Noise robustness evaluation of image processing algorithms for eye blinking detection

•Evaluation of robustness of different eye blinking algorithms.•Development of Low-cost imaging acquisition system and test protocol.•Montecarlo simulations to evaluate the algorithms performance with added Gaussian noise.•Algorithm based on Image correlation offers best performance with low noise l...

Full description

Saved in:
Bibliographic Details
Published in:Measurement : journal of the International Measurement Confederation Vol. 239; p. 115508
Main Authors: Di Nisio, Attilio, D’Alessandro, Vito Ivano, Scarcelli, Giuliano, Lanzolla, Anna Maria Lucia, Attivissimo, Filippo
Format: Journal Article
Language:English
Published: Elsevier Ltd 15.01.2025
Subjects:
Computer vision
Eye blinking
Image processing
Noise
Ophthalmology
Robustness
Computer vision
Robustness
Ophthalmology
Image processing
Noise
Eye blinking
ISSN:0263-2241
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•Evaluation of robustness of different eye blinking algorithms.•Development of Low-cost imaging acquisition system and test protocol.•Montecarlo simulations to evaluate the algorithms performance with added Gaussian noise.•Algorithm based on Image correlation offers best performance with low noise level.•Algorithm based on Local binary pattern provides best results with high noise level. Robust algorithms for eye blinking detection are required due to the effects of noisy environments and varying light conditions on image-based detection methods. This paper compares five non-supervised image-based algorithms for eye blinking detection, evaluating their robustness to additive Gaussian noise. The algorithms were tested on a video dataset acquired using a smartphone and an ophthalmology chin rest. Through Monte Carlo simulation that introduces Gaussian noise at different intensities, we evaluate the algorithms’ precision, sensitivity, and F1-scores for frame classification, True Positive Rate (TPR), False Discovery Rate (FDR) and F1-score for the event detector. The results of experimental tests reveal significant variations in algorithms’ performance with increasing noise levels. Notably, the Image Correlation (IC) algorithm demonstrates superior eye blinking detection capabilities under various noise conditions, emerging as the most robust algorithm among those tested. This distinction highlights the potential of IC for reliable blink detection in noisy environments.
ISSN:0263-2241
DOI:10.1016/j.measurement.2024.115508