Handwritten image augmentation

TL;DR

This paper presents Handwritten augmentation, a data-driven technique for enhancing handwritten character image datasets by altering character shapes, improving CNN-based OCR model performance.

Contribution

It introduces a novel handwritten augmentation method that focuses on shape alterations, easily integrates with existing augmentations, and improves OCR accuracy.

Findings

Enhanced OCR model performance with handwritten augmentation

Compatible with common augmentation techniques like cropping and rotating

Simple to implement and data-driven

Abstract

In this paper, we introduce Handwritten augmentation, a new data augmentation for handwritten character images. This method focuses on augmenting handwritten image data by altering the shape of input characters in training. The proposed handwritten augmentation is similar to position augmentation, color augmentation for images but a deeper focus on handwritten characters. Handwritten augmentation is data-driven, easy to implement, and can be integrated with CNN-based optical character recognition models. Handwritten augmentation can be implemented along with commonly used data augmentation techniques such as cropping, rotating, and yields better performance of models for handwritten image datasets developed using optical character recognition methods.