Jacek Ruminski

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.