from natural images is challenging due to the great variety in text font, color, size, complex background and etc.. The perspective distortion and non-linear spatial arrangement of characters make it further difficult. While rectification based method is intuitively grounded and has pushed the envelope by far, its potential is far from being well exploited. In this paper, we present a bag of tricks that prove to significantly improve the performance of rectification based method. On curved text dataset, our method achieves an accuracy of 89.6 previous state-of-the-art by 6.3 combination of tricks helps us win the ICDAR 2019 Arbitrary-Shaped Text Challenge (Latin script), achieving an accuracy of 74.3 set. We release our code as well as data samples for further exploration at https://github.com/Jyouhou/ICDAR2019-ArT-Recognition-Alchemy

READ FULL TEXT

page 5

page 6

page 8

12/10/2019

A Feasible Framework for Arbitrary-Shaped Scene Text Recognition

Deep learning based methods have achieved surprising progress in Scene T...
09/16/2019

ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT)

This paper reports the ICDAR2019 Robust Reading Challenge on Arbitrary-S...
03/12/2016

Robust Scene Text Recognition with Automatic Rectification

Recognizing text in natural images is a challenging task with many unsol...
08/29/2019

Focus-Enhanced Scene Text Recognition with Deformable Convolutions

Recently, scene text recognition methods based on deep learning have spr...
06/01/2023

FigGen: Text to Scientific Figure Generation

The generative modeling landscape has experienced tremendous growth in r...
08/06/2019

Symmetry-constrained Rectification Network for Scene Text Recognition

Reading text in the wild is a very challenging task due to the diversity...
07/17/2023

Revisiting Scene Text Recognition: A Data Perspective

This paper aims to re-assess scene text recognition (STR) from a data-or...

Please sign up or login with your details

Forgot password? Click here to reset