当前位置: X-MOL 学术Biomed. Phys. Eng. Express › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
SVM classification of facial functions based on facial landmarks and animation Units
Biomedical Physics & Engineering Express ( IF 1.3 ) Pub Date : 2021-07-16 , DOI: 10.1088/2057-1976/ac107c
Amira Gaber 1 , Mona F Taher 1 , Manal Abdel Wahed 1 , Nevin Mohieldin Shalaby 2
Affiliation  

Quantitative assessment and classification of facial paralysis (FP) are essential for treatment selection and progress evaluation of the condition. As part of a comprehensive framework towards this goal, this study aims to classify five normal facial functions: smiling, eye closure, raising the eyebrows, blowing cheeks, and whistling as well as the rest state. 3D facial landmarks and facial animation units (FAUs) were obtained using the Kinect V2, a fast and cost-effective depth camera. These were used to compute the features used in a Support Vector Machine (SVM) classifier. A dataset of 1650 records from 50 normal subjects was compiled for this study. The performances of different SVM kernel models were tested with different feature groups. The best performance (Accuracy=96.7%, Sensitivity=90.2%, and Specificity=98%) was found when using the RBF kernel model applied on just nine differences in FAUs. This research will be developed and extended to include FP classification.



中文翻译:

基于面部特征点和动画单元的面部功能SVM分类

面瘫 (FP) 的定量评估和分类对于治疗选择和病情进展评估至关重要。作为实现这一目标的综合框架的一部分,本研究旨在对五种正常的面部功能进行分类:微笑、闭眼、扬眉、吹脸、吹口哨以及休息状态。使用快速且经济高效的深度相机 Kinect V2 获得 3D 面部标志和面部动画单元 (FAU)。这些用于计算支持向量机 (SVM) 分类器中使用的特征。为这项研究编制了来自 50 名正常受试者的 1650 条记录的数据集。使用不同的特征组测试了不同 SVM 内核模型的性能。最佳性能(准确度=96.7%,灵敏度=90.2%,和特异性 = 98%)是在使用仅应用于 FAU 的九个差异的 RBF 内核模型时发现的。这项研究将得到发展和扩展,以包括 FP 分类。

更新日期:2021-07-16
down
wechat
bug