JZUS - Journal of Zhejiang University SCIENCE

Frontiers of Information Technology & Electronic Engineering

Accepted manuscript available online (unedited version)

Visual knowledge guided intelligent generation of Chinese seal carving

Author(s): Kejun ZHANG, Rui ZHANG, Yehang YIN, Yifei LI, Wenqi WU, Lingyun SUN, Fei WU, Huanghuang DENG, Yunhe PAN
Affiliation(s): College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China; more
Corresponding email(s): zhangkejun@zju.edu.cn, zhang_rui@zju.edu.cn, panyh@zju.edu.cn
Key Words: Seal-carving; Intelligent generation; Deep learning; Parametric modeling; Computational art

Share this article to： More <<< Previous Paper \|Next Paper >>>

Abstract: We digitally reproduce the process of resource collaboration, design creation, and visual presentation of Chinese seal-carving art. We develop an intelligent seal-carving art-generation system (Zhejiang University Intelligent Seal-Carving System, http://www.next.zju.edu.cn/seal/; the website of the seal-carving search and layout system is http://www.next.zju.edu.cn/seal/search_app/) to deal with the difficulty in using a visual knowledge guided computational art approach. The knowledge base in this study is the Qiushi Seal-Carving Database, which consists of open datasets of images of seal characters and seal stamps. We propose a seal character generation method based on visual knowledge, guided by the database and expertise. Furthermore, to create the layout of the seal, we propose a deformation algorithm to adjust the seal characters and calculate layout parameters from the database and knowledge to achieve an intelligent structure. Experimental results show that this method and system can effectively deal with the difficulties in the generation of seal carving. Our work provides theoretical and applied references for the rebirth and innovation of seal-carving art.

视觉知识引导的中国篆刻智能化生成

张克俊^1,2，张瑞¹，殷叶航¹，李一非³，伍文棋¹，孙凌云^1,2，吴飞¹，邓晃煌¹，潘云鹤¹
¹浙江大学计算机科学与技术学院，中国杭州市，310027
²浙江大学―阿里巴巴前沿技术联合研究中心，中国杭州市，310027
³浙江大学软件学院，中国杭州市，310027
摘要：本文将传统篆刻艺术中的资源协同、设计创作、视觉呈现等过程以数字化方式再现，研制了篆刻艺术智能化创作的系统和平台（浙江大学智能篆刻系统：http://www.next.zju.edu.cn/seal/；篆刻搜索排版系统：http://www.next.zju.edu.cn/seal/search_app/），以视觉知识为引导突破计算机艺术学面临的难点问题。本文构建了包含字和印的求是篆刻数据库，并以此为视觉知识库，构建了篆字智能生成算法。此外，为创建印章布局，提出一种篆字变形算法调整印章字符，并结合视觉知识实现智能篆字布局，以实现智能结构。实验结果表明本文所提方法和系统可有效解决篆刻艺术生成中的难点问题，为篆刻艺术的守正与创新提供理论与应用借鉴。

关键词组：篆刻；智能生成；深度学习；参数化模型；计算机艺术

Reference

[1]Baxter B, Scheib V, Lin MC, et al., 2001. DAB: interactive haptic painting with 3D virtual brushes. Proc 28^th Annual Conf on Computer Graphics and Interactive Techniques, p.461-468.

[2]Bi XF, Tang M, Lin JZ, et al., 2003. An experience based virtual brush model. J Comput Res Dev, 40(8):1244-1251 (in Chinese).

[3]Chang B, Zhang Q, Pan SY, et al., 2018. Generating handwritten Chinese characters using CycleGAN. IEEE Winter Conf on Applications of Computer Vision, p.199-207.

[4]Chang J, Gu YJ, Zhang Y, et al., 2018. Chinese handwriting imitation with hierarchical generative adversarial network. British Machine Vision Conf, Article 290.

[5]Chen YS, 1995. Computer processing on the identification of a Chinese seal image. Proc 3^rd Int Conf on Document Analysis and Recognition, p.422-425.

[6]Chen YS, 1996. Automatic identification for a Chinese seal image. Patt Recogn, 29(11):1807-1820.

[7]Chu NSH, Tai CL, 2004. Real-time painting with an expressive virtual Chinese brush. IEEE Comput Graph Appl, 24(5):76-85.

[8]Chu NSH, Tai CL, 2005. MoXi: real-time ink dispersion in absorbent paper. ACM Trans Graph, 24(3):504-511.

[9]Dong J, Xu M, Pan YH, 2008. Statistic model-based simulation on calligraphy creation. Chin J Comput, 31(7):1276-1282 (in Chinese).

