A Performance Comparison between Deep Learning Network and Haar Cascade on an IoT Device

Bratu, Dragos-Vasile; Moraru, Sorin-Aurel; Guseila, Ligia Georgeta

doi:10.1109/issi47111.2019.9043714

Cited by 4 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the literature, some studies compare the Haar Cascade and deep learning networks. According to [35], CNN outperforms cascade classifiers in plenty of cases. Generally, Haar Cascade is fast because it uses fewer features.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Multi-task Deep Learning System for Face Detection and Age Group Classification for Masked Faces

Yolcu

Öztel

2021

Sakarya University Journal of Science

View full text Add to dashboard Cite

COVID-19 is an ongoing pandemic, and according to experts, using a face mask can reduce the spread of the disease. On the other hand, masks cause occlusion in faces and can create safety problems such as the recognition of the face and the estimation of its age. To prevent the spread of COVID-19, some countries have restrictions according to age groups. Also, in different countries, people in some age groups have safety restrictions such as driving and consuming alcohol, etc. But these rules are difficult to follow due to occlusion in faces. Automated systems can assist in monitoring these rules. In this study, a deep learning-based automated multi-task face detection and age group classification system is proposed for masked faces. The system first detects masked/no-masked-faces. Then, it classifies them according to age-groups. It works for multi-person regardless of indoor/outdoor environment. The system achieved 92.0% average precision score for masked face detection using YOLO with resnet50 network. Also, 83.87% accuracy for classifying age groups with masked faces and 84.48% accuracy for nomasked faces using densenet201 network have been observed. It produced better results compared to the literature. The results are significant because they show that a reliable age classification for masked faces is possible.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Generally, Haar Cascade is fast because it uses fewer features. But detection rate is better in a deep learning model because the deep learning system uses many other features [35]. Usage of the Haar Cascade or deep learning model has advantages and disadvantages.…”

Section: Related Workmentioning

confidence: 99%