請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/8453完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 許永真(Yung-Jen Hsu) | |
| dc.contributor.author | Shan-Jean Wu | en |
| dc.contributor.author | 吳尚真 | zh_TW |
| dc.date.accessioned | 2021-05-20T00:54:49Z | - |
| dc.date.available | 2025-07-01 | |
| dc.date.available | 2021-05-20T00:54:49Z | - |
| dc.date.copyright | 2020-07-20 | |
| dc.date.issued | 2020 | |
| dc.date.submitted | 2020-07-14 | |
| dc.identifier.citation | [1] G. Atarsaikhan, B. K. Iwana, A. Narusawa, K. Yanai, and S. Uchida. Neural font style transfer. In 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), volume 5, pages 51–56. IEEE, 2017. [2] B. Chang, Q. Zhang, S. Pan, and L. Meng. Generating handwritten chinese characters using cyclegan. In 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pages 199–207. IEEE, 2018. [3] J. Chang, Y. Gu, Y. Zhang, and Y.-F. Wang. Chinese handwriting imitation with hierarchical generative adversarial network. In BMVC, page 290, 2018. [4] Y. Choi, M. Choi, M. Kim, J.-W. Ha, S. Kim, and J. Choo. StarGAN: Unified generative adversarial networks for multi-domain image-to-image translation. In CVPR, 2018. [5] V. Dumoulin, J. Shlens, and M. Kudlur. A learned representation for artistic style. arXiv preprint arXiv:1610.07629, 2016. [6] L. A. Gatys, A. S. Ecker, and M. Bethge. Image style transfer using convolutional neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2414–2423, 2016. [7] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio. Generative adversarial nets. In Advances in neural information processing systems, pages 2672–2680, 2014. [8] K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016. [9] G. E. Hinton, S. Osindero, and Y.-W. Teh. A fast learning algorithm for deep belief nets. Neural computation, 18(7):1527–1554, 2006. [10] G. E. Hinton and R. R. Salakhutdinov. Reducing the dimensionality of data with neural networks. science, 313(5786):504–507, 2006. [11] G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger. Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4700–4708, 2017. [12] X. Huang and S. Belongie. Arbitrary style transfer in real-time with adaptive instance normalization. In Proceedings of the IEEE International Conference on Computer Vision, pages 1501–1510, 2017. [13] P. Isola, J.-Y. Zhu, T. Zhou, and A. A. Efros. Image-to-image translation with conditional adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1125–1134, 2017. [14] Y. Jiang, Z. Lian, Y. Tang, and J. Xiao. Dcfont: an end-to-end deep chinese font generation system. In SIGGRAPH Asia 2017 Technical Briefs, pages 1–4. 2017. [15] Y. Jiang, Z. Lian, Y. Tang, and J. Xiao. Scfont: Structure-guided chinese font generation via deep stacked networks. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 4015–4022, 2019. [16] J. Johnson, A. Alahi, and L. Fei-Fei. Perceptual losses for real-time style transfer and super-resolution. In European conference on computer vision, pages 694–711. Springer, 2016. [17] T. Kim, M. Cha, H. Kim, J. K. Lee, and J. Kim. Learning to discover cross-domain relations with generative adversarial networks. In Proceedings of the 34th International Conference on Machine Learning-Volume 70, pages 1857-1865. JMLR. org, 2017. [18] D. P. Kingma and J. Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014. [19] D. P. Kingma and M. Welling. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114, 2013. [20] Z. Lian, B. Zha, and J. Xiao. Automatic generation of large-scale handwriting fonts via style learning. In SIGGRAPH Asia, 2016. [21] C.-L. Liu, F. Yin, D.-H. Wang, and Q.-F. Wang. Casia online and offline chinese handwriting databases. In 2011 International Conference on Document Analysis and Recognition, pages 37–41. IEEE, 2011. [22] M.-Y. Liu, T. Breuel, and J. Kautz. Unsupervised image-to-image translation networks. In Advances in neural information processing systems, pages 700–708, 2017. [23] P. Lyu, X. Bai, C. Yao, Z. Zhu, T. Huang, and W. Liu. Auto-encoder guided GAN for Chinese calligraphy synthesis. In ICDAR, 2017. [24] M. Mirza and S. Osindero. