Metadata (cookie, IP address, location) may be collected for the functioning of the site. If you do not want this data processed, then you should leave the site.
OK
Technology for identifying a person’s state using thermograms of the face and neck
Remote measurement of the temperature of the skin of subjects makes it possible to non-contactly assess a person’s state.
Description of the technology and methods
The proposed solution makes it possible to remotely recognize the psychophysiological state of a person, as well as the presence of an acute phase of a respiratory disease, using a thermal imager and a set of developed software modules.
We have proposed a highly efficient neuro-Bayesian algorithm for continuous identification of subjects' states in real time, based on an ensemble of convolutional neural networks that we previously trained on a sample of thermograms of the face and neck of many subjects. A model of changes in the thermograms of subjects depending on their condition and a method for extracting informative features characterizing the following conditions have been developed:
  • three stages of alcohol intoxication;
  • physical fatigue;
  • stress;
  • drowsiness;
  • the presence of an acute form of respiratory disease.





Project news
20/01/2021
Omsk media: scientists have created a technology for remote personal identification
Using a thermal imager and a set of programs developed using AIConstructor, it will be possible to determine what state a person is in, namely: drowsiness, stress, physical fatigue, the presence of an acute form of respiratory disease, and three stages of alcohol intoxication. Project manager Samal Zhumazhanova spoke about the development and why she was interested in biometric technologies:
https://omskgazzeta.ru/rubrika/sotsium/omskie-uche...
https://bk55.ru/news/article/179391/?utm_source=yx...
https://omsk.mk.ru/science/2021/01/15/uchenye-omsk...
https://news.myseldon.com/ru/news/index/243835210
https://omskzdes.ru/society/73317.html
https://omgtu.ru/l/?eid=62195

Key publications
"Recognition of psychophysiological state from thermograms of the face and neck"
Statistical approach for subject's state identification by face and neck thermograms with small training sample
artificial intelligence, applications, intelligent systems, applications, human aspects of safety, risk engineering
view the work at reader.elsevier.com

Zumazhanova, S.S., Sulavko, A.E., Ponomarev, D.B., Pasenchuk, V.A. Statistical approach for subject's state identification by face and neck thermograms with small training sample // IFAC-PapersOnLine. - Vol. 52. - Issue 25 (2019) 46–51

Existing methods of human psychophysiological states identification are either contact, or do not allow a test without the active involvement of a subject in this procedure. The use of thermal imaging systems has number of advantages: the lack of physical contact with the system, and the fact that temperature is a reliable indicator of health. In the work a new feature space consisting of 465 features divided into static (mean values in each face and neck area, correlation of temperatures between areas in each frame) and dynamic (ratio or correlation of temperatures between areas for subsequent frames) groups is proposed. The evaluation of the informativeness of the obtained features for psychophysiological state recognition is provided. The most informative features were found. Several classifiers were tested: a perceptron-type neural network, a network of quadratic forms, as well as a modified Bayes hypothesis formula, which showed the best result. The predicted probability of errors is less than 0.005.
Optimization of artificial neural networks in problems of processing graphic information to identify the psychophysiological states of a subject
IR thermography, thermal images, psychophysiological state, feature space, Bayesian hypothesis formula, convolutional neural networks
view the work on researchgate.net

Zhumazhanova S.S., Sulavko A.E., Lozhnikov P.S. Optimization of artificial neural networks in problems of processing graphic information to identify the psychophysiological states of a subject // Issues of information protection. – 2020. - № 3. – pp. 40-47.

The use of remote technologies for identifying the psychophysiological states (PPS) of the subject is necessary. The use of such systems has a number of advantages associated with the possibility of hidden control, the absence of physical contact between a person and 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 those based on thermal imaging cameras, for their integration into systems of mass screening of subjects. This made it clear that thermal imaging is an alternative tool for combating the spread of the epidemic. Modern systems for assessing human PFS have either insufficient functionality associated with a limited range of identifiable conditions or insufficient accuracy in identifying conditions. Integrating various methods for processing and converting digital images (thermograms), as well as decision-making methods based on statistical and neural network algorithms, can solve this problem. This paper presents the results of studies on the identification of several psychophysiological states using methods and algorithms for digital image processing and a neural network decision-making algorithm based on a committee of trained convolutional neural networks.
On the effect of the shape of a flaw on its detectability against noise background
random fields, flaw detection, human vision, computer vision, detection reliability, capability matching systems
view the work on researchgate.net

Epifantsev B.N., Zhumazhanova S.S. On the effect of the shape of a flaw on its detectability against noise background // Russian Journal of Nondestructive Testing. 2017. vol. 53. № 1. pp. 62-70

When switching to automatic output-quality testing systems, the aspiration for improving the detectability of insignificant deviations of the output parameters from the statutory ones necessitates the solution of a number of new problems. One of those is assessing the effect of the image-energy spectral density from an axisymmetric flaw on the reliability of its detection against background noise by both human and computer vision systems. Knowing this information is a necessary condition for developing new enhanced testing and evaluating techniques. Results are presented on the probabilities of false alarm and correct detection of axisymmetric circular or rectangular flaws depending on the signal-to-noise ratio (SNR) and the ratio of the flaw radius to the background-fluctuation correlation radius. It has been established that for small SNR, human vision is more effective than machine vision that implements the correlation detector algorithm and the Neyman–Pearson criterion.

