簡易檢索 / 詳目顯示

研究生: 許寶丹
Hsu, Pao-Tan
論文名稱: 人臉老化程序模擬
Face Simulation Across Age Progression
指導教授: 黃仲陵
Huang, Chung-Lin
林嘉文
Lin, Chia-Wen
口試委員: 林嘉文
莊仁輝
連震杰
賴尚宏
學位類別: 碩士
Master
系所名稱: 電機資訊學院 - 電機工程學系
Department of Electrical Engineering
論文出版年: 2012
畢業學年度: 101
語文別: 中文
論文頁數: 52
中文關鍵詞: 人臉模擬人臉老化
外文關鍵詞: Poisson image editing, face simulation
相關次數: 點閱:4下載:0
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報
  • 在本篇論文中,我們利用年齡合成(Age synthesis )重新呈現了人類臉部圖像的自然老化現象。我們提出了兩階段方法模擬一個面部衰老的過程:首先,建立一個延伸了顱面生長模型( Craniofacial growth model) 的形狀轉換模型,並且基於心理物理學和人體測量學的研究,觀察並統計面部的五官輪廓隨著年齡的增長的細微變形,該模型主要描述了人類隨時間成長而影響到面部所產生的形狀變化。
    接著運用以圖像梯度為原理的演算法,分區擷取特徵並依此建立老化的紋理模型,在這裡使用Poisson image editing進行細部的紋理的模擬轉換,描述了不同年齡的面部的皺紋和其他皮膚紋理,為了得到老齡化合成的結果,我們透過定義特徵點,並用以三角形測量為基礎的分段仿射的變形( Triangulating and piecewise affine warping)來達成,使模擬結果更加的自然且趨近真實性。
    我們從FG_NET和MORPH 兩大年齡數據庫中,對人臉圖像做統計分析其特徵點參數來建立模型,並且尋找相似度高的圖片來進行我們的面部老化程序,包含形狀及紋理的模擬合成。在最後,用此篇論文所呈現的模擬結果,與真實的老化面部圖像進行比較與觀察。


    目錄 第一章介紹 1 1.1研究動機 1 1.2研究目標 2 1.3相關研究 3 1.4系統流程 4 1.5論文架構 6 第二章人臉老化資料庫 7 2.1 FG-NET 資料庫 8 2.2 MORPH資料庫 9 第三章預測臉部形變模型 10 3.1前處理 10 3.2面部形狀模型預測 11 3.2.1顱面生長模型 12 3.2.2頭骨形狀變化 13 3.3分段仿射變形技術 14 3.4形狀變形模擬 17 第四章臉部紋理建模合成 20 4.1 POISSON編輯圖像技術模擬紋理資訊 20 4.1.1前言介紹 20 4.1.2 Poisson Image Editing基本原理 22 4.1.3 Poisson Image Editing數學推導及實作 24 4.2特徵擷取和紋理建模 30 4.2.1 HOG特徵擷取 30 4.2.2 HOG原理步驟 31 4.2.3特徵擷取及建模 33 第五章實驗結果 35 5.1實驗環境 35 5.2收集形狀範例模型 35 5.3實驗結果 39 5.3.1一對一人臉圖像老化模擬結果 39 5.3.2形狀老化的模擬結果 41 5.3.3對自身老化圖像的模擬及比較 42 5.3.4利用的皺紋紋理模型做模擬及比較其結果 43 第六章結論及未來展望 45 參考文獻 46 附錄 51

