Related Experiment Video
Updated: Dec 21, 2025
08:05
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
14.6K
An automated Residual Exemplar Local Binary Pattern and iterative ReliefF based COVID-19 detection method using chest
Turker Tuncer1, Sengul Dogan1, Fatih Ozyurt2
1Department of Digital Forensics Engineering, College of Technology, Firat University, Elazig, Turkey.
Summary
A new computer vision method accurately detects COVID-19 from X-ray images. This intelligent system uses advanced feature extraction and selection for reliable diagnosis, achieving 100% accuracy.
Area of Science:
- Medical Imaging
- Computer Vision
- Artificial Intelligence
Background:
- COVID-19, a dangerous virus, caused a global pandemic.
- Radiology relies on X-ray and CT images for COVID-19 diagnosis.
- Automated image analysis is crucial for efficient and accurate disease detection.
Purpose of the Study:
- To propose a novel intelligent computer vision method for automatic COVID-19 detection.
- To enhance diagnostic accuracy and efficiency in medical imaging.
- To develop a lightweight and highly accurate automated detection system.
Main Methods:
- Image preprocessing: resizing and grayscale conversion.
- Feature extraction: Residual Exemplar Local Binary Pattern (ResExLBP).
- Feature selection: iterative ReliefF (IRF). Classifiers: SVM, DT, LD, kNN, SD. Validation: LOOCV, 10-fold CV, holdout.
Main Results:
- The proposed method achieved 100.0% classification accuracy using SVM with 10-fold cross-validation.
- Demonstrated perfect classification rate for COVID-19 detection from X-ray images.
- The ResExLBP and IRF based method proved to be cognitive, lightweight, and highly accurate.
Conclusions:
- The developed computer vision method offers a highly accurate and efficient solution for COVID-19 detection.
- This approach shows significant potential for supporting radiologists in diagnosing COVID-19.
- The system's cognitive, lightweight, and accurate nature makes it suitable for widespread clinical application.
