 |
Publisher: Peytchinski Publishing Ltd.
ISSN: 1312-773X (Online)
Issue: 2026, vol. 32, issue1
Subject Area: Medicine
-
DOI: 10.5272/jimab.2026321.6698
Published online: 22 January 2026
Original article
J of IMAB. 2026 Jan-Mar;32(1):6698-6702
RISK ANALYSIS THROUGH IMAGE RECOGNITION
Nikola Sabev1
, Ivan Ralev2
,
1) Department of medical and clinical diagnostic activities, University of Ruse, Bulgaria.
2) Department of Machine Science, Machine Elements, Engineering Graphics and Physics, University of Ruse, Bulgaria.
ABSTRACT:
Purpose: The paper examines the classical techniques used for imaging diagnostics. A variant of the implementation of a system for recognition by external signs is proposed. The physiological expressiveness of deviations in behavioral reactions is examined. The possibilities and problems of a computer system applied to determine the health status of a group of people through the analysis of external signs extracted from the visualization of previously captured images are described.
Materials/Methods: Examines research conducted by a number of researchers on the behavior of groups of people with common physical characteristics. A computerized system for image recognition and analysis among groups in public places is proposed and reviewed.
Results: Classical image recognition is widely used in medicine. A significant problem still remains the small and incomplete research on the psycho-physical expression of people's behavioral traits.
Conclusion: The use of analysis by external signs can improve management and decision-making during a pandemic, disaster or anarchic situation.
Keywords: image recognition, computer image processing,
- Download FULL TEXT /PDF 1568 KB/
Please cite this article as: Sabev N, Ralev I. Risk analysis through image recognition. J of IMAB. 2026 Jan-Mar;32(1):6698-6702. [Crossref - 10.5272/jimab.2026321.6698]
Correspondence to: Ivan Ralev, University of Ruse; 8, Studentska Str., 7017 Ruse, Bulgaria; E-mail: iralev@uni-ruse.bg
REFERENCES:
1. Nattkemper TW. Multivariate image analysis in biomedicine. J Biomed Inform. 2004 Oct;37(5):380-91. [PubMed]
2. Piccinini F, Bevilacqua A. Colour Vignetting Correction for Microscopy Image Mosaics Used for Quantitative Analyses. Biomed Res Int. 2018 Jun 7;2018:7082154. [PubMed ]
3. Bulnes LC, Mariën P, Vandekerckhove M, Cleeremans A. The effects of Botulinum toxin on the detection of gradual changes in facial emotion. Sci Rep. 2019 Aug 13;9(1):11734. [PubMed]
4. Allyn J, Allou N, Vidal C, Renou A, Ferdynus C. Adversarial attack on deep learning-based dermatoscopic image recognition systems: Risk of misdiagnosis due to undetectable image perturbations. Medicine (Baltimore). 2020 Dec 11;99(50):e23568. [PubMed]
5. Abbasi SF, Bilal M, Mukherjee T, Churm J, Pournik O, Epiphaniou G, et al. Deep Learning-Based Synthetic Skin Lesion Image Classification. Stud Health Technol Inform. 2024 Aug 22;316:1145-1150. [PubMed]
6. Panayotov K. [Disabilities in humans - a medico-social phenomenon.] [monograph] Avangard print, Ruse. 2023; 120p. [in Bulgarian]
7. Curran T, Ma C, Liu X, McDuff D, Narayanswamy G, Stergiou G, et al. Estimating Blood Pressure with a Camera: An Exploratory Study of Ambulatory Patients with Cardiovascular Disease. ArXiv. 2 Mar 2025: 2503.00890[Crossref]
Received: 12 August 2025
Published online: 22 January 2026