隨著數位影像軟、硬體裝置上進步與普及，普羅大眾對於影像的使用不僅限於日常生活之中，更隨著網路分享概念等Web技術的擴張，這些數量龐大的影像，在使用上更朝向娛樂化、趣味化及個人化的範疇。本論文提出結合影像處理中的人臉特徵分析（Facial Features Analysis）資訊以及影像內容分割（Image Content Segmentation）及影像變形轉換（Image Warping and Morphing）等技術，設計出可以將真實照片中的人臉轉換成為卡通化的肖像，供使用者於各類媒體上使用。卡通化肖像不但具有隱藏影像細節，保留部份隱私的優勢，同時又兼具充份擁有個人化特色的表徵，透過臉部動畫的參數（Facial Animation Parameters）設定，我們提出的卡通化系統更容許使用者依心情，來合成喜、怒、哀、樂等不同表情。另外，運用兩種轉描式（Rotoscoping）及圖像變形（Morphing）法，以不同的合成技巧來解決不同裝置在限定顏色及效果偏好上的各類需求。 / As the acquisition of digital images becomes more convenient, diversified applications of image collections have surfaced at a rapid pace. Not only have we witnessed the popularity of photo-sharing platforms, we have also seen strong demand for novel mechanism that offers personalized and creative entertainment in recent years. In this thesis, we proposed and implemented a personal caricature generator using transformative approaches. By combing facial feature detection, image segmentation and image warping/morphing techniques, the system is able to generate stylized caricature using only one reference image. The system can also produce multiple expressions by controlling the MPEG-4 facial animation parameters (FAP). Specifically, by referencing to various pre-drawn caricature in our database as well as feature points for mesh creation, personalized caricatures are automatically generated from the real photos using either rotoscoping or transformative approaches. The resulting caricature can be further modified to exhibit multiple facial expressions. Important issues regarding color reduction and vectorized representation of the caricature have also been discussed in this thesis.

The bias against attractiveness is fairly implicit and furthermore, powerfully impacts people’s subsequent impressions of and behaviors toward others (Cash, Gillen, & Burns, 1977; Dion et al., 1972). Pallet, Link and Lee (2010) examined the effect of various facial spatial configurations on attractiveness and found that raters rated faces as most attractive when the eyeto-mouth ratio approximated 36% of the face length (the "golden ratio"), which coincides with the measurements of an average and thus more attractive face. The present study examined the extent to which the distance of these objectively measured facial features affected mentors’ perceptions of their protégés, the subsequent mentoring given to them, and the protégés’ own behavior (e.g. seek feedback, request specific information).The gender composition of the mentor-protégé dyad was expected to moderate these relationships. I also examined whether, given the expected effects of facial measurements, withholding access to visual cues would affect mentor perceptions and behavior. Participants were 118 mentor/protégé dyads from a large Southeastern university who volunteered to participate in a formal online peer mentoring program. After seeing their protégés’ profiles (and for those in the experimental condition, a picture), mentors chatted with their protégés once a week for 30 minutes for a total of 4 weeks. Results indicated that protégés with facial features moderately distant from the golden ratio were perceived as more similar by mentors in same-gender dyads and received greater mentoring than did protégés closest and farthest from the golden ratio. In opposite-gender dyads, however, mentors reported greater similarity toward those that were farthest from the golden ratio but provided the greatest mentoring to those closest to the golden ratio. The relationship iv between facial measurements and protégé proactivity was moderated by whether or not their mentor had access to their picture. While protégés closest to the ratio were more proactive in the picture condition, those that were farthest from it were more proactive in the non-picture condition. Proactivity was as expected associated with greater levels of mentoring, which was ultimately related to a more fulfilled and beneficial relationship for protégés (i.e. less stress, greater self-efficacy and satisfaction). The results of this study indicate that facial measurements are associated with both differences in mentor and in protégé behavior and that the specific nature of these relationships differs as a function of gender composition. Implications for practice and theory will be discussed

Indiana University-Purdue University Indianapolis (IUPUI) / Madeline Heilman’s (1983) Lack of Fit Model, which postulates why discrimination occurs in the selection of sex-typed jobs, has been applied to the interaction of applicant attractiveness. Yet recent research suggests that other appearance variables, namely sex-typed facial features, may be associated with perceptions of fit. Building upon Heilman’s 1983 model, the current study evaluated how sex-typed facial features relate to applicant selection for sex-typed fields. Undergraduate students were recruited for participation during the spring academic semester (n = 413) and data were analyzed using a 2x2x2 ANOVA. Results indicated that selection is significantly impacted by the three-way interaction of applicant sex, facial feature-type, and sex type of the applying field. Further, masculine-featured females and feminine-featured males were significantly less favored for selection within the feminine sex-typed field. Implications of these findings and the differential evaluation of male and female applicants in a feminine field are discussed.