• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권2호
• /
• pp.73-78
• /
• 2021

최근 딥러닝에 대한 관심이 증가하면서 이를 이용한 다양한 분야에서 연구가 진행되고 있다. 그러나 딥러닝 기반의 생성 모델을 이용하는 폰트의 자동 생성 연구들은 로마자 및 한자와 같은 몇 언어들에 국한되어 연구되고 있다. 한글 폰트 디자인은 매우 큰 시간과 비용이 들어가는 작업으로, 딥러닝을 이용하면 손쉽게 생성할 수 있다. 한글 폰트를 생성하는 연구는 딥러닝 기반의 생성 모델들과 발맞추기 위해 프로세스 자동화 관점에서 한글 폰트 데이터셋을 준비하는 것이 중요하다. 이를 위하여 본 논문에서는 딥러닝 기반의 한글 폰트 연구를 위한 한글 폰트 데이터셋을 제안하고. 그 데이터셋을 구성하는 방법을 기술한다. 본 논문에서 제안하는 한글 폰트 데이터셋을 기반으로 딥러닝 한글 폰트 생성 어플리케이션에 적용하는 과정을 통해 제안하는 데이터셋 구성의 유용성을 보인다.

• 스마트미디어저널
• /
• 제10권1호
• /
• 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.

• 한국멀티미디어학회논문지
• /
• 제23권7호
• /
• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권4호
• /
• pp.1166-1186
• /
• 2022

Artistic font design has become an integral part of visual media. However, without prior knowledge of the font domain, it is difficult to create distinct font styles. When the number of characters is limited, this task becomes easier (e.g., only Latin characters). However, designing CJK (Chinese, Japanese, and Korean) characters presents a challenge due to the large number of character sets and complexity of the glyph components in these languages. Numerous studies have been conducted on automating the font design process using generative adversarial networks (GANs). Existing methods rely heavily on reference fonts and perform font style conversions between different fonts. Additionally, rather than capturing style information for a target font via multiple style images, most methods do so via a single font image. In this paper, we propose a network architecture for generating multilingual font sets that makes use of geometric structures as content. Additionally, to acquire sufficient style information, we employ multiple style images belonging to a single font style simultaneously to extract global font style-specific information. By utilizing the geometric structural information of content and a few stylized images, our model can generate an entire font set while maintaining the style. Extensive experiments were conducted to demonstrate the proposed model's superiority over several baseline methods. Additionally, we conducted ablation studies to validate our proposed network architecture.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -2
• /
• pp.793-798
• /
• 2000

As we review the mechanism regarding digital font generation and birth of TrueType font, we realizes that the process is composed of sequential steps such as contour fonts from glyph table. This fact implies that we propose classification of TrueType font in terms of segment width and the number of occurrence from the glyph data.

• 전자공학회논문지A
• /
• 제29A권2호
• /
• pp.100-106
• /
• 1992

In this pape, we designed and implemented a hardware accelerator for the generation of bit map font from Hangul outline font description for LBP (Laser Beam Printer) and screen applications Whole system was implemented as a double size PC/AT application board which consists of processing bolck and display block. The processing block has a master processor (MC68000)and two slave processors which are MC56001 and KAFOG chip responsible for the short vector generation. In the display block, TMS34061 was used for monitor display and GP425 was used for LBP print out. The resolution of the monitor is 640$\times$480 and that of LBP is 2385$\times$3390. The current system called KHGB90-B generates about 100 characters per second where each character consists of 32$\times$32 bits

• 한국정보과학회논문지:시스템및이론
• /
• 제36권4호
• /
• pp.311-325
• /
• 2009

본 논문에서는 외곽선 폰트의 한글 글립을 분석하고 서로 다른 두 폰트에 대한 중간 폰트를 생성하는 방법을 제안한다. 한글 글립은 글자, 자소, 획과 같이 계층적으로 표현되고 분석된다. 글립 분석 결과를 바탕으로 같은 글자를 나타내는 서로 다른 두 글립에 대해서 모핑을 수행함으로써 여러 개의 중간글립들을 얻는다. 자연스러운 글립 외곽선 모핑을 위해 스트링의 가중 평균(weighted-mean)에 의한 커브모핑 방법을 사용하며, 위상이 다른 글립 간 변환을 위한 네 가지 연산을 제공한다. 제안된 한글 글립 모핑 방법은 기존의 폰트 또는 손글씨로 부터 새로운 폰트를 생성하는 데 사용될 수 있다.

• 전자공학회논문지B
• /
• 제28B권9호
• /
• pp.712-718
• /
• 1991

In this paper, we propose a graphic system for high speed generation of bitmap font data from the outline font data such as PostScript, etc. In desk-top publishing system. A VLSI chip called KAFOG was designed for the high-speed calculation of a cubic Bezier curve, which was implemented in 1.5\ulcorner CMOS gate array using 17,000 gates. A cubic Bezier curve is approximated by a set of line segments in KAFOG at the throughput of 250K curves per second with the clock frequency of 40 MHz. A prototype graphic system was developed using two MC6800 microprocessors and the KAFOG chip. Two microprocessors cooperate in a master and slave mode, and handshaking is used for communication between two processors. KAFOG chip, being controlled by the slave processor, operates as a coprocessor for the calculation of the outline font. The throughput of the prototype graphic system is 40 64$\times$64 outline fonts per sencond.

• 산업기술연구
• /
• 제11권
• /
• pp.55-63
• /
• 1991

This paper presents a design of the accelerate circuit for the conversion of the vector font data into the bit-mapped image. Among the Bezier curve algorithm, the subdivision algorithm gives the good performance and easy hardware implementation. The sequencer is realized by the proprammable gate array and the processing unit is composed of EPLDs and TTL ICs.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권11호
• /
• pp.473-482
• /
• 2021

최근 딥러닝을 이용한 한글 생성 모델이 연구되고 있으나, 한글 폰트의 구조가 복잡하고 많은 폰트 데이터가 필요하여 상당한 시간과 자원을 필요로 할 뿐 아니라 스타일이 제대로 변환되지 않는 경우도 발생한다. 이러한 문제점을 보완하기 위하여, 본 논문에서는 한글의 초성, 중성, 종성의 구성요소를 기반으로 최소 글자를 사용하는 한글 폰트 생성 모델인 CKFont 모델을 제안한다. CKFont 모델은 GAN을 사용하는 한글 자동 생성 모델로, 28개의 글자와 초/중/종성 구성요소를 이용하여 다양한 스타일의 모든 한글을 생성할 수 있다. 구성요소로부터 로컬 스타일 정보를 획득함으로써, 글로벌 정보 획득보다 정확하고 정보 손실을 줄일 수 있다. 실험 결과 스타일을 자연스럽게 변환되지 못하는 경우를 감소시키고 폰트의 품질이 향상되었다. 한글 폰트를 생성하는 다른 모델들과 비교하여, 본 연구에서 제안하는 CKFont는 최소 글자를 사용하는 모델로, 모델의 구조가 간결하여 폰트를 생성하는 시간과 자원이 절약되는 효율적인 모델이다. 구성요소를 이용하는 방법은 다른 언어 폰트의 변환은 물론 다양한 이미지 변환과 합성에도 사용될 수 있다.