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784, 2014. [25] A. Odena, C. Olah, and J. Shlens. Conditional image synthesis with auxiliary classifier gans. In Proceedings of the 34th International Conference on Machine Learning-Volume 70, pages 2642–2651. JMLR. org, 2017. [26] A. Radford, L. Metz, and S. Chintala. Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434, 2015. [27] O. Ronneberger, P. Fischer, and T. Brox. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, pages 234–241. Springer, 2015. [28] K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014. [29] D. Sun, T. Ren, C. Li, H. Su, and J. Zhu. Learning to write stylized chinese characters by reading a handful of examples. arXiv preprint arXiv:1712.06424, 2017. [30] D. Sun, Q. Zhang, and J. Yang. Pyramid embedded generative adversarial network for automated font generation. In 2018 24th International Conference on Pattern Recognition (ICPR), pages 976–981. IEEE, 2018. [31] Y. Taigman, A. Polyak, and L. Wolf. Unsupervised cross-domain image generation. arXiv preprint arXiv:1611.02200, 2016. [32] Y. Tian. zi2zi: Master chinese calligraphy with conditional adversarial networks. https://kaonashi-tyc.github.io/2017/04/06/zi2zi.html, 2017. [33] D. Ulyanov, V. Lebedev, A. Vedaldi, and V. S. Lempitsky. Texture networks: Feedforward synthesis of textures and stylized images. In ICML, volume 1, page 4, 2016. [34] Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli. Image quality assessment: from error visibility to structural similarity. TIP, 13(4):600–612, 2004. [35] C. Wen, J. Chang, and Y. Zhang. Handwritten chinese font generation with collaborative stroke refinement. arXiv preprint arXiv:1904.13268, 2019. [36] S. Xu, H. Jiang, T. Jin, F. C. Lau, and Y. Pan. Automatic generation of chinese calligraphic writings with style imitation. IEEE Intelligent Systems, (2):44–53, 2009. Gong. Dualgan: Unsupervised dual learning for image-to-image translation. In Proceedings of the IEEE international conference on computer vision, pages 2849–2857, 2017. [40] Y. Zhang, Y. Zhang, and W. Cai. Separating style and content for generalized style transfer. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 8447–8455, 2018. [41] J.-Y. Zhu, T. Park, P. Isola, and A. A. Efros. Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE international conference on computer vision, pages 2223–2232, 2017. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/8453 | - |
| dc.description.abstract | 書法 (Calligraphy) 是用毛筆在紙上書寫文字的方法，一種書寫的藝術，在生活當中也有許多應用情境。然而，許多書法作品常因為時間的流逝而有所損毀，進而造成學習者與設計者使用上的困擾。因此，書法字的生成是一個重要的問題。 近年來，許多影像轉譯 (image-to-image translation) 的研究已經能夠利用生成對抗網路(generative adversarial network)的方法，從具有場域標記的資料中，學習場域之間的關係，建立複雜的生成模型，將普通的中文字轉譯成具書法風格的中文字。甚至使用單一模型，生成多種不同書法風格。然而，大多數的方法並沒有有效利用中文字本身具有的結構資訊。 本篇論文提出了一種新的方法，將中文字的結構資訊融入到模型中，藉此幫助生成更好的影像。 我們實驗在三種不同的資料集上，並採用質性與量化分析，結果均顯示此方法生成的影像優於先前的方法。 | zh_TW |
| dc.description.abstract | Chinese calligraphy is the writing of Chinese characters as an art form performed with brushes so Chinese characters are rich of shapes and details. Recent studies show that Chinese characters can be generated through image-to-image translation for multiple styles using a single model. We propose a novel method of this approach by incorporating Chinese characters' component information into its model. We also propose an improved network to convert characters to their embedding space. Experiments show that the proposed method generates high-quality Chinese calligraphy characters over state-of-the-art methods measured through numerical evaluations and human subject studies. | en |
| dc.description.provenance | Made available in DSpace on 2021-05-20T00:54:49Z (GMT). No. of bitstreams: 1 U0001-1307202017054000.pdf: 3741148 bytes, checksum: 27adc204a4eda6d89019d115b04bb38a (MD5) Previous issue date: 2020 | en |
