Facial Weakness Analysis and Quantification of Static Images

Zhuang, Yan; McDonald, M; Uribe, Omar; Yin, Xuwang; Parikh, Dhyey; Southerland, Andrew M.; Rohde, Gustavo K.

doi:10.1109/jbhi.2020.2964520

Cited by 16 publications

(13 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Real-World and Public Datasets Efforts have also been made to construct datasets from real-world scenes and make them available for sharing. Recently, Zhuang et al [ 65 ] built a “in-the-wild” static image dataset of facial weakness from YouTube, Google Image, and other public repositories. They combined landmarks and intensity features to detect pathological facial asymmetry, which yielded considerable accuracy.…”

Section: The Facial Recognition System: Applications and Advantagesmentioning

confidence: 99%

“…In a multicenter cross-sectional study of 5796 patients, this method achieved sensitivity of 0.80, specificity of 0.54, and AUC of 0.730. Zhuang et al [ 65 ] has also built a model to identify the asymmetric face of stroke. These studies represented the potential of an automated facial video- or image-based assessing system to detect acute and severe diseases.…”

Section: The Facial Recognition System: Applications and Advantagesmentioning

confidence: 99%

See 1 more Smart Citation

Review on Facial-Recognition-Based Applications in Disease Diagnosis

Qiang

et al. 2022

Bioengineering

View full text Add to dashboard Cite

Diseases not only manifest as internal structural and functional abnormalities, but also have facial characteristics and appearance deformities. Specific facial phenotypes are potential diagnostic markers, especially for endocrine and metabolic syndromes, genetic disorders, facial neuromuscular diseases, etc. The technology of facial recognition (FR) has been developed for more than a half century, but research in automated identification applied in clinical medicine has exploded only in the last decade. Artificial-intelligence-based FR has been found to have superior performance in diagnosis of diseases. This interdisciplinary field is promising for the optimization of the screening and diagnosis process and assisting in clinical evaluation and decision-making. However, only a few instances have been translated to practical use, and there is need of an overview for integration and future perspectives. This review mainly focuses on the leading edge of technology and applications in varieties of disease, and discusses implications for further exploration.

show abstract

Section: The Facial Recognition System: Applications and Advantagesmentioning

confidence: 99%

Section: The Facial Recognition System: Applications and Advantagesmentioning

confidence: 99%

Review on Facial-Recognition-Based Applications in Disease Diagnosis

Qiang

et al. 2022

Bioengineering

View full text Add to dashboard Cite

show abstract

“…After preprocessing the video, the HoG features are extracted for each individual frame. We prefer the HoG features over landmarks features, which are commonly done for vision based facial weakness analysis, due to the fact that landmark-based methods can suffer from inaccuracies in face landmarks localization (17,18), while the HoG features are able to handle local misalignment and capture the detailed gradient features exhibited by facial weakness (15). Since HoG features are high-dimensional, to increase computation efficiency and avoid overfitting, the principal component coefficients are computed from the training dataset to reduce the dimensions of the HoG features to the components that can cover 95% of the variance.…”

Section: Computer Vision Algorithmmentioning

confidence: 99%

“…Finally, a voting classifier aggregates the individual classification results and outputs discrete classification results: normal, left facial weakness, and right facial weakness (Figure 1). In addition, an ensemble of regression trees based facial landmark extractor (20) is used in our study because of its accurate and robust performance (18). The configurations for HoG features are set as follows: the number of orientation bins in a cell is nine, a cell consists of eight by eight pixels, and each block contains four cells in each block is four.…”

Section: Computer Vision Algorithmmentioning

confidence: 99%

Human vs. Machine Learning Based Detection of Facial Weakness Using Video Analysis

et al. 2022

Self Cite

View full text Add to dashboard Cite

BackgroundCurrent EMS stroke screening tools facilitate early detection and triage, but the tools' accuracy and reliability are limited and highly variable. An automated stroke screening tool could improve stroke outcomes by facilitating more accurate prehospital diagnosis and delivery. We hypothesize that a machine learning algorithm using video analysis can detect common signs of stroke. As a proof-of-concept study, we trained a computer algorithm to detect presence and laterality of facial weakness in publically available videos with comparable accuracy, sensitivity, and specificity to paramedics.Methods and ResultsWe curated videos of people with unilateral facial weakness (n = 93) and with a normal smile (n = 96) from publicly available web-based sources. Three board certified vascular neurologists categorized the videos according to the presence or absence of weakness and laterality. Three paramedics independently analyzed each video with a mean accuracy, sensitivity and specificity of 92.6% [95% CI 90.1–94.7%], 87.8% [95% CI 83.9–91.7%] and 99.3% [95% CI 98.2–100%]. Using a 5-fold cross validation scheme, we trained a computer vision algorithm to analyze the same videos producing an accuracy, sensitivity and specificity of 88.9% [95% CI 83.5–93%], 90.3% [95% CI 82.4–95.5%] and 87.5 [95% CI 79.2–93.4%].ConclusionsThese preliminary results suggest that a machine learning algorithm using computer vision analysis can detect unilateral facial weakness in pre-recorded videos with an accuracy and sensitivity comparable to trained paramedics. Further research is warranted to pursue the concept of augmented facial weakness detection and external validation of this algorithm in independent data sets and prospective patient encounters.

show abstract

“…This watermarking based method was designed to certify that biometric data had originated from a genuine sensor. Zhuang et al [13] discuss the experimentation and evaluation of some of the existing feature extraction methods that are used to measure facial weaknesses. Since an open source annotated facial weakness images dataset was unavailable, experimentation involved first creating a facial weakness dataset using images and videos from public repositories like Google Images and YouTube.…”

Section: Sharing Datasets Attributes and Provenancementioning

confidence: 99%

Certifying Provenance of Scientific Datasets with Self-sovereign Identity and Verifiable Credentials

Barclay,

Radha,

Preece

et al. 2020

Preprint

View full text Add to dashboard Cite

In order to increase the value of scientific datasets and improve research outcomes, it is important that only trustworthy data is used. This paper presents mechanisms by which scientists and the organisations they represent can certify the authenticity of characteristics and provenance of any datasets they publish so that secondary users can inspect and gain confidence in the qualities of data they source. By drawing on data models and protocols used to provide self-sovereign ownership of identity and personal data to individuals, we conclude that providing self-sovereignty to digital assets offers a viable approach for institutions to certify qualities of their datasets in a cryptographically secure manner, and enables secondary data users to efficiently perform verification of the authenticity of such certifications. By building upon emerging standards for decentralized identification and cryptographically verifiable credentials, we envisage an infrastructure of tools being developed to foster adoption of metadata certification schemes, and improving the quality of information provided in support of shared data assets.

show abstract

Facial Weakness Analysis and Quantification of Static Images

Cited by 16 publications

References 28 publications

Review on Facial-Recognition-Based Applications in Disease Diagnosis

Review on Facial-Recognition-Based Applications in Disease Diagnosis

Human vs. Machine Learning Based Detection of Facial Weakness Using Video Analysis

Certifying Provenance of Scientific Datasets with Self-sovereign Identity and Verifiable Credentials

Contact Info

Product

Resources

About