    參考文獻
    [1] Y. Wu and N. M. Thalmann, ''A Dynamic Wrinkle Model in Facial Animation and Skin Aging'', Journal of Visualization and Computer Animation, vol. 6, no. 4, pp. 195-205, 1995.
    [2] Y. Wu, P. Kalra and T. N. Magnenat, ''Physically-Based Wrinkle Simulation and Skin Rendering'', Proc. Eurographics Workshop on Computer Simulation and Animation, pp. 69-79, 1997.
    [3] Y. Wu, P. Beylot and N. M. Thalmann, ''Skin Aging Estimation by Facial Simulation'', Proc. Computer Animation, pp. 210-219, 1999.
    [4] L. Boissieux, G. Kiss, N. M. Thalmann and P. Kalra, ''Simulation of Skin Aging and Wrinkles with Cosmetics Insight'', Proc. Eurographics, Workshop on Animation Computer Animation and Simulation, pp. 15-27, 2000.
    [5] N. Ramanathan and R. Chellappa, ''Modeling Shape and Textural Variations in Aging Faces'', Eighth Int'l Conf. Automatic Face and Gesture Recognition, 2008.
    [6] Y. Bando, T.Kuratate and T.Nishita, ''A Simple Method for Modeling Wrinkles on Human Skin'', Proc. Tenth Pacific Conf. Computer Graphics and Applications, pp. 166-175, 2002.
    [7] D. M. Burt and D. I. Perrett, ''Perception of Age in Adult Caucasian Male Faces: Computer Graphic Manipulation of Shape and Color Information'', Proc. Royal Soc. London, vol. 259, no. 1355, pp. 137-143, 1995.
    [8] A. Lanitis, ''Comparative Evaluation of Automatic Age-Progression Methodologies'', EURASIP Journal on Advances in Signal Processing, vol. 8, no. 2, pp. 1-10, 2008.
    [9] P. J. Benson and D. I. Perrett, ''Extracting Prototypical Facial Images from Exemplars'', Perception and Psychophysics, vol. 22, no. 3, pp. 257-262, 1993.
    [10] F. J. Galton, ''Composite Portraits'', Nature, vol. 18, no. 447, pp. 97-100, 1879.
    [11] D. A. Rowland and D. I. Perrett, ''Manipulating Facial Appearance through Shape and Color'', IEEE Trans. on Computer Graphics and Applications, vol. 15, no. 5, pp. 70-76, 1995.
    [12] B. P. Tiddeman, D. M. Burt and D. I. Perrett, ''Prototyping and Transforming Facial Textures for Perception Research'', IEEE Trans. Computer Graphics and Applications, vol. 21, no. 5, pp. 42-50, 2001.
    [13] P. Phillips, H. Moon, P. Rauss, and S. Rizvi. The FERET evaluation methodology for face-recognition algorithms. In Proceedings Computer Vision and Pattern Recognition, 1997.
    [14] P. Phillips, H. Moon, P. Rauss, and S. Rizvi. The FERET september 1996 database and evaluation procedure. In Proceedingsof Audio and Video-based Biometric Person Authentication, 1997
    [15] P.J. Phillips, P.J. Flynn, T. Scruggs, K.W. Bowyer, J. Chang, K. Hoffman, J. Marques, J. Min, W. Worek, Overview of the face recognition grand challenge, Computer Vision and Pattern Recognition (CVPR) (2005), pp. I:947–954.
    [16] R. Gross, I. Mathews, J. Cohn, T. Kanade, and S. Baker. Multipie. In IEEE International Conference on Automatic Face and Gesture Recognition, 2006
    [17] The FG-NET Aging Database [Online]. Available: http://www.fgnet.rsunit.com/
    [18] K. J. Ricanek and T. Tesafaye. Morph: A longitudinal image database of normal adult age-progression. In FGR ’06: Proc.7th International Conference on Automatic Face and GestureRecognition, pages 341–345, Washington, D.C., 2006
    [19] Todd DK (1980) Groundwater hydrology, 2nd edn. Wiley, New York, 535 pp
    [20] J. B. Pittenger, R. E. Shaw, and L. S. Mark, “Perceptual information for the age level of faces as a higher order invariant to growth,” Journal of Experimental Psychology : Human Perception and Performance, vol. 5, pp. 478–493, 1979.
    [21] Zimbler MS, Kokoska MS, Thomas JR. Anatomy and pathophysiology of facial aging. Facial Plast Surg Clin North Am 2001; 9:179-87.
    [22] Pessa, J. E., Desvigne, L. D., Lambros, V. S., et al. Changes in ocular globe-to-orbital rim position with age: Implications for aesthetic blepharoplasty of the lower eyelids. Aesthetic Plast. Surg. 23: 337, 1999.
    [23] J. Suo, S. Zhu, S. Shan, and X. Chen, “A compositional and dynamic model for face aging,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 32, no. 3, pp. 385-401, March 2010.
    [24] A. Lanitis, C. J. Taylor, and T. F. Cootes, ÒToward automatic simulation of aging effects on face images,Ó IEEE Trans. Pattern Anal. Mach. Intell., vol. 24, no. 4, pp. 442Ð455, Apr. 2002.
    [25] N. Ramanathan and R. Chellappa, “Modeling Age Progression in Young Faces”, CVPR, I:387-394, 2006
    [26] V. Kwatra, A. Schodl, I. Essa, and A. Bobick, “Graphcut Textures: Image and Video Synthesis Using Graph Cuts,” Proc. SIGGRAPH, July 2003.
    [27] BOYKOV, Y., AND JOLLY, M.-P. 2001. Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images. In Proc. IEEE Int. Conf. on Computer Vision, CD.ROM.
    [28] A. Levin, A. Zomet, S. Peleg and Y. Weiss, “Seamless Image Stitching in the Gradient Domain,” Proceedings of European Conference on Computer Vision, 2004
    [29] P´erez, P., Gangnet, M., and Blake, A. (2003). Poisson image editing. ACM Transactions on Graphics, 22(3), 313–318.
    [30] Burt, P. J. and E. H. Adelson, "The Laplacian pyramid as a compact image code," IEEE Trans. on Communication, vol.31, no.4, pp.532-540, 1983.
    [31] N. Dalal and B. Triggs, “Histograms of Oriented Gradients for Human Detection,” Computer Vision and Pattern Recognition, 2005.CVPR 2005. IEEE Computer Society Conference on, vol. 1, pp. 886–893 vol. 1, June
    2005.
    [32] J. S. O. Dniz, G. Bueno and F. D. la Torre, \Face recognition using histograms of oriented gradients," ELSEVIER Pattern Recognition Letters, pp. 1598
    [33] A. Dhall, A. Asthana, R. Goecke, and T. Gedeon. Emotion recognition using PHOG and LPQ features. In Proceedings of the Ninth IEEE International Conference on Automatic Face Gesture Recognition and Workshops (FG’2011), Facial Expression Recognition and Analysis Challenge Workshop (FERA), pages 878–883, 2011
    [34] J.T. Todd, S.M. Leonard, R.E. Shaw, and J.B. Pittenger, “The Perception of Human Growth,” Scientific Am., vol. 242, no. 2, pp. 106-114, 1980.
    [35] I. Matthews and S. Baker, “Active appearance models revisited,” International Journal of Computer Vision, vol. 60, no. 2, pp. 135 – 164, November 2004.

    無法下載圖示 全文公開日期 本全文未授權公開 (校內網路)
    全文公開日期 本全文未授權公開 (校外網路)

    QR CODE