On the Ability of a CNN to Realize Image-to-Image Language Conversion

TL;DR

This paper demonstrates that CNNs can perform image-to-image language conversion, specifically converting Korean Hangul characters into Latin phonetic symbols, even with limited data, by capturing structural features.

Contribution

It introduces a novel CNN architecture tailored for image-to-image language conversion tasks with significantly different input and output features.

Findings

CNN can successfully convert Hangul to Latin characters

The network captures structural features with limited data

The proposed network handles different feature spaces effectively

Abstract

The purpose of this paper is to reveal the ability that Convolutional Neural Networks (CNN) have on the novel task of image-to-image language conversion. We propose a new network to tackle this task by converting images of Korean Hangul characters directly into images of the phonetic Latin character equivalent. The conversion rules between Hangul and the phonetic symbols are not explicitly provided. The results of the proposed network show that it is possible to perform image-to-image language conversion. Moreover, it shows that it can grasp the structural features of Hangul even from limited learning data. In addition, it introduces a new network to use when the input and output have significantly different features.