# TextCaps : Handwritten Character Recognition with Very Small Datasets

## TL;DR

This paper introduces a data augmentation technique for handwritten character recognition that significantly improves accuracy on small datasets, enabling effective recognition in low-resource languages.

## Contribution

The authors propose a realistic data augmentation method using controlled noise, enhancing recognition performance with very limited training samples.

## Key findings

- Outperforms existing methods on EMNIST-letter with only 200 samples per class
- Achieves state-of-the-art results on EMNIST-balanced, EMNIST-digits, and MNIST datasets
- Effective for low-resource languages and general object recognition tasks

## Abstract

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.