Easter2.0: Improving convolutional models for handwritten text recognition

05/30/2022
by   Kartik Chaudhary, et al.
4

Convolutional Neural Networks (CNN) have shown promising results for the task of Handwritten Text Recognition (HTR) but they still fall behind Recurrent Neural Networks (RNNs)/Transformer based models in terms of performance. In this paper, we propose a CNN based architecture that bridges this gap. Our work, Easter2.0, is composed of multiple layers of 1D Convolution, Batch Normalization, ReLU, Dropout, Dense Residual connection, Squeeze-and-Excitation module and make use of Connectionist Temporal Classification (CTC) loss. In addition to the Easter2.0 architecture, we propose a simple and effective data augmentation technique 'Tiling and Corruption (TACO)' relevant for the task of HTR/OCR. Our work achieves state-of-the-art results on IAM handwriting database when trained using only publicly available training data. In our experiments, we also present the impact of TACO augmentations and Squeeze-and-Excitation (SE) on text recognition accuracy. We further show that Easter2.0 is suitable for few-shot learning tasks and outperforms current best methods including Transformers when trained on limited amount of annotated data. Code and model is available at: https://github.com/kartikgill/Easter2

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/26/2021

StackMix and Blot Augmentations for Handwritten Text Recognition

This paper proposes a handwritten text recognition(HTR) system that outp...
research
04/12/2022

Back to the Roots: Reconstructing Large and Complex Cranial Defects using an Image-based Statistical Shape Model

Designing implants for large and complex cranial defects is a challengin...
research
06/10/2019

BDNet: Bengali handwritten numeral digit recognition based on densely connected convolutional neural networks

Bengali handwritten digit recognition can be done using different image ...
research
12/24/2019

Multi-Graph Transformer for Free-Hand Sketch Recognition

Learning meaningful representations of free-hand sketches remains a chal...
research
02/07/2023

Hebbian and Gradient-based Plasticity Enables Robust Memory and Rapid Learning in RNNs

Rapidly learning from ongoing experiences and remembering past events wi...
research
03/05/2023

A Study of Augmentation Methods for Handwritten Stenography Recognition

One of the factors limiting the performance of handwritten text recognit...
research
01/12/2018

How to augment a small learning set for improving the performances of a CNN-based steganalyzer?

Deep learning and convolutional neural networks (CNN) have been intensiv...

Please sign up or login with your details

Forgot password? Click here to reset