Use of AI mechanisms for detecting screen distance
DOI:
https://doi.org/10.34767/SIMIS.2026.01.05Keywords:
Artificial intelligence, Neural networks, Convolutional neural networks, Face detection, Image analysis, MediaPipe, Android StudioAbstract
The thesis explores the use of artificial intelligence mechanisms to detect the user's facial distance from the screen. A mobile application for Android was developed, analyzing the front camera image to estimate the user's distance from the device. The project utilizes the FaceLandmarker model from the MediaPipe library, which identifies key facial landmarks. Using statistical analysis and calibration, the application estimates the distance. This system can be applied in educational and health-related applications, such as alerting children about improper screen proximity. Tests demonstrated that the solution performs well under certain conditions but loses accuracy in low-light environments or at greater distances.
References
A survey of the Vision Transformers and their CNN-Transformer based Variants; Asifullah Khan, Zunaira Rauf, Anabia Sohail, Abdul Rehman, Hifsa Asif, Aqsa Asif, Umair Farooq; arXiv:2305.09880.
Facial Landmark Detection Using Deep Learning: A Comprehensive Approach with Resnet18; Sk. Mastan Sharif, N. Sri Harsha2, Sk. Abdul Subhan, Y. Threeshal; http://dx.doi.org/10.4108/eai.28-4-2025.2358028 (dostęp 20226.01.18)
Fast Facial Landmark Detection and Applications: A Survey; Kostiantyn Khabarlak, Larysa Koriashkina; arXiv:2101.10808 [cs.CV]
Overcoming classic challenges for artificial neural networks by providing incentives and practice; Kazuki Irie, Brenden M. Lake; arXiv:2410.10596 [cs.AI]
Zhao, X., Wang, L., Zhang, Y. et al. A review of convolutional neural networks in computer vision. Artif Intell Rev 57, 99 (2024). https://doi.org/10.1007/s10462-024-10721-6 (dostęp 2026.01.18)
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
