Adaptive Text Recognition through Visual Matching

09/14/2020
by   Chuhan Zhang, et al.
7

In this work, our objective is to address the problems of generalization and flexibility for text recognition in documents. We introduce a new model that exploits the repetitive nature of characters in languages, and decouples the visual representation learning and linguistic modelling stages. By doing this, we turn text recognition into a shape matching problem, and thereby achieve generalization in appearance and flexibility in classes. We evaluate the new model on both synthetic and real datasets across different alphabets and show that it can handle challenges that traditional architectures are not able to solve without expensive retraining, including: (i) it can generalize to unseen fonts without new exemplars from them; (ii) it can flexibly change the number of classes, simply by changing the exemplars provided; and (iii) it can generalize to new languages and new characters that it has not been trained for by providing a new glyph set. We show significant improvements over state-of-the-art models for all these cases.

READ FULL TEXT

page 15

page 16

page 17

page 18

page 20

page 21

page 25

page 26

research
03/10/2022

Towards Open-Set Text Recognition via Label-to-Prototype Learning

Scene text recognition is a popular topic and can benefit various tasks....
research
12/26/2021

Continuous Offline Handwriting Recognition using Deep Learning Models

Handwritten text recognition is an open problem of great interest in the...
research
07/20/2016

Sequence to sequence learning for unconstrained scene text recognition

In this work we present a state-of-the-art approach for unconstrained na...
research
05/24/2023

MRN: Multiplexed Routing Network for Incremental Multilingual Text Recognition

Traditional Multilingual Text Recognition (MLTR) usually targets a fixed...
research
01/10/2022

Transfer Learning for Scene Text Recognition in Indian Languages

Scene text recognition in low-resource Indian languages is challenging b...
research
05/29/2017

Pose-Aware Person Recognition

Person recognition methods that use multiple body regions have shown sig...
research
08/06/2023

Towards Scene-Text to Scene-Text Translation

In this work, we study the task of “visually" translating scene text fro...

Please sign up or login with your details

Forgot password? Click here to reset