及时准确地评价面瘫患者的面神经损伤程度，有助于医生为患者选择合适的治疗和康复方案。临床常用的人工量表评价法过于主观，而基于计算机视觉的面瘫评价方法更加客观。本文以利用计算机视觉对面瘫进行客观评价的研究进展为主要内容，从面部特征的提取，面部不对称性的量化和面瘫程度的自动评价等方面出发，分析了特征点法、局部区域法、表情法和神经网络法这四种评价方法的发展与不足，并对面瘫的客观评价方法的发展趋势进行了展望。

[1] Farahvash MR, Yaghoobi A, Farahvash B, et al. The extratemporal facial nerve and its branches: analysis of 42 hemifacial dissections in fresh Persian (Iranian) cadavers[J]. Aesthetic Surgery Journal, 2013, 33(2):201-208.

[2] 冯殿恩, 靳令经, 王鹏. 面瘫与面肌痉挛[M].上海: 上海科学技术出版社, 2011.

[3] 金炳旭, 唐纯志. 针灸治疗周围性面瘫研究进展[J]. 甘肃中医, 2005, 18(5):28-30.

[4] Mishima K, Sugahara T. Review article: analysis methods for facial motion[J]. Japanese Dental Science Review, 2009, 45(1): 4-13.

[5] Zhai MY, Feng GD, Gao ZQ. Facial grading system: physical and psychological impairments to be considered[J]. Journal of Otology, 2008, 3(2): 61-67.

[6] Hashmat P. Determining normal and abnormal lip shapes during movement for use as a surgical outcome measure[D]. Cardiff, UK: Cardiff University, 2012.

[7] 杨万章, 吴芳, 张敏. 周围性面神经麻痹的中西医结合评定及疗效标准 (草案)[J]. 中西医结合心脑血管病杂志, 2005, 3(9):786-787.

[8] Li Y, Feng GD, Tian X, et al. Agreement between house-brackmann grading system and facial nerve grading system 2.0 in patients with facial nerve paralysis[J]. Chinese Journal of Otology, 2014, 12(3): 361.

[9] 李雪，廖品东，罗敏，等. 评价周围性面瘫的“口眼喎僻度指数”研究[J]. 中国针灸,2011,31(9)：837-839.

Li X, Liao PD,Luo M, et al. Deviation index of eye and mouth on peripheral facial paralysis [J].Chinese Acupuncture &Moxibustion, 2011,31 (9): 837-839.

[10] Frey M, Giovanoli P, Gerber H, et al. Three-dimensional video analysis of facial movements: a new method to assess the quantity and quality of the smile[J]. Plastic and Reconstructive Surgery, 1999, 104(7): 2032-2039.

[11] Wachtman GS, Cohn JF, Vanswearingen JM, et al. Automated tracking of facial features in patients with facial neuromuscular dysfunction[J]. Plastic & Reconstructive Surgery, 2001, 107(5): 1124-1133.

[12] Dong J, Ma L, Li Q, et al. An approach for quantitative evaluation of the degree of facial paralysis based on salient point detection[C]// International Symposium on Intelligent Information Technology Application Workshops. Washington, DC, USA: IEEE Computer Society, 2008: 483-486.

[13] Nishida T, Chen YW, Matsushiro N, et al. An image based quantitative evaluation method for Facial Paralysis[C]// International Conference on Software Engineering and Data Mining. Chengdu, China: IEEE Press, 2010.

[14] 蔡志刚, 俞光岩, 王勇, 等. 计算机临床量化面神经功能评价系统的应用研究[J]. 中华口腔医学杂志, 2001, 36(6):454-456.

Cai ZG, Yu GY, Wang Y, et al. Application research of computer clinical quantitative facial nerve function evaluation system[J]. Chinese Journal of Stomatology, 2001, 36(6): 454-456.

[15] Berlin N, Berssenbrügge P, Runte C, et al. Quantification of facial asymmetry by 2D analysis - A comparison of recent approaches[J]. Journal of Cranio-Maxillofacial Surgery, 2014, 42(3): 265-271.

