學術產出-學位論文
文章檢視/開啟
書目匯出
-
題名 基於筆畫與結構分析之中文書法美感評估
Aesthetic Evaluation of Chinese Calligraphy Based on Stroke and Structural Analysis作者 林育如
Lin, Yuh Ru貢獻者 廖文宏
Liao, Wen Hung
林育如
Lin, Yuh Ru關鍵詞 美感評估
書法
楷書
筆畫分析
結構分析
機器學習
Aesthetic evaluation
Calligraphy
Kai style
Stroke analysis
Structural analysis
Machine learning日期 2016 上傳時間 1-四月-2016 10:41:45 (UTC+8) 摘要 中文書法經過了長久歷史的演變，已不單用來記錄事物，儼然成為了一種藝術。從古至今，有眾多書法大家和美學家撰寫書法專書，然而中文書法理論大多講述較抽象的技法，且在相關文獻鮮少之情況下難以具體將美感量化。本論文的目的為以電腦視覺角度解析中文書法筆畫與結構，找出影響書法美觀程度的視覺元素，並加以量化分析，透過機器學習機制，使電腦具有基本的書法鑑賞能力。有別於前人研究，我們提出6種描述整體楷書書法作品美感的特徵，包含排版工整度、字距掌握度、文字偏移程度、文字書寫大小穩定度、筆畫風格一致程度以及筆畫平滑程度。本研究蒐集書法比賽和素人作品共100張，每張皆經由一般母語為中文之受測者的評估，並且將得到的評分作為樣本的標籤，透過SVM辨識3個級別和5個級別的樣本，兩者皆有好的辨識效果。再者，我們將辨識結果轉換成美感分數，亦能真實呼應人工評分。透過我們的研究成果，期望能提供書法初學者在書法創作上的基礎參考標準。
After a long history of evolution, Chinese calligraphy has transformed from a tool for writing to a unique form of art. Many publications regarding calligraphy writing techniques and appreciation have emerged along the way. Although the theory of Chinese calligraphy aesthetics is profound, it is difficult to define measures to quantify ‘beauty’ or ‘taste’. The objective of this research is to explore and extract relevant visual features for aesthetic evaluation of Chinese calligraphy using computer vision and machine learning techniques. Specifically, we propose six visual features to describe the quality of calligraphy work in Kai style, including layout, word separation, character offset, size regularity, style consistency and stroke uniformity. We then employ support vector machine (SVM) classifier to categorize the work into three or five levels of expertise. In both cases, good recognition results have been achieved. Furthermore, an aesthetic score can be obtained by converting the classification result with weighting factors. We hope that the evaluation result can assist beginners in identifying flaws in their writings and provide constructive suggestions to improve their skills in Chinese calligraphy.參考文獻 [1] 李賢輝，「視覺素養學習網」，http://vr.theatre.ntu.edu.tw/fineart/。[2] 房弘毅，「黃自元間架結構摘要九十二法」，中國書店，2005。[3] 蔡元培，「蔡元培文集（卷二）．教育上」，錦繡出版社，台北市，民國84年。[4] 梁啟超，「飲冰室專集（五）．作文教學法．書法指導」，中華書局，台北市，未標出版年。[5] 簡月娟，「書法美學研究方法論的省思」，興大中文學報第18期，民國95年1月，頁213-232。[6] Pak-keung Lai and Dit-yan Yeung, “Chinese glyph generation using character composition and beauty evaluation metrics”, Proceedings of the 1995 International Conference on Computer Processing of Oriental Languages, pp.92-99, 1995.[7] 張炘中，「漢字識別技術」，清華大學出版社，1992。[8] 房弘毅，「歐陽詢三十六法八訣」，中國書店，2005。[9] Dan Cires¸an and Jurgen Schmidhuber, “Multi-column deep neural networks for offline Handwritten Chinese character classification”, Technical Report, Aug 2013.[10] Yanwei Wang, Xin Li, Changsong Liu, Xiaoqing Ding and Youxin Chen, “An MQDF-CNN Hybrid Model for Offline Handwritten Chinese Character Recognition”, 14th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp.246–249, 2014.[11] S.H. Xu, FCM Lau and Y. Pan, “A preliminary attempt at evaluating the beauty of Chinese calligraphy”, A Computational Approach to Digital Chinese Painting and Calligraphy, pp.253-284, 2009.[12] Rongju Sun, Zhouhui Lian, Yingmin Tang and Jianguo Xiao, “Aesthetic Visual Quality Evaluation of Chinese Handwritings”, Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI 2015).