Designing a Computer-Vision Application: A Case Study for Hand-Hygiene Assessment in an Open-Room Environment

Zhong, Chengzhang; Reibman, Amy R.; Mina, Hansel A.; Deering, Amanda J.

doi:10.3390/jimaging7090170

Cited by 7 publications

(2 citation statements)

References 70 publications

(120 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MobileNet-V2, ResNet-18, Inception-V3, and Augmented Multiscale Deep Infomax (AmDim) networks were used for classification. Zhong et al [9] created a custom dataset with different camera angles. Region of interest areas were labelled manually.…”

Section: Vision-based Workmentioning

confidence: 99%

Evaluation of Hand Washing Procedure Using Vision-Based Frame Level and Spatio-Temporal Level Data Models

Ozakar

Gedikli

2023

Electronics

View full text Add to dashboard Cite

Hand hygiene is obligatory for all healthcare workers and vital for patient care. During COVID-19, adequate hand washing was among recommended measures for preventing virus transmission. A general hand-washing procedure consisting several steps is recommended by World Health Organization for ensuring hand hygiene. This process can vary from person to person and human supervision for inspection would be impractical. In this study, we propose computer vision-based new methods using 12 different neural network models and 4 different data models (RGB, Point Cloud, Point Gesture Map, Projection) for the classification of 8 universally accepted hand-washing steps. These methods can also perform well under situations where the order of steps is not observed or the duration of steps are varied. Using a custom dataset, we achieved 100% accuracy with one of the models, and 94.23% average accuracy for all models. We also developed a real-time robust data acquisition technique where RGB and depth streams from Kinect 2.0 camera were utilized. Results showed that with the proposed methods and data models, efficient hand hygiene control is possible.

show abstract

Section: Vision-based Workmentioning

confidence: 99%

Evaluation of Hand Washing Procedure Using Vision-Based Frame Level and Spatio-Temporal Level Data Models

Ozakar

Gedikli

2023

Electronics

View full text Add to dashboard Cite

show abstract

“…To achieve accuracy, the algorithms need to be trained on large datasets containing many images, both positive and negative. Training increases the algorithm's capacity to detect and locate faces in images [14]. Face detection in figures can be difficult due to a variety of factors such as expression, orientation, posture, position, pixel values, the color of the skin, the absence of spectacles or hair on the face, and changes in camera gain, lighting conditions, and image resolution.…”

Section: Introductionmentioning

confidence: 99%

Enhancing and Securing a Real-Time Embedded Face Recognition System using Raspberry Pi

Alhajim,

Salman FAHAMA,

T.A

2024

J. Al-Qadisiyah Comp. Sci. Math.

View full text Add to dashboard Cite

The modern world is full of data of all kinds; however, the vast amount of video and image data available provides the data set needed for facial recognition. Facial recognition is crucial in safety and surveillance systems that analyze visual data and millions of images. Using facial recognition software, a person's identity can be verified through a variety of media images. For facial recognition, there is a variety of algorithms available. The article presents an approach to a face recognition framework using Haar Cascade, a biometric technology in safety and surveillance systems. It investigates combining standard machine learning techniques for face detection and identification with Raspberry Pi face detection, a cost-effective and easy-to-use embedded system. The system detects faces from indirect and direct images, achieving high speed using the latest Raspberry Pi 4 and Python libraries. The work demonstrates a machine-learning-based design method and a complete embedded system. The face detection accuracy is 92%, and the average time is 0.35 compared to the local binary model (LBP). Many facial recognition algorithms on the web and in literature reviews are vulnerable to image attacks. These methods are very effective in identifying faces in webcams, video streams, images, and videos. This system's use of the Raspberry Pi 4 and advanced Python libraries results in fast and accurate real-time face detection. This paper extends the work first presented at the 12th Iranian/Second International Conference on Machine Vision and Image Processing (MVIP).

show abstract

ResMFuse-Net: Residual-based multilevel fused network with spatial–temporal features for hand hygiene monitoring

Asif,

Xu,

Zhao

et al. 2024

Appl Intell

View full text Add to dashboard Cite

Designing a Computer-Vision Application: A Case Study for Hand-Hygiene Assessment in an Open-Room Environment

Cited by 7 publications

References 70 publications

Evaluation of Hand Washing Procedure Using Vision-Based Frame Level and Spatio-Temporal Level Data Models

Evaluation of Hand Washing Procedure Using Vision-Based Frame Level and Spatio-Temporal Level Data Models

Enhancing and Securing a Real-Time Embedded Face Recognition System using Raspberry Pi

ResMFuse-Net: Residual-based multilevel fused network with spatial–temporal features for hand hygiene monitoring

Contact Info

Product

Resources

About