Jacek Rumiński

Natalia Kowalczyk, Jacek Rumiński

Face masks are recommended to reduce the transmission of many viruses, especially SARS-CoV-2. Therefore, the automatic detection of whether there is a mask on the face, what type of mask is worn, and how it is worn is an important research topic. In this work, the use of thermal imaging was considered to analyze the possibility of detecting (localizing) a mask on the face, as well as to check whether it is possible to classify the type of mask on the face. The previously proposed dataset of thermal images was extended and annotated with the description of a type of mask and a location of a mask within a face. Different deep learning models were adapted. The best model for face mask detection turned out to be the Yolov5 model in the "nano" version, reaching mAP higher than 97% and precision of about 95%. High accuracy was also obtained for mask type classification. The best results were obtained for the convolutional neural network model built on an autoencoder initially trained in the thermal image reconstruction problem. The pretrained encoder was used to train a classifier which achieved an accuracy of 91%.

Efklidis Katsaros, Piotr K. Ostrowski, Krzysztof Włódarczak et al.

A microcamera firmly attached to a dental handpiece allows dentists to continuously monitor the progress of conservative dental procedures. Video enhancement in video-assisted dental interventions alleviates low-light, noise, blur, and camera handshakes that collectively degrade visual comfort. To this end, we introduce a novel deep network for multi-task video enhancement that enables macro-visualization of dental scenes. In particular, the proposed network jointly leverages video restoration and temporal alignment in a multi-scale manner for effective video enhancement. Our experiments on videos of natural teeth in phantom scenes demonstrate that the proposed network achieves state-of-the-art results in multiple tasks with near real-time processing. We release Vident-lab at https://doi.org/10.34808/1jby-ay90, the first dataset of dental videos with multi-task labels to facilitate further research in relevant video processing applications.

Krzysztof Czuszynski, Jacek Ruminski, Jerzy Wtorek

The study evaluates the influence of natural light conditions on the effectiveness of the linear optical gesture sensor, working in the presence of ambient light only (passive mode). The orientations of the device in reference to the light source were modified in order to verify the sensitivity of the sensor. A criterion for the differentiation between two states: "possible gesture" and "no gesture" was proposed. Additionally, different light conditions and possible features were investigated, relevant for the decision of switching between the passive and active modes of the device. The criterion was evaluated based on the specificity and sensitivity analysis of the binary ambient light condition classifier. The elaborated classifier predicts ambient light conditions with the accuracy of 85.15%. Understanding the light conditions, the hand pose can be detected. The achieved accuracy of the hand poses classifier trained on the data obtained in the passive mode in favorable light conditions was 98.76%. It was also shown that the passive operating mode of the linear gesture sensor reduces the total energy consumption by 93.34%, resulting in 0.132 mA. It was concluded that optical linear sensor could be efficiently used in various lighting conditions.