臉部肌肉僵硬及萎縮會造成臉部運動功能障礙，是帕金森氏症及顏面神經麻痺患者常見的症狀，除了藥物治療，適當的運動介入有助於延緩及改善病情。然而，由於醫療資源有限，治療師難以兼顧所有復健病人，且往返醫院對病患身心所造成的消耗及枯燥乏味的復健療程，容易使病患產生逃避的念頭。若要在家裡自行做運動，也可能因動作不正確或是缺乏督促，最後不了了之。因此，本文將針對上述問題提出可能的解決方案，期望改善患者現有復健環境以及減輕健保醫療負擔。
本研究利用Kinect v2裝置開發一套臉部運動訓練系統，提供居家復健環境。系統開發過程中與專業復健研究人員合作，設計合適的臉部運動，將復健療程數位化，並以遊戲方式提高復健過程的趣味性，加強復健動機。本系統目前包含訓練及遊戲兩種模式，訓練模式是藉由反覆練習目標動作讓患者能夠活動臉部肌肉，而遊戲模式加入得分，並以隨機出現目標動作的方式，讓患者除了活動臉部肌肉外，亦能訓練反應能力和注意力。此外，本系統在復健結束後會將復健數據上傳至雲端，讓治療師能夠定期追蹤病患復健情況。
本研究招募30位年輕男性、30位年輕女性、31位年長受試者以及1位中風病患對系統的動作判斷機制進行初步測試，結果顯示，對於正常的年輕受試者，該系統各項動作的判斷準確率皆高於80%；對於年長受試者，各項動作的判斷準確率也都高於70%；而對於中風病患，由於樣本數不足，無法與年輕受試者或年長受試者進行統計上的分析。

We have developed a home-based facial exercise system for patients who suffer facial dysfunction. The study cooperated with professional therapists to design appropriate facial exercise during development processes. There are two modes in the developed rehabilitation program, the first one is a training mode aimed at training facial muscle by practicing the target motions repeatedly. The second is a game mode which needs more attention because it trains not only facial muscles but also the ability of patients’ responses. This system allows users to store data and therapists to access remotely after the rehabilitation. In this study, we have recruited 30 young men, 30 young women, 31 elderly, and 1 stroke patient for the preliminary test of the system. The results show that the accuracy rate of each motion in young and elderly groups are higher than 80% and 70%, respectively. For the stroke patient, we cannot perform the statistical analysis due to insufficient samples.

[1]Yeung, L., Cheng, K. C., Fong, C., et al., "Evaluation of the Microsoft Kinect as a clinical assessment tool of body sway," Gait & posture, Vol.40, No.4, pp.532-538, 2014.
[2]Clark, R. A., Bryant, A. L., Pua, Y., et al., "Validity and reliability of the Nintendo Wii Balance Board for assessment of standing balance," Gait & posture, Vol.31, No.3, pp.307-310, 2010.
[3]Lange, B., Chang, C.-Y., Suma, E., et al., "Development and evaluation of low cost game-based balance rehabilitation tool using the Microsoft Kinect sensor," Proceedings of the International Conference of IEEE Engineering in medicine and biology society, pp.1831-1834, 2011.
[4]Lange, B., Flynn, S., and Rizzo, A., "Initial usability assessment of off-the-shelf video game consoles for clinical game-based motor rehabilitation," Physical Therapy Reviews, Vol.14, No.5, pp.355-363, 2009.
[5]Esculier, J.-F., Vaudrin, J., Bériault, P., et al., "Home-based balance training programme using Wii Fit with balance board for Parkinson's disease: a pilot study," Journal of Rehabilitation Medicine, Vol.44, No.2, pp.144-150, 2012.
[6]Flynn, S., Palma, P., and Bender, A., "Feasibility of using the Sony PlayStation 2 gaming platform for an individual poststroke: a case report," Journal of neurologic physical therapy, Vol.31, No.4, pp.180-189, 2007.
[7]Kizony, R., Weiss, P. L. T., Shahar, M., et al., "TheraGame: A home based virtual reality rehabilitation system," International Journal on Disability and Human Development, Vol.5, No.3, pp.265-270, 2006.
[8]Assad, O., Hermann, R., Lilla, D., et al., "Motion-based games for Parkinson’s disease patients," International Conference on Entertainment Computing, pp.47-58, 2011.
[9]Burke, J. W., McNeill, M., Charles, D. K., et al., "Optimising engagement for stroke rehabilitation using serious games," The Visual Computer, Vol.25, No.12, p.1085, 2009.