| dc.description.tableofcontents | Acknowledgments i Abstract ii List of Figures vii List of Tables ix Chapter 1 Introduction 1 1.1 Background . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.2 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 1.3 Objective . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 1.4 Outline of the Thesis . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 Chapter 2 Related Work 6 2.1 Generative Adversarial Network . . . . . . . . . . . . . . . . . . . . . 6 2.1.1 Deep Convolutional Generative Adversarial Networks . . . . . 7 2.1.2 Conditional Generative Adversarial Network . . . . . . . . . . 8 2.1.3 Auxiliary Classifier Generative Adversarial Network . . . . . . 8 2.2 Image-to-Image Translation . . . . . . . . . . . . . . . . . . . . . . . 9 2.2.1 Neural Network Based Style Transfer . . . . . . . . . . . . . . 9 2.2.2 GAN Based Paired Image-to-Image Translation . . . . . . . . 10 2.2.3 GAN Based Unpaired Image-to-Image Translation . . . . . . . 10 2.3 Chinese Characters Generation . . . . . . . . . . . . . . . . . . . . . 11 2.3.1 Chinese Calligraphy Generation . . . . . . . . . . . . . . . . . 12 2.3.2 Chinese Handwriting Generation . . . . . . . . . . . . . . . . 12 2.3.3 Chinese Font Generation . . . . . . . . . . . . . . . . . . . . . 13 Chapter 3 Methodology 15 3.1 Problem Definition . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 3.2 Symbols Table . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 3.3 Proposed Method . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 3.3.1 Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 3.3.2 Image Encoder and Decoder . . . . . . . . . . . . . . . . . . . 19 3.3.3 Component Encoder . . . . . . . . . . . . . . . . . . . . . . . 19 3.3.4 Discriminator and Auxiliary Style Classifier . . . . . . . . . . 22 3.3.5 Losses . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22 Chapter 4 Experiments 24 4.1 Data Sets . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24 4.1.1 Regular Script Dataset . . . . . . . . . . . . . . . . . . . . . . 25 4.1.2 Clerical Script Dataset . . . . . . . . . . . . . . . . . . . . . . 26 4.1.3 TrueType Font Dataset . . . . . . . . . . . . . . . . . . . . . . 27 4.1.4 Data Processing . . . . . . . . . . . . . . . . . . . . . . . . . . 29 4.2 Training Detail . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30 4.3 Evaluation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30 4.3.1 Evaluation Metrics . . . . . . . . . . . . . . . . . . . . . . . . 30 4.3.2 Experimental Results . . . . . . . . . . . . . . . . . . . . . . . 30 4.3.3 Effect of Component Embedding Layer . . . . . . . . . . . . . 33 4.3.4 Human Subject Study . . . . . . . . . . . . . . . . . . . . . . 36 4.3.5 Comparison with AEGG . . . . . . . . . . . . . . . . . . . . . 37 4.4 Further Analysis of Component Encoder . . . . . . . . . . . . . . . . 39 4.4.1 Choice of RNN model . . . . . . . . . . . . . . . . . . . . . . 39 4.4.2 Choice of Component Codes’ Embedding Dimension . . . . . . 42 Chapter 5 Conclusion 44 5.1 Summary of Contributions . . . . . . . . . . . . . . . . . . . . . . . . 44 5.2 Future Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45 Bibliography 47 | |
| dc.language.iso | en | |
| dc.title | 具風格與結構意識的中文書法生成器 | zh_TW |
| dc.title | CalliGAN: Style and Structure-aware Chinese Calligraphy Character Generator | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 108-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 梁容輝(Rung-Huei Liang),王鈺強(Yu-Chiang Wang),李明穗(Ming-Sui Lee),楊智淵(Chih-Yuan Yang) | |
| dc.subject.keyword | 風格轉換,對抗式生成網路,多場域影像轉譯, | zh_TW |
| dc.subject.keyword | Style Transfer,Generative Adversarial Network,Image-to-Image Translation, | en |
| dc.relation.page | 51 | |
| dc.identifier.doi | 10.6342/NTU202001478 | |
| dc.rights.note | 同意授權(全球公開) | |
| dc.date.accepted | 2020-07-14 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊網路與多媒體研究所 | zh_TW |
| dc.date.embargo-lift | 2025-07-01 | - |
| 顯示於系所單位： | 資訊網路與多媒體研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-1307202017054000.pdf | 3.65 MB | Adobe PDF | 檢視/開啟 |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。