Performance Evaluation of Deep Generative Models for Generating Hand-Written Character Images

TL;DR

This paper evaluates and compares different deep generative models, including auto-encoders and GANs, for generating handwritten character images, demonstrating their potential to augment datasets for improved recognition accuracy.

Contribution

The study provides a comparative analysis of various deep generative models on handwritten character datasets, including Indonesian BALI language, highlighting their effectiveness in data augmentation.

Findings

Auto-encoders and GANs can generate realistic handwritten characters.

Generated characters improve recognition performance.

GANs outperform auto-encoders in quality of generated images.

Abstract

There have been many work in the literature on generation of various kinds of images such as Hand-Written characters (MNIST dataset), scene images (CIFAR-10 dataset), various objects images (ImageNet dataset), road signboard images (SVHN dataset) etc. Unfortunately, there have been very limited amount of work done in the domain of document image processing. Automatic image generation can lead to the enormous increase of labeled datasets with the help of only limited amount of labeled data. Various kinds of Deep generative models can be primarily divided into two categories. First category is auto-encoder (AE) and the second one is Generative Adversarial Networks (GANs). In this paper, we have evaluated various kinds of AE as well as GANs and have compared their performances on hand-written digits dataset (MNIST) and also on historical hand-written character dataset of Indonesian BALI language. Moreover, these generated characters are recognized by using character recognition tool for calculating the statistical performance of these generated characters with respect to original character images.