[10]Katsikitis, M. and Pilowsky, I., "A controlled study of facial mobility treatment in Parkinson's disease," Journal of psychosomatic research, Vol.40, No.4, pp.387-396, 1996.
[11]Konecny, P., Elfmark, M., and Urbanek, K., "Facial paresis after stroke and its impact on patients' facial movement and mental status," Journal of rehabilitation medicine, Vol.43, No.1, pp.73-75, 2011.
[12]Ricciardi, L., Baggio, P., Ricciardi, D., et al., "Rehabilitation of hypomimia in Parkinson’s disease: a feasibility study of two different approaches," Neurological Sciences, Vol.37, No.3, pp.431-436, 2016.
[13]Beurskens, C. H. and Heymans, P. G., "Mime therapy improves facial symmetry in people with long-term facial nerve paresis: a randomised controlled trial," Australian Journal of Physiotherapy, Vol.52, No.3, pp.177-183, 2006.
[14]Kang, J.-A., Chun, M. H., Choi, S. J., et al., "Effects of Mirror Therapy Using a Tablet PC on Central Facial Paresis in Stroke Patients," Annals of rehabilitation medicine, Vol.41, No.3, pp.347-353, 2017.
[15]Yang, M.-H., Kriegman, D. J., and Ahuja, N., "Detecting faces in images: A survey," IEEE Transactions on pattern analysis and machine intelligence, Vol.24, No.1, pp.34-58, 2002.
[16]Yang, G. and Huang, T. S., "Human face detection in a complex background," Pattern recognition, Vol.27, No.1, pp.53-63, 1994.
[17]Yow, K. C. and Cipolla, R., "Enhancing human face detection using motion and active contours," Asian Conference on Computer Vision, pp.515-522, 1998.
[18]Dai, Y. and Nakano, Y., "Face-texture model based on SGLD and its application in face detection in a color scene," Pattern recognition, Vol.29, No.6, pp.1007-1017, 1996.
[19]Yang, M.-H. and Ahuja, N., "Detecting Human Faces in Color Images," Image Processing, Vol.1, pp.127-130, 1998.
[20]Sinha, P., "Object recognition via image invariance a case study," Investigative ophthalmology and visual science, Vol.35, pp.1735-1740, 1994.
[21]Yuille, A. L., Hallinan, P. W., and Cohen, D. S., "Feature extraction from faces using deformable templates," International journal of computer vision, Vol.8, No.2, pp.99-111, 1992.
[22]Rowley, H. A., Baluja, S., and Kanade, T., "Neural network-based face detection," IEEE Transactions on pattern analysis and machine intelligence, Vol.20, No.1, pp.23-38, 1998.
[23]Ekman, P. and Friesen, W. V., "Measuring facial movement," Environmental psychology and nonverbal behavior, Vol.1, No.1, pp.56-75, 1976.
[24]Hamm, J., Kohler, C. G., Gur, R. C., et al., "Automated facial action coding system for dynamic analysis of facial expressions in neuropsychiatric disorders," Journal of neuroscience methods, Vol.200, No.2, pp.237-256, 2011.
[25]Zhao, X., Li, X., Pang, C., et al., "Structured streaming skeleton--a new feature for online human gesture recognition," ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), Vol.11, No.1s, p.22, 2014.
[26]Chanthaphan, N., Uchimura, K., Satonaka, T., et al., "Facial emotion recognition based on facial motion stream generated by Kinect," 11th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), pp.117-124, 2015.
[27]Soukupova, T. and Cech, J., "Real-time eye blink detection using facial landmarks," 21st Computer Vision Winter Workshop (CVWW’2016), pp.1-8, 2016.
[28]Argueta, C., "Facial Emotion Recognition: Single-Rule 1–0 DeepLearning," <https://machinelearnings.co/facial-emotion-recognition-single-rule-1-0-deeplearning-c90c3c2be788>, accessed on May 27th 2018.
[29]Kazemi, V. and Josephine, S., "One millisecond face alignment with an ensemble of regression trees," 27th IEEE Conference on Computer Vision and Pattern Recognition, pp.1867-1874, 2014.
[30]Sagonas, C., Antonakos, E., Tzimiropoulos, G., et al., "300 faces in-the-wild challenge: Database and results," Image and Vision Computing, Vol.47, pp.3-18, 2016.
[31]SOCIETY, P. S. D. A. M. D., <http://www.parkinsonssocietyindia.com/>, accessed on May 28th 2018.
[32]中醫世家, <http://www.zysj.com.cn/lilunshuji/rentijiepouxue/970-12-2.html>, accessed on July 19th 2018.