本論文探討以雙鏡頭拍攝之側臉影像來重建三維人臉模型。首先，應用雙鏡頭模組拍攝側臉影像，接著利用立體視覺技術得到視差影像。然後再使用人臉偵測掌握人臉位置，並加以分析視差影像是否為側臉。若是經判斷為側臉，則接著計算側臉的旋轉程度，並逐步重建出三維臉部模型來。最後，實驗結果顯示本論文所提出的方法在重建三維人臉模型上具有良好的性能。

This thesis discusses the reconstruction of a three-dimensional (3D) face model using side-view face images taken by a binocular camera. First, the side-view face images are taken by using a binocular camera. Then, the parallax images are obtained by using stereo vision. We use face detection to get the face position and then analyze whether a parallax images is a side-view face image. If it is judged as a side-view face, the degree of rotation of the side-view face is calculated and the 3D face model is reconstructed step by step. Finally, the experimental results show that there will be good performance in the reconstruction of 3D face model by using the proposed method.

[1] Y. I. Abdel-Aziz and H. M. Karara, “Direct linear transformation from comparator coordinates into object space coordinates,” ASP Symposium on Close-Range Photogrammetry (CRP), 1971.
[2] R. Y. Tsai, “An efficient and accurate camera calibration technique for 3D machine vision,” IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Miami Beach, June 22-26, 1986, pp. 364-374.
[3] Q. T. Luong and O. Faugeras, “Self-calibration of a moving camera from point correspondences and fundamental matrices,” International Journal of Computer Vision (IJCV), pp. 261-289, 1997.
[4] R. I. Hartley, “An algorithm for self calibration from several views,” IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 908-912, Seattle, WA, June 1994.
[5] Z. Zhang, “A flexible new technique for camera calibration,” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 22, no. 11, pp. 1330-1334, Nov. 2000.
[6] R. Zabih and J. Woodfill, “Non-parametric local transforms for computing visual correspondence,” European Conference on Computer Vision (ECCV), pp. 151-158, 1994.
[7] Y. Heo, K. Lee, and S. Lee, “Robust stereo matching using adaptive normalized cross correlation,” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), no. 99, 2011.
[8] K. Zhang, J. Lu, and F. Catthoor, “Cross-based local stereo matching using orthogonal integral images,” IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), vol. 19, no. 7, pp. 1073-1079, Jul. 2009.
[9] Y. Boykov and G. Funka-Lea, “Optimal object extraction via constrained graph-cuts,” International Journal of Computer Vision (IJCV), 2004.
[10] S. Birchfield and C. Tomasi, “Depth discontinuities by pixel-to-pixel stereo,” International Journal of Computer Vision (IJCV), vol. 35, no. 3, pp. 1-25, Dec. 1999.
[11] H. Hirschmller, “Stereo processing by semiglobal matching and mutual Information,” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 30, no. 2, pp. 328-341, Feb. 2008.
[12] S. Lawrence, C. L. Giles, A.C. Tsoi, and A. D. Back, “Face recognition: a convolutional neural-network approach,” IEEE Transactions on Neural Networks, pp. 98-113, 1997.
[13] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks,” Neural Information Processing Systems 25 (NIPS), Lake Tahoe, Nevada, Dec. 3-6, 2012, pp. 1106-1114.
[14] M. D. Zeiler and R. Fergus, “Visualizing and understanding convolutional networks,” European Conference on Computer Vision (ECCV), Zurich, Switzerland, Sep. 6-12, 2014.
[15] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition”. International Conference on Learning Representations (ICLR), Toulon, France, May 7-9, 2015.
[16] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going deeper with convolutions,” Computing Research Repository (CoRR), abs/1409.4842, 2014.
[17] R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation,” IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, June 24-27, 2014.
[18] R. Girshick, “Fast r-cnn,” International Conference on Computer Vision (ICCV), Santiago, Chile, Dec. 13-16, 2015.