[13] Jinjun Wang, Jianchao Yang, Kai Yu,Fengjun Lv, Thomas Huang, and Yihong Gong, “Locality-constrained linear coding for image classification”, Computer Vision and Pattern Recognition (CVPR), pp.3360–3367, 2010.[14] A Wilsona and A Chatterjee, “The assessment of preference for balance: Introducing a new test”, Empirical Studies of the Arts, vol. 23, pp.165-180, 2005.[15] Gershoni S and Hochstein S, “Measuring pictorial balance perception at first glance using Japanese calligraphy”, i-Perception, vol. 2 Issue 6, pp.508-527, 2011.[16] Boris Epshtein, Eyal Ofek, and Yonatan Wexler, “Detecting text in natural scenes with stroke width transform”, CVPR, pp.2963-2970, 2010. [17] 陳仕侗，「筆歌墨舞-書法欣賞」，http://tmw3.tmps.tp.edu.tw/100501/%E7%AD%86%E6%AD%8C%E5%A2%A8%E8%88%9E/%E6%9B%B8%E6%B3%95%E6%AC%A3%E8%B3%9E.htm[18]「數位化的藝術廊道」，http://ndap.wzu.edu.tw/index.html。 描述 碩士
國立政治大學
資訊科學學系
102753018資料來源 http://thesis.lib.nccu.edu.tw/record/#G0102753018 資料類型 thesis dc.contributor.advisor 廖文宏 zh_TW dc.contributor.advisor Liao, Wen Hung en_US dc.contributor.author (作者) 林育如 zh_TW dc.contributor.author (作者) Lin, Yuh Ru en_US dc.creator (作者) 林育如 zh_TW dc.creator (作者) Lin, Yuh Ru en_US dc.date (日期) 2016 en_US dc.date.accessioned 1-四月-2016 10:41:45 (UTC+8) - dc.date.available 1-四月-2016 10:41:45 (UTC+8) - dc.date.issued (上傳時間) 1-四月-2016 10:41:45 (UTC+8) - dc.identifier (其他 識別碼) G0102753018 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/83542 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 資訊科學學系 zh_TW dc.description (描述) 102753018 zh_TW dc.description.abstract (摘要) 中文書法經過了長久歷史的演變，已不單用來記錄事物，儼然成為了一種藝術。從古至今，有眾多書法大家和美學家撰寫書法專書，然而中文書法理論大多講述較抽象的技法，且在相關文獻鮮少之情況下難以具體將美感量化。本論文的目的為以電腦視覺角度解析中文書法筆畫與結構，找出影響書法美觀程度的視覺元素，並加以量化分析，透過機器學習機制，使電腦具有基本的書法鑑賞能力。有別於前人研究，我們提出6種描述整體楷書書法作品美感的特徵，包含排版工整度、字距掌握度、文字偏移程度、文字書寫大小穩定度、筆畫風格一致程度以及筆畫平滑程度。本研究蒐集書法比賽和素人作品共100張，每張皆經由一般母語為中文之受測者的評估，並且將得到的評分作為樣本的標籤，透過SVM辨識3個級別和5個級別的樣本，兩者皆有好的辨識效果。再者，我們將辨識結果轉換成美感分數，亦能真實呼應人工評分。透過我們的研究成果，期望能提供書法初學者在書法創作上的基礎參考標準。 zh_TW dc.description.abstract (摘要) After a long history of evolution, Chinese calligraphy has transformed from a tool for writing to a unique form of art. Many publications regarding calligraphy writing techniques and appreciation have emerged along the way. Although the theory of Chinese calligraphy aesthetics is profound, it is difficult to define measures to quantify ‘beauty’ or ‘taste’. The objective of this research is to explore and extract relevant visual features for aesthetic evaluation of Chinese calligraphy using computer vision and machine learning techniques. Specifically, we propose six visual features to describe the quality of calligraphy work in Kai style, including layout, word separation, character offset, size regularity, style consistency and stroke uniformity. We then employ support vector machine (SVM) classifier to categorize the work into three or five levels of expertise. In both cases, good recognition results have been achieved. Furthermore, an aesthetic score can be obtained by converting the classification result with weighting factors. We hope that the evaluation result can assist beginners in identifying flaws in their writings and provide constructive suggestions to improve their skills in Chinese calligraphy. en_US dc.description.tableofcontents 