SKFont: skeleton-driven Korean font generator with conditional deep adversarial networks

Ko, Debbie Honghee; Hassan, Ammar Ul; Suk, Jungjae; Choi, Jaeyoung

doi:10.1007/s10032-021-00374-4

Cited by 5 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ko et al [12] proposed a method for font image skeletonization based on the pix2pix framework. Later, this method was extended as a three-stage stack network architecture for generating Korean Hangul fonts [11]. Some methods have also utilized Chinese character radicals for Chinese character recognition [13,14].…”

Section: Many-shot Font Generation Methodsmentioning

confidence: 99%

“…The style conversion of Chinese fonts remains a challenging task because of the large number of characters (70,224 characters, GB18010-2005) and complex shapes (some characters have more than 50 strokes) compared to Roman characters. Several models based on GAN [6,7] have recently been proposed and have demonstrated success in font synthesis tasks [8][9][10][11][12][22][23][24][25][26]. We divided these methods into two categories, many-shot and few-shot font generation methods, which are discussed in the next section.…”

Section: Related Workmentioning

confidence: 99%

“…For generating a new character, the GC-Module uses the CCFont training module to generate Chinese characters. Figure 2 depicts an example of Chinese To solve this problem, SKFont [11] proposed a three-stage network based on character image skeletonization [12] for generating Hangul font images. Additionally, the direct conversion of relatively simple components has also been attempted [13][14][15][16][17][18][19][20][21].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

CCFont: Component-Based Chinese Font Generation Model Using Generative Adversarial Networks (GANs)

2022

Self Cite

View full text Add to dashboard Cite

Font generation using deep learning has made considerable progress using image style transfer, but the automatic conversion/generation of Chinese characters still remains a difficult task owing to the complex character shape and large number of Chinese characters. Most known Chinese character generation models use the image conversion method of the Chinese character shape itself; however, it is difficult to reproduce complex Chinese characters. Recent methods have utilized character compositionality by separating up to three or four components to improve the quality of generated characters, but it is still difficult to generate high-quality results for complex Chinese characters with many components. In this study, we proposed the CCFont model (component-based Chinese font generation model using generative adversarial networks (GANs)) that automatically generates all Chinese characters using Chinese character components (up to 17 components). The CCFont model generates all Chinese characters in various styles using the components of Chinese characters based on conditional GAN. By acquiring local style information from the components, the information is more accurate and there is less information loss than when global information is obtained from the image of the entire character, reducing the failure of style conversion and improving quality to produce high-quality results. Additionally, the CCFont model generates high-quality results without any additional training (zero-shot font generation without any additional training) for the first-seen characters and styles. For example, the CCFont model, which was trained with only traditional Chinese (TC) characters, generates high-quality results for languages that can be divided into components, such as Korean and Thai, as well as simplified Chinese (SC) characters that are only seen during inference. CCFont can be adopted as a multi-lingual font-generation model that can be applied to all languages, which can be divided into components. To the best of our knowledge, the proposed method is the first to generate a zero-shot multilingual generation model using components. Qualitative and quantitative experiments were conducted to demonstrate the effectiveness of the proposed method.

show abstract

Section: Many-shot Font Generation Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

CCFont: Component-Based Chinese Font Generation Model Using Generative Adversarial Networks (GANs)

2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Certain methods were excluded from the comparison for specific reasons. First, we excluded methods that are not suitable for handling font styles that have not been seen before and would require extra adjustments, such as fine-tuning [2,3,7]. Second, we removed the non-generic models created for specific compositional writing systems [1].…”

Section: Baseline Evaluationmentioning

confidence: 99%

“…For example, the Korean language has 11,172 Hangul characters, and the Chinese language has over 50,000 Hanja characters. Recent advances in generative models have led to the development of new font synthesis methods [1][2][3][4][5][6][7][8][9] that use generative adversarial networks (GANs). These methods approach the font synthesis problem as an image-to-image translation task, with training in either a supervised setting with paired image data or a set level of supervision for font style labels [1][2][3][4][5][6][7][8][9].…”

Section: Introductionmentioning

confidence: 99%

FontFusionGAN: Refinement of Handwritten Fonts by Font Fusion

Kumar,

Kang,

Muhammad

et al. 2023

Electronics

Self Cite

View full text Add to dashboard Cite

Handwritten fonts possess unique expressive qualities; however, their clarity often suffers because of inconsistent handwriting. This study introduces FontFusionGAN (FFGAN), a novel method that enhances handwritten fonts by mixing them with printed fonts. The proposed approach leverages a generative adversarial network (GAN) to synthesize fonts that combine the desirable features of both handwritten and printed font styles. Training a GAN on a comprehensive dataset of handwritten and printed fonts enables it to produce legible and visually appealing font samples. The methodology was applied to a dataset of handwriting fonts, showing substantial enhancements in the legibility of the original fonts, while retaining their unique aesthetic essence. Unlike the original GAN setting where a single noise vector is used to generate a sample image, we randomly selected two noise vectors, z1 and z2, from a Gaussian distribution to train the generator. Simultaneously, we input a real image into the fusion encoder for exact reconstruction. This technique ensured the learning of style mixing during training. During inference, we provided the encoder with two font images, one handwritten and the other printed font, to obtain their respective latent vectors. Subsequently, the latent vector of the handwritten font image was injected into the first five layers of the generator, whereas the latent vector of the printed font image was injected into the last two layers to obtain a refined handwritten font image. The proposed method has the potential to improve the readability of handwritten fonts, offering benefits across diverse applications, such as document composition, letter writing, and assisting individuals with reading and writing difficulties.

show abstract