Russian Federation
This article examines the impact of image preprocessing on the performance of face detection using the Viola-Jones method. Experiments are presented on the WIDER FACE dataset using three Haar classifiers. The results demonstrate that preprocessing methods such as grayscale, noise reduction, sharpening, histogram equalization, gamma correction, and morphological closing improve key detection performance indicators. Quantitative evaluations of the improvements and an analysis of the effectiveness of the proposed methods are presented.
face detection, Viola-Jones method, image preprocessing, Haar classifiers, quality metrics
1. Metriki v zadachah mashinnogo obucheniya // Habr. – 2025. – URL: https://habr.com/ru/companies/ods/articles/328372/ (data obrascheniya: 10.03.2025). – Tekst : elektronnyy.
2. Raschka, S. Machine Learning with PyTorch and Scikit-Learn / S. Raschka, L. Yuxi, V. Mirjalili. – Birmingham : Packt Publishing Ltd., 2022. – 741 s. – Tekst : neposredstvennyy.
3. Szeliski, R. Computer Vision: Algorithms and Applications / R. Szeliski. – 2-e izd. – [B. m.] : [b. i.], 2022. – 378 s. – Tekst : neposredstvennyy. DOI: https://doi.org/10.1007/978-3-030-34372-9
4. Mochalov, V. P. Algoritm dinamicheskogo raspredeleniya i balansirovki nagruzki v raspredelennyh oblachnyh vychisleniyah / V. P. Mochalov, N. Yu. Bratchenko, D. V. Gosteva // Modelirovanie sistem i processov. – 2024. – T. 17, № 1. – S. 92–102. – DOIhttps://doi.org/10.12737/2219-0767-2024-17-1-92-102. – EDN EWMPYM. – Tekst : neposredstvennyy.
5. Viola, P. Robust Real-Time Face Detection / P. Viola, M. Jones // International Journal of Computer Vision. – 2004. – Vol. 57, № 2. – P. 137–154. – Tekst : neposredstvennyy. DOI: https://doi.org/10.1023/B:VISI.0000013087.49260.fb
6. OpenCV Documentation // OpenCV: [sayt]. – URL: https://docs.opencv.org (data obrascheniya: 10.03.2025). – Tekst : elektronnyy.
7. Gonzalez, R. C. Digital Image Processing / R. C. Gonzalez, R. E. Woods. – 4-e izd. – [B. m.] : [b. i.], 2020. – 120–685 s. – Tekst : neposredstvennyy.
8. Rosebrock, A. Practical Python and OpenCV / A. Rosebrock. – 3-e izd. – [B. m.] : [b. i.], 2016. – 156 s. – Tekst : neposredstvennyy.
9. WIDERFACE: A Face Detection Benchmark // WIDERFACE: [sayt]. – URL: http://shuoyang1213.me/WIDERFACE/ (data obrascheniya: 10.03.2025). – Tekst : elektronnyy.
10. Python Documentation // Python.org: [sayt]. – URL: https://docs.python.org/3/ (data obrascheniya: 10.03.2025). – Tekst : elektronnyy.
11. Müller, A. Introduction to Machine Learning with Python: A Guide for Data Scientists / A. Müller, S. Guido. – 2-e izd. – [B. m.] : O'Reilly, 2023. – 400 s. – Tekst : neposredstvennyy.
12. Kalach, A. V. O vozmozhnostyah primeneniya metoda pochti-periodicheskogo analiza dlya obrabotki izobrazheniy / A. V. Kalach, A. A. Paramonov, S. L. Saharov // Modelirovanie sistem i processov. – 2024. – T. 17, № 3. – S. 44–52. – DOIhttps://doi.org/10.12737/2219-0767-2024-42-50. – EDN HKBSAV. – Tekst : neposredstvennyy.