第一章 緒論 1第二章 相關研究 52.1 美感評估文獻探討 52.2 中文書法美感評估工具 82.2.1 平衡度分析 82.2.2 筆畫寬度分析 11第三章 視覺元素特徵擷取 143.1 整體作品 153.1.1 排版工整度 153.1.2 字距掌握度 193.1.3 文字偏移程度 233.1.4 文字書寫大小穩定度 253.1.5 筆畫風格一致度 273.1.6 筆畫平滑程度 313.2 個別字 323.2.1 平衡度測量 32第四章 美感評估與機器學習預測 364.1 受測者可信度驗證 364.2 書法作品切字前處理 444.3 視覺元素特徵檢測 484.3.1 排版工整度 484.3.2 字距掌握度 514.3.3 偏移程度 534.3.4 文字書寫大小穩定度 564.3.5 筆畫風格一致度 574.3.6 筆畫平滑程度 594.3.7 平衡度 614.4 書法作品評估學習 63第五章 結論與未來方向 68參考文獻 70 zh_TW dc.format.extent 4499400 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0102753018 en_US dc.subject (關鍵詞) 美感評估 zh_TW dc.subject (關鍵詞) 書法 zh_TW dc.subject (關鍵詞) 楷書 zh_TW dc.subject (關鍵詞) 筆畫分析 zh_TW dc.subject (關鍵詞) 結構分析 zh_TW dc.subject (關鍵詞) 機器學習 zh_TW dc.subject (關鍵詞) Aesthetic evaluation en_US dc.subject (關鍵詞) Calligraphy en_US dc.subject (關鍵詞) Kai style en_US dc.subject (關鍵詞) Stroke analysis en_US dc.subject (關鍵詞) Structural analysis en_US dc.subject (關鍵詞) Machine learning en_US dc.title (題名) 基於筆畫與結構分析之中文書法美感評估 zh_TW dc.title (題名) Aesthetic Evaluation of Chinese Calligraphy Based on Stroke and Structural Analysis en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) [1] 李賢輝，「視覺素養學習網」，http://vr.theatre.ntu.edu.tw/fineart/。[2] 房弘毅，「黃自元間架結構摘要九十二法」，中國書店，2005。[3] 蔡元培，「蔡元培文集（卷二）．教育上」，錦繡出版社，台北市，民國84年。[4] 梁啟超，「飲冰室專集（五）．作文教學法．書法指導」，中華書局，台北市，未標出版年。[5] 簡月娟，「書法美學研究方法論的省思」，興大中文學報第18期，民國95年1月，頁213-232。[6] Pak-keung Lai and Dit-yan Yeung, “Chinese glyph generation using character composition and beauty evaluation metrics”, Proceedings of the 1995 International Conference on Computer Processing of Oriental Languages, pp.92-99, 1995.[7] 張炘中，「漢字識別技術」，清華大學出版社，1992。[8] 房弘毅，「歐陽詢三十六法八訣」，中國書店，2005。[9] Dan Cires¸an and Jurgen Schmidhuber, “Multi-column deep neural networks for offline Handwritten Chinese character classification”, Technical Report, Aug 2013.[10] Yanwei Wang, Xin Li, Changsong Liu, Xiaoqing Ding and Youxin Chen, “An MQDF-CNN Hybrid Model for Offline Handwritten Chinese Character Recognition”, 14th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp.246–249, 2014.[11] S.H. Xu, FCM Lau and Y. Pan, “A preliminary attempt at evaluating the beauty of Chinese calligraphy”, A Computational Approach to Digital Chinese Painting and Calligraphy, pp.253-284, 2009.[12] Rongju Sun, Zhouhui Lian, Yingmin Tang and Jianguo Xiao, “Aesthetic Visual Quality Evaluation of Chinese Handwritings”, Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI 2015).[13] Jinjun Wang, Jianchao Yang, Kai Yu,Fengjun Lv, Thomas Huang, and Yihong Gong, “Locality-constrained linear coding for image classification”, Computer Vision and Pattern Recognition (CVPR), pp.3360–3367, 2010.[14] A Wilsona and A Chatterjee, “The assessment of preference for balance: Introducing a new test”, Empirical Studies of the Arts, vol. 23, pp.165-180, 2005.[15] Gershoni S and Hochstein S, “Measuring pictorial balance perception at first glance using Japanese calligraphy”, i-Perception, vol. 2 Issue 6, pp.508-527, 2011.[16] Boris Epshtein, Eyal Ofek, and Yonatan Wexler, “Detecting text in natural scenes with stroke width transform”, CVPR, pp.2963-2970, 2010. [17] 陳仕侗，「筆歌墨舞-書法欣賞」，http://tmw3.tmps.tp.edu.tw/100501/%E7%AD%86%E6%AD%8C%E5%A2%A8%E8%88%9E/%E6%9B%B8%E6%B3%95%E6%AC%A3%E8%B3%9E.htm[18]「數位化的藝術廊道」，http://ndap.wzu.edu.tw/index.html。 zh_TW