[16] Karuppusamy S, Jerome J, Shankar N. Embedded implementation of facial landmarks detection using extended active shape model approach[C]// International Conference on Embedded Systems. IEEE Press, 2014: 265-270.

[17] Yoshihara H, Seo M, Ngo TH, et al. Automatic feature point detection using deep convolutional networks for quantitative evaluation of facial paralysis[C]// 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics. Datong, China: IEEE Press, 2016: 811-814.

[18]  McGrenary S, O'Reilly BF, Soraghan JJ. Objective grading of facial paralysis using artificial intelligence analysis of video data[C]//18th IEEE Symposium on Computer-Based Medical Systems. Dublin, Ireland: IEEE Press, 2005: 587-592.

[19] Tomat LR, Manktelow RT. Evaluation of a new measurement tool for facial paralysis reconstruction[J]. Plastic and Reconstructive Surgery, 2005, 115(3): 696-704.

[20] Liu L, Cheng G, Dong J, et al. Evaluation of facial paralysis degree based on regions[C]// Third International Conference on Knowledge Discovery and Data Mining. Phuket, Thailand: IEEE Computer Society, 2010: 514-517.

[21] Wang T, Zhang S, Dong J, et al. Automatic evaluation of the degree of facial nerve paralysis[J]. Multimedia Tools and Applications, 2016, 75(19):11893-11908.

[22] Codari M, Pucciarelli V, Stangoni F, et al. Facial thirds?based evaluation of facial asymmetry using stereophotogrammetric devices: Application to facial palsy subjects[J]. Journal of Cranio-Maxillofacial Surgery, 2017, 45(1):76-81.

[23] Meier-Gallati V, Scriba H, Fisch U. Objective scaling of facial nerve function based on area analysis (OSCAR)[J]. Otolaryngology - Head and Neck Surgery, 1998, 118(4): 545-550.

[24] Tanaka T, Nemoto J, Ohta M, et al. The evaluation of facial palsy by amount of feature point movements at facial expressions[C] //IEEE 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. San Francisco, CA, USA: IEEE Press, 2004, 2: 1463-1466.

[25] He S, Soraghan JJ, O’ Reilly BF. Biomedical image sequence analysis with application to automatic quantitative assessment of facial paralysis[J]. EURASIP Journal on Image and Video Processing, 2007, 2007: 081282.

[26] Hontanilla B, Aubá, C. Automatic three-dimensional quantitative analysis for evaluation of facial movement[J]. Journal of Plastic, Reconstructive & Aesthetic Surgery, 2008, 61(1):18-30.

[27] Katsumi S, Esaki S, Hattori K, et al. Quantitative analysis of facial palsy using a three-dimensional facial motion measurement system[J]. Auris Nasus Larynx, 2015, 42(4):275-283.

[28] Hsu GS, Kang JH, Huang WF. Deep hierarchical network with line segment learning for quantitative analysis of facial palsy[J]. IEEE Access, 2019, 7: 4833-4842.

[29] Guo ZX, Shen M, Duan L, et al. Deep assessment process: Objective assessment process for unilateral peripheral facial paralysis via deep convolutional neural network[C]// IEEE International Symposium on Biomedical Imaging. Melbourne, Australia: IEEE Press, 2017:135-138.

[30] Song A, Wu Z, Ding, X, et al. Neurologist standard classification of facial nerve paralysis with deep neural networks[J]. Future Internet, 2018, 10(11): 111.

[31] Sajid M, Shafique T, Baig MJA, et al. Automatic grading of palsy using asymmetrical facial features: a study complemented by new solutions[J]. Symmetry, 2018, 10(7): 242.

[32] Samsudin WSW, Sundaraj K. Image processing on facial paralysis for facial rehabilitation system: a review[C]// 2012 IEEE International Conference on Control System, Computing and Engineering (ICCSCE). Penang, Malaysia: IEEE Press, 2012:259-263.