• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.2
• /
• pp.73-78
• /
• 2021

Recently, as interest in deep learning has increased, many researches in various fields using deep learning techniques have been conducted. Studies on automatic generation of fonts using deep learning-based generation models are limited to several languages such as Roman or Chinese characters. Generating Korean font is a very time-consuming and expensive task, and can be easily created using deep learning. For research on generating Korean fonts, it is important to prepare a Korean font dataset from the viewpoint of process automation in order to keep pace with deep learning-based generation models. In this paper, we propose a Korean font dataset for deep learning-based Korean font research and describe a method of constructing the dataset. Based on the Korean font data set proposed in this paper, we show the usefulness of the proposed dataset configuration through the process of applying it to a deep learning Korean font generation application.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.79-87
• /
• 2021

In recent years research on automatic font generation with machine learning mainly focus on using transformation-based methods, in comparison, generative model-based methods of font generation have received less attention. Transformation-based methods learn a mapping of the transformations from an existing input to a target. This makes them ambiguous because in some cases a single input reference may correspond to multiple possible outputs. In this work, we focus on font generation using the generative model-based methods which learn the buildup of the characters from noise-to-image. We propose a novel way to train a conditional generative deep neural model so that we can achieve font style control on the generated font images. Our research demonstrates how to generate new font images conditioned on both character class labels and character style labels when using the generative model-based methods. We achieve this by introducing a modified generator network which is given inputs noise, character class, and style, which help us to calculate losses separately for the character class labels and character style labels. We show that adding the character style vector on top of the character class vector separately gives the model rich information about the font and enables us to explicitly specify not only the character class but also the character style that we want the model to generate.

• Journal of Korea Multimedia Society
• /
• v.23 no.7
• /
• pp.850-861
• /
• 2020

Hangul is a language that is composed of initial, medial, and final syllables. It has 11,172 characters. For this reason, the current method of designing all the characters by hand is very expensive and time-consuming. In order to solve the problem, this paper proposes an automatic Hangul font generation system and evaluates the standards for mapping Hangul characters to produce an effective automated Hangul font generation system. The system was implemented using character generation engine based on deep learning CycleGAN. In order to evaluate the criteria when mapping characters in pairs, each criterion was designed based on Hangul structure and character shape, and the quality of the generated characters was evaluated. As a result of the evaluation, the standards designed based on the Hangul structure did not affect the quality of the automated Hangul font generation system. On the other hand, when tried with similar characters, the standards made based on the shape of Hangul characters produced better quality characters than when tried with less similar characters. As a result, it is better to generate automated Hangul font by designing a learning method based on mapping characters in pairs that have similar character shapes.

• Journal of Korea Multimedia Society
• /
• v.24 no.8
• /
• pp.1184-1191
• /
• 2021

In a pop song, the creator's intention is communicated to the user through music and lyrics. Lyric meaning is as important as music, but in most cases lyrics are delivered to users in a static form without non-verbal cues. Providing lyrics in a static text format is inefficient in conveying the emotions of a music. Recently, lyrics video with kinetic typography are increasingly provided, but producing them requires expertise and a lot of time. Therefore, in this system, the emotions of the lyrics are found through the analysis of the text of the lyrics, and the deep learning model is trained with the data obtained by converting the melody into a Mel-spectrogram format to find the appropriate emotions for the music. It sets properties such as motion, font, and color using the emotions found in the music, and automatically creates a kinetic typography video. In this study, we tried to enhance the effect of conveying the meaning of music through this system.