• KIISE Transactions on Computing Practices
• /
• v.22 no.9
• /
• pp.449-454
• /
• 2016

Radicals of Korean characters consist of some strokes, and complete letters are comprised of a combination of radicals. During the process of combining strokes and radicals, it requires a lot of effort as the size and the position of the components can be changed. Unlike this, METAFONT can improve the efficiency in the production process of fonts by changing its parameters. It also provides a system which can easily transform size and position of the strokes and radicals. We propose a structural Korean font generator which allows users to modify parameters of letters through METAFONT and generates a variety of fonts automatically. The suggested Korean font generator can be applied to font embedding and font editor.

• Journal of Information Processing Systems
• /
• v.17 no.1
• /
• pp.1-13
• /
• 2021

In this research, we study the problem of font image skeletonization using an end-to-end deep adversarial network, in contrast with the state-of-the-art methods that use mathematical algorithms. Several studies have been concerned with skeletonization, but a few have utilized deep learning. Further, no study has considered generative models based on deep neural networks for font character skeletonization, which are more delicate than natural objects. In this work, we take a step closer to producing realistic synthesized skeletons of font characters. We consider using an end-to-end deep adversarial network, SkelGAN, for font-image skeletonization, in contrast with the state-of-the-art methods that use mathematical algorithms. The proposed skeleton generator is proved superior to all well-known mathematical skeletonization methods in terms of character structure, including delicate strokes, serifs, and even special styles. Experimental results also demonstrate the dominance of our method against the state-of-the-art supervised image-to-image translation method in font character skeletonization task.

• 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.

• KIISE Transactions on Computing Practices
• /
• v.24 no.2
• /
• pp.88-92
• /
• 2018

'UFO2MF' and 'Korean MetaFont Generator' have been developed to convert UFO codes to the corresponding Metafont codes by using outline editing methods. However, 'UFO2MF' cannot express smooth curves because it use only reference points without using control points. And 'Korean MetaFont Generator' can easily design the curve of characters, and supports Hangul characters, but this system does not support Roman characters. In this paper, we propose a UFO2xMF system, which can convert both Korean and Roman characters from outline text information into Metafont codes. UFO2xMF can apply attribute values which can change the shape of letters during the conversion of Metafont code. It is also a highly compatible system that can convert the characters of various languages not only Korean characters but also Roman and other characters into Metafont codes by applying letters with baseline and centerline of gravity.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.04a
• /
• pp.1013-1014
• /
• 2015

본 논문에서는 한글 글꼴의 기본 구성요소인 자소를 자동 생성하는 기법을 기반하여 한글의 전체 글꼴을 효율적으로 제작할 수 있는 글꼴 에디터를 개발한다. 본 글꼴 에디터에서는 몇 개의 기본 자소만을 설계하고 나면 KSX1001 표준한글 2350자 및 Unicode 표준한글 11172자 문자들을 자동생성할 수 있다. 이를 이용하여 한글 서체의 디자인 작업 시간을 크게 줄일 수 있었다.

• Journal of the Korean Society of Industry Convergence
• /
• v.24 no.6_2
• /
• pp.699-706
• /
• 2021

Existing license plate recognition system is used as an optical character recognition method, but a method of using deep learning has been proposed in recent studies because it has problems with image quality and Korean misrecognition. This requires a lot of data collection, but the collection of license plates is not easy to collect due to the problem of the Personal Information Protection Act, and labeling work to designate the location of individual license plates is required, but it also requires a lot of time. Therefore, in this paper, to solve this problem, five types of license plates were created using a virtual Korean license plate generation program according to the notice of the Ministry of Land, Infrastructure and Transport. And the generated license plate is synthesized in the license plate part of collectable vehicle images to construct 10,147 learning data to be used in deep learning. The learning data classifies license plates, Korean, and numbers into individual classes and learn using YOLOv5. Since the proposed method recognizes letters and numbers individually, if the font does not change, it can be recognized even if the license plate standard changes or the number of characters increases. As a result of the experiment, an accuracy of 96.82% was obtained, and it can be applied not only to the learned license plate but also to new types of license plates such as new license plates and eco-friendly license plates.

• Journal of Korea Multimedia Society
• /
• v.13 no.4
• /
• pp.609-617
• /
• 2010

Since Korean mobile communication companies each use different mobile platforms, developers must configure and translate their game contents to run under each of the platforms so that they can be serviced correctly. Nevertheless, such translation tasks require lengthy times and costs. This is one of the reasons why a variety of contents could not be provided. In order to mitigate such difficulty, this paper implemented an automatic mobile contents translating system that automatically translates mobile C game contents of the GNEX platform to mobile java contents of the WIPI platform. The GNEX C-to-WIPI Java automatic contents translation system helps minimize the amount of time and cost required in servicing contents to different mobile communication companies by promptly translating a platform-specific-content to run under other platforms. Also, the automatic translation and servicing of existing contents increases the reusability of these contents and also the productivity of new contents thereby offering users with a more variety of games.