中醫針灸與穴位按摩是中醫常用的療法，根據病患不同症狀可以針對對應的穴位做針灸或穴位按摩來緩解病患症狀。由於有龐大的穴位點的數量，並且穴位點有多樣化、複雜性與專一性，除非經由一段時間的專業訓練，常人很難記得每個穴位點的位置以及對應的治療用途。我們系統藉由擴真實境，穴位點會顯示在人體的輸入影像上，相比傳統使用穴位點量測電阻值，我們的系統透過軟體的方式，使用已有的智慧型手機，不需要額外的硬體支出。在輕微症狀如頭痛、睡眠障礙，透過我們的系統能幫助病人快速定位穴位點用於按摩達到緩解症狀，而不需中醫專家的幫助。我們的提出新的穴位預估系統以人臉為範例，利用人臉特徵標記點和3D變形模型達到可以適應不同臉型與臉部角度，在預估穴位的精準度方面，提出的系統比起現有的系統提昇高達170%之多。系統也被實作在Android平台上，以展示真實的穴位應用用於緩解症狀。

Acupuncture therapy is one of the main modalities of treatment in Traditional Chinese Medicine (TCM). Based on the different symptoms of the patient, needling or massaging is applied to the corresponding acupuncture points to relieve the symptoms. However, given that the large number of acupuncture points and the complexity of their specificity, it is difficult for one to remember the location and purpose of each acupuncture point without a period of professional training. In our system, through the use of augmented reality, the acupuncture points will be displayed directly on the image of human body. Compared to the traditional acupoint probe devices that work by measuring the skin conductivity, our system does not require any additional hardware and is purely software-based. In the case of mild symptoms (e.g. headache, sleep disorder), with the aid of our proposed system, the patient can quickly locate the corresponding acupuncture points for the application of massage, and relieve his/her symptoms without the the help from TCM physicians. We proposed a new approach for acupoints estimation, human face is taken as an example in our work, we leverage the facial landmark points and the 3D morphable model (3DMM), and have shown the proposed system is capable of estimating acupoints on different face shapes with various input face angles, the tracking mechanism is added to mitigate face detection failure when some of the face area is occluded by hand when do the acupuncture. Our system is shown to outperform the existing work by 170% in terms of estimation precision. A prototype system based on Android is also presented to demonstrate the application of real-life symptoms relief.

[1] Eos camera movie record. https://sourceforge.net/projects/eos-movrec/.
[2] Open source computer vision library. https://github.com/opencv/opencv.
[3] Webcamstudio for gnu/linux. https://sourceforge.net/projects/webcamstudio/.
[4] Volker Blanz and Thomas Vetter. A morphable model for the synthesis of 3d faces. Proceedings of the 26th annual conference on Computer graphics and interactive techniques (SIGGRAPH), pages 187–194, 1999.
[5] Dav Bolme, J. Ross Beveridge, Bruce a. Draper, and Yui Man Lui. Visual object tracking using adaptive correlation filters. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pages 2544–2550, 2010.
[6] Menglong Chang and Qing Zhu. Automatic location of facial acupuncture-point based on facial feature points positioning. 5th International Conference on Frontiers of Manufacturing Science and Measuring Technology (FMSMT), 130(545–549):5, 2017.
[7] Qing Chen, Nicolas D Georganas, and Emil M Petriu. Hand gesture recognition using haar-like features and a stochastic context-free grammar. IEEE transactions on instrumentation and measurement, 57(8):1562–1571, 2008.
[8] Xing CHEN. Warps an image by a few control points. https://github.com/opencv/opencv.
[9] Navneet Dalal and Bill Triggs. Histograms of oriented gradients for human detection. 1:886–893, June 2005.
[10] Martin Danelljan, Gustav Häger, Fahad Khan, and Michael Felsberg. Accurate scale estimation for robust visual tracking. Proceedings of the British Machine Vision Conference BMVC, Nottingham, 2014.
[11] Peter Deadman, Mazin Al-Khafaji, and Kevin Baker. A manual of acupuncture. Journal of Chinese Medicine Publications, 2007.
[12] Pedro F Felzenszwalb, Ross B Girshick, David McAllester, and Deva Ramanan. Object detection with discriminatively trained part-based models. IEEE transactions on pattern analysis and machine intelligence, 32(9):1627–1645, 2010.
[13] Martin A. Fischler and Robert C. Bolles. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM, 24(6):381–395, June 1981.
[14] Claudia Focks. Atlas of Acupuncture. Elsevier Health Sciences, 2008.
[15] Daniel Grest, Thomas Petersen, and Volker Krüger. A comparison of iterative 2d-3d pose estimation methods for real-time applications. 16th Scandinavian Conference on Image Analysis, pages 706–715, 2009.
