Handwriting Recognition in Low-resource Scripts using Adversarial Learning

11/04/2018
by   Ayan Kumar Bhunia, et al.
0

Handwritten Word Recognition and Spotting is a challenging field dealing with handwritten text possessing irregular and complex shapes. Designing models using deep neural networks makes it necessary to extend datasets in order to introduce variances and increase the number of training samples; word-retrieval is therefore very difficult in low-resource scripts. Much of the existing literature use preprocessing strategies which are seldom sufficient to cover all possible variations. We propose the Adversarial Feature Deformation Module that learns ways to elastically warp extracted features in a scalable manner. It is inserted between intermediate layers and trained alternatively with the original framework, boosting its capability to better learn highly informative features rather than trivial ones. We test our meta-framework which is built on top of popular spotting and recognition frameworks and enhanced by the AFDM not only on extensive Latin word datasets, but on sparser Indic scripts too. We record results for varying training data sizes, and observe that our enhanced network generalizes much better in the low-data regime; the overall word-error rates and mAP scores are observed to improve as well.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/19/2017

Cross-language Framework for Word Recognition and Spotting of Indic Scripts

Handwritten word recognition and spotting of low-resource scripts are di...
research
02/15/2017

Transfer Deep Learning for Low-Resource Chinese Word Segmentation with a Novel Neural Network

Recent studies have shown effectiveness in using neural networks for Chi...
research
07/10/2018

Deep Learning on Low-Resource Datasets

In training a deep learning system to perform audio transcription, two p...
research
07/10/2018

Deep Learning for Audio Transcription on Low-Resource Datasets

In training a deep learning system to perform audio transcription, two p...
research
07/13/2018

Low-Resource Text Classification using Domain-Adversarial Learning

Deep learning techniques have recently shown to be successful in many na...
research
11/17/2021

Green CWS: Extreme Distillation and Efficient Decode Method Towards Industrial Application

Benefiting from the strong ability of the pre-trained model, the researc...

Please sign up or login with your details

Forgot password? Click here to reset