Approach to image preprocessing for household waste classification in circular economy

Скорочена інформація про документ
dc.contributor.authorDerzhak, V.V.
dc.contributor.authorMazurets, O.V.
dc.contributor.authorМазурець, Олександр Вікторович
dc.date.accessioned2025-12-10T10:14:01Z
dc.date.available2025-12-10T10:14:01Z
dc.date.issued2025
dc.description.abstractThis work proposes an intelligent image preparation pipeline for stable multi-class classification of household waste in field conditions, emphasizing data quality control rather than architectural complexity. A coordinated scheme of non-reference quality assessment, guided selection of training frames, and carefully designed partitioning protocols significantly improves model stability under realistic variations in lighting, background contamination, small object occlusions and inter-site distribution shifts. Using MobileNetV3-Small with standardized hyperparameters, the study demonstrates higher reliability, reduced metric variability, and consistent behavior across critical subsets without sacrificing class representativeness. The methodology is reproducible, hardware-efficient, and suitable for industrial sorting systems, supporting circular economy practices by increasing fraction purity and reducing material loss. Future work will extend cross-site benchmarking and explore threshold dynamics for different waste categories.
dc.identifier.citationDerzhak V.V., Mazurets O.V. Approach to image preprocessing for household waste classification in circular economy. Resource-Saving Technologies of Apparel, Textile & Food Industry. Proceedings of International Scientific and Practical Conference. November 20, 2025. Khmelnytskyi, Ukraine. Pp. 319-323.
dc.identifier.urihttps://elar.khmnu.edu.ua/handle/123456789/19937
dc.language.isoen
dc.titleApproach to image preprocessing for household waste classification in circular economy
dc.typeСтаття
Файли
Контейнер файлів
Зараз показуємо 1 - 1 з 1
Ескіз
Назва:
khmnu2025-319-323.pdf
Розмір:
216.62 KB
Формат:
Adobe Portable Document Format
Завантажити
Ліцензійна угода
Зараз показуємо 1 - 1 з 1
Назва:
license.txt
Розмір:
4.26 KB
Формат:
Item-specific license agreed upon to submission
Опис:
Завантажити
Зібрання
Кафедра комп’ютерних наук