To obtain access to full text of journal and articles you must register!
- Article name
- Analysis of face and neck thermograms for users drowsiness recognition based on the Bayesian classifier
- Authors
- Lozhnikov P. S., , lozhnikov@gmail.com, Omsk State Technical University, Omsk, Russia
Sulavko A. E., , sulavich@mail.ru, Omsk State Technical University, Omsk, Russia
Zhumazhanova S. S., , samal_shumashanova@mail.ru, Omsk State Technical University, Omsk, Russia
- Keywords
- IR thermography / thermal images / psychophysiological state / feature space / Bayesian hypothesis formula / convolutional neural networks
- Year
- 2020 Issue 3 Pages 40 - 47
- Code EDN
- Code DOI
- Abstract
- The use of remote technologies for psychophysiological deviations (PPS) identification is currently necessary. The use of such systems has a number of advantages associated with the absence of damage while collecting information about the state of the subject, physical contact of a person with the system, etc. In connection with the spread of the coronavirus infection COVID-19, the security industry is looking for ways to use existing solutions, in particular, based on thermal imaging cameras, for their integration into subjects mass-screening systems. It makes it clear that thermal imaging is an alternative tool in the fight against the spread of the epidemic. Modern systems for assessing human PPS have either insufficient functionality associated with a limited range of identifiable states, or insufficient accuracy in identifying states. The integration of various methods of processing and transforming digital images (thermograms), as well as decision-making methods based on statistical and neural network algorithms, can solve this problem. This article presents the results of studies on identification of several psychophysiological states using methods and algorithms for processing digital images and a neural network decision-making algorithm based on a committee of trained convolutional neural networks.
- Text
- BUY for read the full text of article
- Buy
- 500.00 rub