[16] Gary B. Huang, Manu Ramesh, Tamara Berg, and Erik Learned-Miller. Labeled faces in the wild: A database for studying face recognition in unconstrained environments.Technical Report 07-49, University of Massachusetts, Amherst, October 2007.
[17] Patrik Huber. A lightweight 3d morphable face model fitting library in modern c++11/14. https://github.com/patrikhuber/eos, 2015.
[18] Patrik Huber, Zhen-Hua Feng, William Christmas, Josef Kittler, and Matthias Rätsch. Fitting 3d morphable models using local features. 2015 IEEE International Conference on Image Processing (ICIP), pages 1195–1199, 2015.
[19] Patrik Huber, Guosheng Hu, Rafael Tena, Pouria Mortazavian, P Koppen, WJ Christmas, Matthias Ratsch, and Josef Kittler. A multiresolution 3d morphable face model and fitting framework. Proceedings of the 11th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 2016.
[20] Haotian Jiang, James Starkman, Chia-Hung Kuo, and Ming-Chun Huang. Acu glass: Quantifying acupuncture therapy using google glass. Proceedings of the 10th EAI International Conference on Body Area Networks, pages 7–10, 2015.
[21] Vahid Kazemi and Josephine Sullivan. One millisecond face alignment with an ensemble of regression trees. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pages 1867–1874, 2014.
[22] Alif Ridzuan Khairuddin, Mohamad Shukor Talib, and Habibollah Haron. Review on simultaneous localization and mapping (SLAM). IEEE International Conference on Control System, Computing and Engineering (ICCSCE), (November):85–90, 2015.
[23] Jungdae Kim and Dae-In Kang. Positioning standardized acupuncture points on the whole body based on x-ray computed tomography images. Medical acupuncture, 26(1):40–49, 2014.
[24] Jungdae Kim and Dae-in Kang. Partially automated method for localizing standardized acupuncture points on the heads of digital human models. 2015.
[25] Davis E. King. A toolkit for making real world machine learning and data analysis applications in c++. http://dlib.net.
[26] Davis E. King. Dlib-ml: A machine learning toolkit. Journal of Machine Learning Research, 10:1755–1758, 2009.
[27] Jorge J Moré. The levenberg-marquardt algorithm: implementation and theory. In Numerical analysis, pages 105–116. Springer, 1978.
[28] P. Paysan, R. Knothe, B. Amberg, S. Romdhani, and T. Vetter. A 3d face model for pose and illumination invariant face recognition. Proceedings of the 6th IEEE International Conference on Advanced Video and Signal based Surveillance (AVSS) for Security, Safety and Monitoring in Smart Environments, 2009.
[29] Simon JD Prince. Computer vision: models, learning, and inference. Cambridge University Press, 2012.
[30] Rajeev Ranjan, Vishal M. Patel, and Rama Chellappa. Hyperface: A deep multi-task learning framework for face detection, landmark localization, pose estimation, and gender recognition. CoRR, 2016.
[31] Shaoqing Ren, Xudong Cao, Yichen Wei, and Jian Sun. Face alignment at 3000 fps via regressing local binary features. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1(1):1685–1692, 2014.
[32] Christos Sagonas, Epameinondas Antonakos, Georgios Tzimiropoulos, Stefanos Zafeiriou, and Maja Pantic. 300 faces in-the-wild challenge: Database and results. Image and Vision Computing, 47:3–18, 2016.
[33] Scott Schaefer, Travis McPhail, and Joe Warren. Image deformation using moving least squares. ACM Transactions on Graphics, 25(3):533–540, 2006.
[34] Statista. Smartphone penetration rate as share of mobile phone users worldwide from 2010 to 2019. https://www.statista.com/statistics/203734/global-smartphone-penetration-per-capita-since-2005/, 2014.
[35] Paul Viola and Michael Jones. Rapid object detection using a boosted cascade of simple features. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), volume 1, pages 511–518, 2001.
[36] Phillip Ian Wilson and John Fernandez. Facial feature detection using haar classifiers. Journal of Computing Sciences in Colleges, 21(4):127–133, 2006.
[37] Zhanpeng Zhang, Ping Luo, Chen Change Loy, and Xiaoou Tang. Learning deep representation for face alignment with auxiliary attributes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(5):918–930, 2016.
[38] Lei Zheng, Binjie Qin, Tiange Zhuang, Ulf Tiede, and Karl Heinz Höhne. Localization of acupoints on a head based on a 3d virtual body. Image and Vision Computing, 23(1):1–9, 2005.
[39] J. A. Zondag, T. Gritti, and V. Jeanne. Practical study on real-time hand detection. In 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, pages 1–8, Sept 2009.