Informativeness Assessment of the Thermal Pattern Features of the Face and Neck Region in the Tasks of Recognition of the Subject’s Changed State

facial temperature parameters, thermograms, alcoholic intoxication, psycho-physiological state, face asymmetry, features informativeness.
view the work on researchgate.net

S. S. Zhumazhanova, V. A. Pasenchuk, D. V. Lukin, D. D. Vishnyakov and A. A. Belgorodtsev, "Informativeness Assessment of the Thermal Pattern Features of the Face and Neck Region in the Tasks of Recognition of the Subject’s Changed State," 2019 20th International Conference of Young Specialists on Micro/Nanotechnologies and Electron Devices (EDM), Erlagol, Russia, 2019, pp. 97-101, doi: 10.1109/EDM.2019.8823524.

Diagnosis of the functional state of the subject-operator is usually based on the measurement results of psycho-physiological information. Infrared radiation (IR) from various areas of the human body is directly dependent on their blood filling. The fundamental problem in making decisions about a subject in an altered psycho-physiological state is the determination of the space of identifying features. This article is devoted to the assessment of the informativeness of the identification features obtained from the thermograms of twenty-six anatomical areas of the face and neck of a subject-operator in one of four psycho-physiological states. The conclusions about the prospect of use of certain decision-making algorithms for a given feature space were reached, based on the results of computational experiments.

Analysis of face and neck thermograms for users' drowsiness recognition based on the bayesian classifier

IR THERMOGRAPHY, THERMAL IMAGES, PSYCHOPHYSIOLOGICAL STATE, DROWSINESS, FEATURE SPACE, BAYES HYPOTHESIS FORMULA
https://elibrary.ru/item.asp?id=43024523

Zhumazhanova S.S., Sulavko A.E., Lukin D.V. Analysis of thermograms of the face and neck to recognize the state of drowsiness of users based on the Bayes classifier // Issues of information protection. – 2020. - No. 2. – pp. 24-30

The results of identification studies using methods of thermography in conjunction with methods of pattern recognition and artificial intelligence of the state of drowsiness of users are presented. The analysis of the developed space of signs and decision-making algorithms based on the consistent application of the Bayesian hypothesis formula is carried out.
About the Possibilities of Subject's Changed State Identification on Face Thermograms After Exposure of Different External Stimuli: Analysis of Identification Feature Space and Key Tasks Determination
temperature parameters of the face, thermograms, alcoholic intoxication,
emotional states, face asymmetry
view the work at semanticscholar.org

Zhumazhanova S.S. About the possibilities of subjects changed state identification on face thermograms after exposure of different external stimuli: analysis of identification feature space and key tasks determination // 2018 XIV International Scientific-Technical Conference on Actual Problems of Electronics Instrument Engineering (APEIE). pp. 121-129

The results of an analytical study of the current state in the field of remote recognition of subjects' state are presented. A promising tool in this case is thermal imaging, which has already been represented in medical applications. Field and computational experiments were provided to collect and analyze the thermograms of subjects before and after exposure to external stimuli (images with unpleasant contents, noise, a small dose of alcohol). Conclusions about the possibility of changed state identification even with minor effects on the subject are provided. A new space of identification features of person thermograms is proposed to solve this problem. New challenges for future work are determined.

Human psychophysiological state recognition based on analysis of thermograms of face and neck regions

temperature characteristics of the face, thermograms, method of sequential application of the Bayesian hypothesis formula, face asymmetry, temperature of the carotid artery
view the work at semanticscholar.org
Sulavko A.E., Zhumazhanova S.S. Human psychophysiological state recognition based on analysis of thermograms of face and neck regions // 2017 Dynamics of Systems, Mechanisms and Machines, Dynamics 2017. - 14-16 November, 2017, Omsk, Russia.
A technique for features extraction on thermograms of face and neck regions, characterizing subjects and their following psychophysiological states: normal (calm), drowsiness and a state of alcohol intoxication is proposed. A method of subject-dependent recognition of these states (with the need to create templates of each person's states) is proposed with an error rate of 1.5% and subject-independent state recognition (no templates are required) with an error rate of 24.2%.
The Problem of Biometric Identification of a Subject and Subject's Changed State: Perspectives of New Features Application in Analysis of Face and Neck Thermograms
Pattern recognition, biometric identification, user's variant state detection, encryption key, face thermal images
view the work at semanticscholar.org
Zhumazhanova S.S. The problem of biometric identification of a subject and subjects changed state: perspectives of new features application in analysis of face and neck thermograms // В сборнике: International Conference of Young Specialists on Micro/Nanotechnologies and Electron Devices, EDM. EDM 2018 - Proceedings. 2018. pp. 110-113
The analysis of the current state in the field of subjects biometric identification is provided. The main methods of biometric identification, the process of features space formation used subsequently for decision-making on the subject's access to system resources, as well as new approaches to the use of biometric images for protection of data on electronic documents are considered. The new problem of identification of subject's changed state, and perspectives of using subjects' thermal images for the purpose of determining changed state, is discussed.
Made on
Tilda