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
(KOCETI) (YH S&T) (YH S&T) (Biosystem)
저널정보
유공압건설기계학회 드라이브·컨트롤 드라이브·컨트롤 Vol.22 No.4
오류 신고하기

검색

    초록·키워드

    In the recycling process of PET bottles, impurities such as labels, caps, and internal foreign substances degrade material purity and hinder high-quality recycling. Accordingly, accurate identification of contaminated PET bottles during the classification stage is essential for improving recycling efficiency. This study develops an AI-based detection model specialized for identifying foreign substances in PET bottles and evaluates its applicability to unmanned PET bottle collection equipment. Performance differences were experimentally analyzed from three perspectives: image augmentation strategies, labeling methods, and transfer learning–based YOLO model versions— reflecting the characteristics of the domain, where the target objects are limited to PET bottles and the imaging environment remains constant. Based on these evaluations, we propose an effective development direction for AI models optimized for PET bottle classification and contamination detection.

    본문·목차

    최근 본 자료 전체보기

      UCI(KEPA) : I410-151-26-02-094785792