[10]Fan TJ, Tsai WH, 1984. Automatic Chinese seal identification. Comput Vis Graph Image Process, 25(3):311-330.

[11]FontLab, 2020. FontLab 7. https://www.fontlab.com/ [Accessed on Jan. 1, 2021].

[12]Founder Group, 2020. FounderType. http://www.foundertype.com/ [Accessed on Jan. 1, 2021].

[13]Girshick RB, 2004. Simulating Chinese brush painting: the parametric hairy brush. ACM SIGGRAPH, Article 22.

[14]Glyphs, 2020. Glyphs. https://glyphsapp.com/ [Accessed on Jan. 1, 2021].

[15]Gu ZL, 2013. Eight Lectures on the Basis of Seal Cutting. Shanghai Painting and Calligraphy Publishing House, China (in Chinese).

[16]Guo QL, Kunii TL, 1991. Modeling the diffuse paintings of ‘Sumie’. In: Kunii TL (Ed.), Modeling in Computer Graphics. IFIP Series on Computer Graphics. Springer, Tokyo.

[17]High-Logic, 2020. High-Logic. https://www.high-logic.com/ [Accessed on Jan. 1, 2021].

[18]Huang D, 1999. Zhongguo Lidai Yinfeng. Chongqing Press, Chongqing, China (in Chinese).

[19]Isola P, Zhu JY, Zhou TH, et al., 2017. Image-to-image translation with conditional adversarial networks. IEEE Conf on Computer Vision and Pattern Recognition, p.5967-5976.

[20]Jiang Y, Lian ZH, Tang YM, et al., 2017. DCFont: an end-to-end deep Chinese font generation system. SIGGRAPH, Article 22.

[21]Jiang Y, Lian ZH, Tang YM, et al., 2019. SCFont: structure-guided Chinese font generation via deep stacked networks. Proc AAAI Conf on Artificial Intelligence, p.4015-4022.

[22]Lee J, 1999. Simulating oriental black-ink painting. IEEE Comput Graph Appl, 19(3):74-81.

[23]Leung H, 2004. Analysis of traditional Chinese seals and synthesis of personalized seals. IEEE Int Conf on Multimedia and Expo, p.1283-1286.

[24]Li GT, Ma SD, 2009. Zhuankexue. Jiangsu Education Publishing House, China (in Chinese).

[25]Li W, Song YP, Zhou CL, 2014. Computationally evaluating and synthesizing Chinese calligraphy. Neurocomputing, 135:299-305.

[26]Lian ZH, Xiao JG, 2012. Automatic shape morphing for Chinese characters. SIGGRAPH, p.1-4.

[27]Lian ZH, Zhao B, Chen XD, et al., 2018. EasyFont: a style learning-based system to easily build your large-scale handwriting fonts. ACM Trans Graph, 38(1):6.

[28]Lin JW, Wang CY, Ting CL, et al., 2014. Font generation of personal handwritten Chinese characters. Proc 5^th Int Conf on Graphic and Image Processing, Article 90691T.

[29]Lin JW, Hong CY, Chang RI, et al., 2015. Complete font generation of Chinese characters in personal handwriting style. IEEE 34^th Int Performance Computing and Communications Conf, p.1-5.

[30]Liu J, 2010. Zhuanke Changyongzi Zidian. Xiling Yinshe, China (in Chinese).

[31]Lu JW, Barnes C, DiVerdi S, et al., 2013. RealBrush: painting with examples of physical media. ACM Trans Graph, 32(4):117.

[32]Lyu PY, Bai X, Yao C, et al., 2017. Auto-encoder guided GAN for Chinese calligraphy synthesis. 14^th IAPR Int Conf on Document Analysis and Recognition, p.1095-1100.

[33]Mi XF, Xu J, Tang M, et al., 2002. The droplet virtual brush for Chinese calligraphic character modeling. Proc 6^th IEEE Workshop on Applications of Computer Vision, p.330-334.

[34]Pan YH, 2019. On visual knowledge. Front Inform Technol Electron Eng, 20(8):1021-1025.

[35]Pan YH, 2021. Miniaturized five fundamental issues about visual knowledge. Front Inform Technol Electron Eng, 22(5):615-618.

[36]Qiu X, Matto GL, Norman J, 2000. Chinese Writing. Institute of East Asian Studies, University of California, USA.

[37]Saito S, Nakajima M, 1999. 3D physics-based brush model for painting. ACM SIGGRAPH, Article 226.

