DeepAI AI Chat
Log In Sign Up

TextCaps : Handwritten Character Recognition with Very Small Datasets

04/17/2019
by   Vinoj Jayasundara, et al.
The University of Sydney
University of Moratuwa
0

Many localized languages struggle to reap the benefits of recent advancements in character recognition systems due to the lack of substantial amount of labeled training data. This is due to the difficulty in generating large amounts of labeled data for such languages and inability of deep learning techniques to properly learn from small number of training samples. We solve this problem by introducing a technique of generating new training samples from the existing samples, with realistic augmentations which reflect actual variations that are present in human hand writing, by adding random controlled noise to their corresponding instantiation parameters. Our results with a mere 200 training samples per class surpass existing character recognition results in the EMNIST-letter dataset while achieving the existing results in the three datasets: EMNIST-balanced, EMNIST-digits, and MNIST. We also develop a strategy to effectively use a combination of loss functions to improve reconstructions. Our system is useful in character recognition for localized languages that lack much labeled training data and even in other related more general contexts such as object recognition.

READ FULL TEXT

page 3

page 7

page 8

04/08/2020

MNIST-MIX: A Multi-language Handwritten Digit Recognition Dataset

In this letter, we contribute a multi-language handwritten digit recogni...
01/02/2018

Learning audio and image representations with bio-inspired trainable feature extractors

Recent advancements in pattern recognition and signal processing concern...
08/25/2018

How many labeled license plates are needed?

Training a good deep learning model often requires a lot of annotated da...
03/06/2022

Capsule Networks for Character Recognition in Low Resource Languages

Most of the existing techniques in handwritten character recognition are...
03/30/2010

Recognition of handwritten Roman Numerals using Tesseract open source OCR engine

The objective of the paper is to recognize handwritten samples of Roman ...
01/01/2016

Discriminative Sparsity for Sonar ATR

Advancements in Sonar image capture have enabled researchers to apply so...