On the Ability of a CNN to Realize Image-to-Image Language Conversion
This addresses a specific problem in cross-lingual image processing, but it appears incremental as it applies existing CNN techniques to a new task.
The paper tackled the novel task of image-to-image language conversion by developing a CNN-based network that converts images of Korean Hangul characters directly into images of phonetic Latin equivalents without explicit conversion rules. The results demonstrate that the network can perform this conversion and grasp Hangul's structural features from limited data.
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.