[38]Shi C, Xiao JG, Xu CH, et al., 2014. Automatic generation of Chinese character using features fusion from calligraphy and font. The Engineering Reality of Virtual Reality, Article 90120N.

[39]Strassmann S, 1986. Hairy brushes. ACM SIGGRAPH Comput Graph, 20(4):225-232.

[40]Su CL, 2007a. Edge distance and gray level extraction and orientation invariant transform for Chinese seal recognition. Appl Math Comput, 193(2):325-334.

[41]Su CL, 2007b. Ring-to-line mapping and orientation invariant transform for Chinese seal character recognition. Int J Comput Math, 84(1):11-22.

[42]Sun DY, Ren TZ, Li CX, et al., 2017. Learning to write stylized Chinese characters by reading a handful of examples. https://arxiv.org/abs/1712.06424v3

[43]Tang SS, Xia ZQ, Lian ZH, et al., 2019. FontRNN: generating large-scale Chinese fonts via recurrent neural network. Comput Graph Forum, 38(7):567-577.

[44]Tian YC, 2016. Rewrite. https://github.com/kaonashi-tyc/Rewrite [Accessed on Jan. 1, 2021].

[45]Tian YC, 2017. zi2zi. https://github.com/kaonashi-tyc/zi2zi [Accessed on Jan. 1, 2021].

[46]Unicode Consortium, 2020. Roadmap to the TIP. https://unicode.org/roadmaps/tip/ [Accessed on Jan. 1, 2021].

[47]Wang L, 1980. Manuscript of Chinese History. Zhong Hua Book Company, Beijing, China (in Chinese).

[48]Wang YG, Pang YJ, 1986. CCC—computer Chinese calligraphy system. Inform Contr, (2):38-43 (in Chinese).

[49]Wen C, Chang J, Zhang Y, et al., 2019. Handwritten Chinese font generation with collaborative stroke refinement. https://arxiv.org/abs/1904.13268

[50]Wong HTF, Ip HHS, 2000. Virtual brush: a model-based synthesis of Chinese calligraphy. Comput Graph, 24(1):99-113.

[51]Xu SH, Tang M, Lau F, et al., 2002. A solid model based virtual hairy brush. Comput Graph Forum, 21(3):299-308.

[52]Xu SH, Jiang H, Lau FCM, 2007. An intelligent system for Chinese calligraphy. Proc 22^nd National Conf on Artificial Intelligence, p.1578-1583.

[53]Xu SH, Jiang H, Jin T, et al., 2009. Automatic generation of Chinese calligraphic writings with style imitation. IEEE Intell Syst, 24(2):44-53.

[54]Xu YX, 2007. The Research and Implementation of Chinese Calligraphy Tablet Generation Techniques. MS Thesis, Zhejiang University, Hangzhou, China (in Chinese).

[55]Yin YH, Chen ZW, Zhao YJ, et al., 2020. Automated Chinese seal carving art creation with AI assistance. IEEE Conf on Multimedia Information Processing and Retrieval, p.394-395.

[56]Yu JH, Peng QS, 2005. Realistic synthesis of cao shu of Chinese calligraphy. Comput Graph, 29(1):145-153.

[57]Yu JH, Zhang JD, Cong YQ, 1996. A physically-based brush-pen model. J Comput-Aid Des Comput Graph, 8(4):241-245 (in Chinese).

[58]Yu K, 2010. Researches on Some Key Technologies of Computer Calligraphy. PhD Thesis, Zhejiang University, Hangzhou, China (in Chinese).

[59]Yuan R, 1979. Hanyin Fenyun Hebian. Shanghai Bookstore Publishing House, China (in Chinese).

[60]Zhang JS, 2019. A survey of digital calligraphy. Sci Sin Inform, 49(2):143-158 (in Chinese).

[61]Zhang YX, Zhang Y, Cai WB, 2018. Separating style and content for generalized style transfer. IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.8447-8455.

[62]Zheng ZZ, Zhang FY, 2018. Coconditional autoencoding adversarial networks for Chinese font feature learning. https://arxiv.org/abs/1812.04451

[63]Zhou BY, Wang WH, Chen ZH, 2011. Easy generation of personal Chinese handwritten fonts. IEEE Int Conf on Multimedia and Expo, p.1-6.

[64]Zong A, Zhu YK, 2014. StrokeBank: automating personalized Chinese handwriting generation. Proc 28^th AAAI Conf on Artificial Intelligence, p.3024-3029.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

- Go to

视觉知识引导的中国篆刻智能化生成

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference