在電腦硬體快速發展的時代，以前被視為只能在工作站上執行的3D繪圖現今也可以輕易地在普通的家用電腦上執行。藉著網路視訊攝影機低廉的價格以及其普及化的趨勢，我們設計一套兼顧快速以及經濟性的系統。使用者可以輕易自行架構攝影環境，不需專業的操作便可以自動產生立體的人臉誇張模型。另一方面我們改良並結合先前的2D誇張肖像漫畫研究，除了大幅提升五官定位的精確度外，藉著替換多張參考畫作，產生出來的模型可以呈現不同藝術風格的外觀，以供廣泛的娛樂用途。 / With the advances of hardware nowadays, the computation and demonstration of 3D graphics are readily attained on a personal computer. At the same time, thanks to the prevalence of instant messaging software, webcam has become very popular. These combined factors have motivated us to design an economic and effective solution for general users to create their own 3D caricature models without complex procedures or instructions. In this thesis, we have developed a system which can extract and analyze facial features from an image pair captured by two webcams, and then generate a 3D face model based on it. Specifically, we improved previous research to obtain more accurate feature locations, and extended the exaggeration algorithm to generate more impressive effects. By fusing a caricature produced with different work as references, the system is capable of painting the face model with various artists’ styles.

在這個運動產業相當興盛的時代，隨著資訊流通急遽，運動員所擁有的形象價值在商業上亦水漲船高，也因此，形象相關的侵權事件以及各種樣態不斷的出現，如何對於個人形象權利進行充足之保護則成為相當重要的議題；本文透過文獻分析法，搜集國內外關於美國法上所發展出之形象權(Right of Publicity)法制的文獻，詳盡地介紹美國形象權的發展現況，包含：歷史緣由、主客體問題、構成要件以及法律效果，再進而針對運動產業中的形象權案例，以個案探討之方式呈現運動事件中形象權的實務操作，最後將視野拉回我國現今法制狀況，在仍以民法中關於人格權之規定，解決此種具有財產權色彩的權利問題之情況下，本文透過比較我國各法與形象權法保護內容上之差異，來凸顯我國法制保護上之不充足，並且提供我國實務可修正之方向，做為未來建構我國實務的依據，並且在未來能進一步做為制定專法的參考資料，以給予運動員在形象權利上更完整的保護。

誇張肖像畫是以誇張與諷刺的手法來表現模特兒的特徵。現今這類畫作比起以寫實手法繪製的肖像畫，更受到大眾的喜愛；但是人們若想要自己模仿繪製出這類的肖像畫，除了要有繪畫天賦之外，也必須經過長時間的繪畫訓練以及對人臉的觀察，才能抓出模特兒的臉部特徵，並用生動的手法誇飾出來。 因此，如果電腦能做到代替誇張肖像畫家的工作，自動模仿繪製出誇張化的卡通肖像畫，將能替人們節省大量的時間及經費。本研究主要在設計一套能誇張肖像畫的系統，以根據使用者輸入的臉部影像，自動擷取臉部的特徵（包括特徵點的相對位置、絕對位置、形狀及大小等），並藉由分析這些特徵與常人相異之處，以一致的方式自動將特徵誇張化。這個系統並能以藝術家的作品為輸入，將使用者的臉部影像轉換成具有畫家卡通風格的誇張肖像畫。除了人臉的效果外，我們也進行了頭髮分離與模擬的研究，以強化畫像風格模擬的完整性。最後，我們以實做出了系統對數個具特徵的人臉影像進行實驗，以驗證其可行性及有效性。 / Caricaturists are good at drawing sketches which express the exaggerated likeness of a person with a bit flavor of humor or sarcasm. People are willing to pay for this kind of work because it requires a lot of practice to achieve excellence. Acute observation is needed to extract the distinct features from the subject, and decent painting skill is essential to depict these features vividly. It will save much time and effort if computers can be trained used to draw caricatures. In this thesis, we developed a system which can extract and analyze facial features from simple an input facial images. The main purpose of this system is to generate the user-own caricature model by exaggerating his/her unique facial features. Different types of features, including relative locations and sizes, absolute locations and sizes, and each the shape of features are all taken in accountwill be considered. Unlike the complex process reported in the literature, we develop a transformative process that can handle different types of features in a more uniform fashion. Using an artist’s finished work as the source image; the proposed system is capable of producing cartoon-like colorful caricatures of a similar style effectively and efficiently. Besides the caricature painting of the face part, we also present some approaches for hair segmentation and hair style painting to increase make the system more the completeness of our system. Finally, we prove the feasibility and effectiveness of our system by showing several experimental results.

Comment définir ces peintures ou rondes-bosses que sont les portraits japonais figurant des moines ? Par leur forme spécifique qui, issue d’un prototype continental qui n’a pas été remis en question, est demeurée stable à l’exception de brèves périodes. Cette constance s’explique par l’importance accordée à la Chine, l’usage de modèles iconographiques (zuzō) et le recours à une réplique qui n’est jamais dénigrée. Le portrait est de plus une image au bénéfice des sectes qui la produisent. En fournissant une représentation qui ne se dégrade pas, il est aussi la preuve d’un état de sainteté, voire de bouddhéité. Quant à la fonction de certificat des portraits Zen (chinzō), elle semble rare. Portrait de groupe, rouleaux illustrés (emaki) et littérature ont également décrit des personnages à leur façon, autorisant des comparaisons. Le portrait aurait pu inventer sa propre représentation ; il a préféré emprunter aux images sacrées : figurations de vénérés, maṇḍala et illustrations de jātaka. / How can one define these paintings and sculptures in the round that make up Japanese portraits of monks? Through their specific form that derives from a continental prototype which has never been reappraised and which remained stable except for short periods of time. Such a consistency results from a strong influence of China, and from the use of iconographic models (zuzō). Furthermore, copying a work of art has never been undervalued. Portraits are also images which benefit the sect that produces them. By providing an image or representation that never decays, they bear testimony to a monk's holiness, even buddhahood. Lastly, the Zen portraits (chinzō) are often seen as a kind of certification; however, this function seems quite rare. Group portraits, scrolls (emaki) and literature also describe people in their own way, allowing comparison with portraits. Portraiture could have followed its own path; it has preferred to borrow from holy images: deities, maṇḍala and jātaka illustrations.

京都大学 / 新制・論文博士 / 博士(文学) / 乙第13510号 / 論文博第667号 / 新制||文||725(附属図書館) / 京都大学大学院文学研究科思想文化学専攻 / (主査)教授 平川 佳世, 准教授 杉山 卓史, 准教授 筒井 忠仁 / 学位規則第4条第2項該当 / Doctor of Letters / Kyoto University / DGAM