HOME > Detail View

Detail View

Typeface completion with generative adversarial networks

Typeface completion with generative adversarial networks

Material type
학위논문
Personal Author
박용규 朴龍圭
Title Statement
Typeface completion with generative adversarial networks / Yonggyu Park
Publication, Distribution, etc
Seoul :   Graduate School, Korea University,   2019  
Physical Medium
vi, 35장 : 삽화(일부천연색) ; 26 cm
기타형태 저록
Typeface Completion with Generative Adversarial Networks   (DCOLL211009)000000084648  
학위논문주기
학위논문(석사)-- 고려대학교 대학원: 컴퓨터·전파통신공학과, 2019. 8
학과코드
0510   6D36   1101  
General Note
지도교수: 강재우  
Bibliography, Etc. Note
참고문헌: 장 32-35
이용가능한 다른형태자료
PDF 파일로도 이용가능;   Requires PDF file reader(application/pdf)  
비통제주제어
MachineLearning , GenerativeAdversarialNetwork,,
000 00000nam c2200205 c 4500
001 000045999329
005 20191017133054
007 ta
008 190624s2019 ulka bmAC 000c eng
040 ▼a 211009 ▼c 211009 ▼d 211009
085 0 ▼a 0510 ▼2 KDCP
090 ▼a 0510 ▼b 6D36 ▼c 1101
100 1 ▼a 박용규 ▼g 朴龍圭
245 1 0 ▼a Typeface completion with generative adversarial networks / ▼d Yonggyu Park
260 ▼a Seoul : ▼b Graduate School, Korea University, ▼c 2019
300 ▼a vi, 35장 : ▼b 삽화(일부천연색) ; ▼c 26 cm
500 ▼a 지도교수: 강재우
502 0 ▼a 학위논문(석사)-- ▼b 고려대학교 대학원: ▼c 컴퓨터·전파통신공학과, ▼d 2019. 8
504 ▼a 참고문헌: 장 32-35
530 ▼a PDF 파일로도 이용가능; ▼c Requires PDF file reader(application/pdf)
653 ▼a MachineLearning ▼a GenerativeAdversarialNetwork
776 0 ▼t Typeface Completion with Generative Adversarial Networks ▼w (DCOLL211009)000000084648
900 1 0 ▼a Park, Yong-gyu, ▼e
900 1 0 ▼a 강재우 ▼g 姜在雨, ▼e 지도교수
945 ▼a KLPA

Electronic Information

No. Title Service
1
Typeface completion with generative adversarial networks (13회 열람)
View PDF Abstract Table of Contents

Holdings Information

No. Location Call Number Accession No. Availability Due Date Make a Reservation Service
No. 1 Location Science & Engineering Library/Stacks(Thesis)/ Call Number 0510 6D36 1101 Accession No. 123062333 Availability Available Due Date Make a Reservation Service B M
No. 2 Location Science & Engineering Library/Stacks(Thesis)/ Call Number 0510 6D36 1101 Accession No. 123062334 Availability Available Due Date Make a Reservation Service B M

Contents information

Abstract

The mood of a text and the intention of the writer can be reflected in the typeface.
However, in designing a typeface, it is difficult to keep the style of various characters consistent, especially for languages with lots of morphological variations such as Chinese.
In this paper, we propose a Typeface Completion Network (TCN) which takes one character as an input, and automatically completes the entire set of characters in the same style as the input characters.
Unlike existing models proposed for image-to-image translation, TCN embeds a character image into two separate vectors representing typeface and content.
Combined with a reconstruction loss from the latent space, and with other various losses, TCN overcomes the inherent difficulty in designing a typeface.
Also, compared to previous image-to-image translation models, TCN generates high quality character images of the same typeface with a much smaller number of model parameters.
We validate our proposed model on the Chinese and English character datasets, which is paired data, and the CelebA dataset, which is unpaired data. 
In these datasets, TCN outperforms recently proposed state-of-the-art models for image-to-image translation.
The source code of our model is available at https://github.com/yongqyu/TCN.

Table of Contents

Abstract
Contents
List of Figures
List of Tables
1. Introduction
2. Related Works
2.1. Image-to-Image Translation
2.2. Character Image Generation
3. Task Definition
4. Proposed Model
4.1. Encoders
4.1.1. Typeface and Content Feature
4.1.2. Encoder Pretraining
4.2. Generator
4.2.1. Feature Combination
4.2.2. Image Generation
4.3. Discriminator
4.4 Training Process
4.4.1. Identity Loss
4.4.2. SSIM Loss
4.4.3. Adversarial Losses
4.4.4. Reconstruction Loss
4.4.5. Perceptual Reconstruction Loss
4.4.6. Discriminator Loss
4.5. Test Process
5. Evaluation
5.1. Datasets
5.1.1. Chinese Character
5.1.2. English Character
5.2. Metrics
5.2.1. SSIM
5.2.2. L1 distance
5.2.3. Classification Accuracy
5.3. Implementation Details
5.4. Baselines
5.4.1. CycleGAN
5.4.2. MUNIT
5.4.3. StarGAN
5.5. Experiment
5.5.1. Typeface Completion
5.5.2. Character Reconstruction
5.5.3. Ablation Study
5.5.4. Face Generation
6. Analyze
7. Conclusion

New Arrivals Books in Related Fields