Skip to main navigation menu Skip to main content Skip to site footer

Gaphic Engineering and Design

Vol. 38 No. 04 (2023): Proceedings of Faculty of Technical Sciences

THE INFLUENCE OF NOISE AND BLUR ON FACE DETECTION IN PHOTOGRAPHS

DOI:
https://doi.org/10.24867/22EF02Saric
Submitted
October 24, 2022
Published
2023-04-04

Abstract

Face detection is one of the most widely used computer vision applications. Face detection is a fundamental problem in computer vision and pattern recognition. Face detection is a computer technology that determines the location and size of a human face in digital images. Given an image, the goal of face recognition is to determine if there are faces and return a bounding box for each detected face. Face detection is a necessary first step for all face analysis algorithms, including face alignment, face recognition, face verification, and face parsing. For the purposes of the experiment the influence of the Gaussian Blur Radius and noise was analyzed (Gaussian Noise Amount) in the Adobe Photoshop software on the number of recognized faces in the photos that were used as simulated samples using the Every Pixel software. This software was used to test the extent to which blurring and noise affect the ability of the software to recognize faces in given simulated samples.

References

[1] G. Boesch. “Face Detection: Real-time applications with deep learning (2022 Guide).” viso.ai. https://viso.ai/deep-learning/face-detection-overview/ (pristupljeno: septembar 23, 2022).
[2] H. Koren.”Correlating the Performance of Computer Vision Algorithms with Objective Image Quality Metrics.” imatest.com. https://www.imatest.com/2022/06/correlating-the-performance-of-computer-vision-algorithms-with-objective-image-quality-metrics/?mc_cid=3a22e12045&mc_eid=266c6f68c9 (pristupljeno: septembar 10, 2022).