Recognition of Facial Action Units with Action Unit Classifiers and an Association Network

2015 ◽  
pp. 672-683
Author(s):  
Junkai Chen ◽  
Zenghai Chen ◽  
Zheru Chi ◽  
Hong Fu
Keyword(s):  
Association Network ◽  
Action Unit ◽  
Facial Action ◽  
Action Units

scholarly journals Classify Elderly Pain Severity from Open-Source Automatically Video Clip Facial Action Units Analysis. A Study from the Integrated Pain Artificial Intelligence Network (I-PAIN) Data Repository.

2021 ◽  
Author(s):  
Patama Gomutbutra ◽  
Adisak Kittisares ◽  
Atigorn Sanguansri ◽  
Noppon Choosri ◽  
Passakorn Sawaddiruk ◽  
...  
Keyword(s):  
Machine Learning ◽  
Open Source ◽  
Video Clip ◽  
Pain Severity ◽  
Support Vector ◽  
Action Unit ◽  
Multilayer Perception ◽  
Facial Action ◽  
Action Units ◽  
Analysis Experiment

Abstract Background: It is increasingly interesting to monitor pain severity in elderly individuals by applying machine learning models. In previous studies, OpenFace© - a well-known automated facial analysis algorithm, was used to detect facial action units (FAUs) that initially need long hours of human coding. However, OpenFace© developed from the dataset that dominant young Caucasians who were illicit pain in the lab. Therefore, this study aims to evaluate the accuracy and feasibility of the model using data from OpenFace© to classify pain severity in elderly Asian patients in clinical settings.Methods: Data from 255 Thai individuals with chronic pain were collected at Chiang Mai Medical School Hospital. The phone camera recorded faces for 10 seconds at a 1-meter distance briefly after the patients provided self-rating pain severity. For those unable to self-rate, the video was recorded just after the move, which illicit pain. The trained assistant rated each video clip for the Pain Assessment in Advanced Dementia (PAINAD). The classification of pain severity was mild, moderate, or severe. OpenFace© process video clip into 18 FAUs. Five classification models were used, including logistic regression, multilayer perception, naïve Bayes, decision tree, k-nearest neighbors (KNN), and support vector machine (SVM). Results: Among the models that included only FAU described in the literature (FAUs 4, 6, 7, 9, 10, 25, 26, 27 and 45), multilayer perception yielded the highest accuracy of 50%. Among the machine learning selection features, the SVM model for FAU 1, 2, 4, 7, 9, 10, 12, 20, 25, 45, and gender yielded the best accuracy of 58%. Conclusion: Our open-source automatic video clip facial action unit analysis experiment was not robust for classifying elderly pain. Retraining facial action unit detection algorithms, enhancing frame selection strategies, and adding pain-related functions may improve the accuracy and feasibility of the model.

Tunneled Latent Variables Method for Facial Action Unit Tracking

2009 ◽  
Vol 35 (2) ◽  
pp. 198-201 ◽  
Author(s):  
Lei WANG ◽  
Bei-Ji ZOU ◽  
Xiao-Ning PENG
Keyword(s):  
Latent Variables ◽  
Action Unit ◽  
Facial Action

Multi-view facial action unit detection via DenseNets and CapsNets

2021 ◽  
Author(s):  
Dakai Ren ◽  
Xiangmin Wen ◽  
Jiazhong Chen ◽  
Yu Han ◽  
Shiqi Zhang
Keyword(s):  
Action Unit ◽  
Facial Action ◽  
Action Unit Detection

scholarly journals Assessing Automated Facial Action Unit Detection Systems for Analyzing Cross-Domain Facial Expression Databases

Sensors ◽  
2021 ◽  
Vol 21 (12) ◽  
pp. 4222
Author(s):  
Shushi Namba ◽  
Wataru Sato ◽  
Masaki Osumi ◽  
Koh Shimokawa
Keyword(s):  
Affective Computing ◽  
Detection System ◽  
Characteristic Curve ◽  
Unmet Need ◽  
Systematic Evaluation ◽  
Dynamic Mode ◽  
Coding System ◽  
Static Mode ◽  
Action Unit ◽  
Facial Action

In the field of affective computing, achieving accurate automatic detection of facial movements is an important issue, and great progress has already been made. However, a systematic evaluation of systems that now have access to the dynamic facial database remains an unmet need. This study compared the performance of three systems (FaceReader, OpenFace, AFARtoolbox) that detect each facial movement corresponding to an action unit (AU) derived from the Facial Action Coding System. All machines could detect the presence of AUs from the dynamic facial database at a level above chance. Moreover, OpenFace and AFAR provided higher area under the receiver operating characteristic curve values compared to FaceReader. In addition, several confusion biases of facial components (e.g., AU12 and AU14) were observed to be related to each automated AU detection system and the static mode was superior to dynamic mode for analyzing the posed facial database. These findings demonstrate the features of prediction patterns for each system and provide guidance for research on facial expressions.

Pain Assessment Using Facial Action Units and Bayesian Network

2021 ◽  
Author(s):  
Wenqiang Guo ◽  
Ziwei Xu ◽  
Zhigao Guo ◽  
Lingling Mao ◽  
Yongyan Hou ◽  
...  
Keyword(s):  
Bayesian Network ◽  
Pain Assessment ◽  
Facial Action ◽  
Action Units

Automated Pain Estimation based on Facial Action Units from Multi-Databases

2021 ◽  
Author(s):  
Manh Tu Vu ◽  
Marie Beurton-Aimar ◽  
Pierre-yves Dezaunay ◽  
Marine Cotty Eslous
Keyword(s):  
Facial Action ◽  
Action Units

scholarly journals FACSGen: A Tool to Synthesize Emotional Facial Expressions Through Systematic Manipulation of Facial Action Units

2010 ◽  
Vol 35 (1) ◽  
pp. 1-16 ◽  
Author(s):  
Etienne B. Roesch ◽  
Lucas Tamarit ◽  
Lionel Reveret ◽  
Didier Grandjean ◽  
David Sander ◽  
...  
Keyword(s):  
Facial Expressions ◽  
Emotional Facial Expressions ◽  
Facial Action ◽  
Action Units ◽  
Systematic Manipulation

Quality characteristic decoupling planning of different meta-action units for computer numerical control machine tool

2019 ◽  
Vol 234 (14) ◽  
pp. 2760-2770 ◽  
Author(s):  
Yan Ran ◽  
Teng Zhang ◽  
Zongyi Mu ◽  
Genbao Zhang ◽  
Hongwei Wang ◽  
...  
Keyword(s):  
Machine Tool ◽  
Optimization Method ◽  
Computer Numerical Control ◽  
Quality Characteristics ◽  
Numerical Control ◽  
Quality Characteristic ◽  
Control Machine Tool ◽  
Action Unit ◽  
Action Units ◽  
Control Machine

Since computer numerical control machine tool is composed of multiple meta-action units to achieve one specific function, including the meta-action units' own quality, it still needs to control the coupling relationships among different meta-action units' quality characteristics to guarantee the whole machine's quality. In this article, a method of quality characteristic decoupling planning based on meta-action unit for computer numerical control machine tool was proposed. Firstly, the coupling constraint models based on meta-action unit were established. Secondly, the comprehensive coupling strengths of meta-action units were calculated and introduced into the design structure matrices. Thirdly, multidisciplinary design optimization method was adopted to obtain the optimized control sequence of different meta-action units' quality characteristics. What is more, automatic pallet changer rotary motion of computer numerical control machine tool was taken as an example to illustrate the rightness and effectiveness of this method.

Sign in / Sign up

Export Citation Format

Share Document