메뉴 건너뛰기
소속 기관 / 학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
고객센터 ENG
주제분류

논문 기본 정보

저자정보
(Handong Global University) (Handong Global University) (Handong Global University) (Handong Global University)
저널정보
한국정보기술학회 Proceedings of The International Workshop on Future Technology The Proceedings of ADINTECH 2025
오류 신고하기

피인용 0

검색

    초록·키워드

    The increasing accumulation of plastic waste over recent decades has become a pressing environmental concern. Although public awareness of recycling has grown, studies show that up to 75% of recyclable municipal solid waste is still discarded in landfills. To address this issue, we propose a deep learningbased pipeline for plastic waste sorting that combines the YOLOv8 object detection framework with contrast-enhanced image preprocessing using CLAHE (Contrast-Limited Adaptive Histogram Equalization). CLAHE is applied independently to each RGB channel of the input image and blended with the original to enhance visual features while preserving color fidelity. The proposed system is designed to detect and classify multiple plastic types (PE, PET, PP, PS) from real-world images. Experimental results demonstrate that the model achieves a mean Average Precision (mAP@0.5) of 0.878 and an F1-score of 0.83 at the optimal confidence threshold, indicating robust detection performance. Notably, the balanced blending strategy outperformed both unprocessed and fully enhanced inputs. These results suggest that the integration of adaptive contrast enhancement can significantly improve detection robustness in practical waste sorting systems. Our approach offers a scalable and accurate solution for real-time deployment in automated recycling facilities, contributing to improved plastic recovery and sustainable waste management.

    최근 본 자료 전체보기

      UCI(KEPA) : I410-151-25-02-093929071