[19] S. Ren, K. He, R. Girshick and J. Sun, “Faster r-cnn: towards real-time object detection with region proposal networks,” Conference and Workshop on Neural Information Processing Systems (NIPS), Montreal, Canada, Dec. 7-12, 2015.
[20] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: unified, real-time object detection,” IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30, 2016.
[21] J. Redmon and A. Farhadi, “Yolo9000: better, faster, stronger,” IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017.
[22] R.-L. Hsu, M. Abdel-Mottaleb, and A. K. Jain, “Face detecting in color images,” IEEE Transaction on Pattern Analysis and Machine Intelligence (TPAMI), vol. 24, no. 5, pp. 696-706, 2002.
[23] C. Garcia and G. Tziritas, “Face detection using quantized skin color regions merging and wavelet packet analysis,” IEEE Transaction Multimedia, vol. 1, no. 3, pp. 264-277, 1999.
[24] M. Gargesha and S. Panchanathan, “Face detection from color images by Iterative thresholding on skin probability maps,” IEEE International Symposium on Circuit and Systems (ISCAS), vol. 5, no. 5, pp. 673-676, 2002.
[25] R. C. Gonzalez and R. E. Woods, “Digital image processing,” Prentice Hall, NJ, USA, 2002.
[26] J. Wu and Z.-H. Zhou, “Efficient face candidates selector for face detection,” International Journal of Pattern Recognition, vol. 36, no. 5, pp. 1175-1186, 2003.
[27] Z. Jin, Z. Lou, J.-Y. Yang, and Q. S. S. Sun, “Face detection using template matching and skin-color information,” International Journal of Neurocomputing, pp. 794-800, 2007.
[28] A. Anjos, M. M. Chakka, and S. Marcel, “Motion-based countermeasures to photo attacks in face recognition,” Institution of Engineering and Technology (IET), July 24-29, 2013.
[29] P. Viola and M. Jones, “Robust real-time object detection,” Second International Workshop on Statistical and Computational Theories of Vision, Vancouver, Canada, July 13, 2001.
[30] W.-S. Lee and N. M. Thalmann, “Head Modeling from Pictures and Morphing in 3D with Image Metamorphosis Based on Triangulation,” Modelling and Motion Capture Techniques for Virtual Environments, pp. 254-268, 1998.
[31] T. Kurihara and K. Arai, “A transformation method for modeling and animation of the human face from photographs,” State of the Art in Computer Animation, pp. 45-57. Springer-Verlag, 1991.
[32] Z. Zhu, P. Luo, X. Wang, and X. Tang, “Multi-view perceptron: a deep model for learning face identity and view representations,” Conference and Workshop on Neural Information Processing Systems (NIPS), Montreal, Canada, Dec. 8-13, 2014.
[33] J. H. Y. Qian and W. Deng, “Task specific networks for identity and face variation,” IEEE International Conference on Automatic Face and Gesture Recognition (FG), Xi’an, China, May 15-19, 2018, pp. 271-277.
[34] I. Goodfellow, P.-A. Jean, M. Mirza, B. Xu, W.-F. David, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial nets”, Neural Information Processing Systems, 2015.
[35] R. Huang, S. Zhang, T. Li, and R. He, “Beyond face rotation: global and local perception GAN for photorealistic and identity preserving frontal view synthesis,” International Conference on Computer Vision (ICCV), pp. 2458-2467, Venice, Italy, Oct. 22-29, 2017.
[36] X. Yin, X. Yu, K. Sohn, X. Liu, and M. Chandraker, “Towards large-poseface frontalization in the wild,” International Conference on Computer Vision (ICCV), Venice, Italy, Oct. 22-29, 2017.
[37] L. Tran, X. Yin, and X. Liu, “Disentangled representation learning GAN for pose-invariant face recognition,” IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017.
[38] 吳炳飛、徐勝均、瞿忠正，2018，《智慧影像分析在物聯網的應用：智慧購物的技術研發(3/3)》，計畫編號：MOST 106-2622-E-009-001-CC2，台北:科技部補助產學合作研究計畫(成果報告)。