In factory automation, efforts are being made to increase productivity while maintaining high-quality products. In this study, a CNN network structure was designed to quickly and accurately recognize a cigarette located in the opposite direction or a cigarette with a loose end in an automated facility rotating at high speed for cigarette production. Tobacco inspection requires a simple network structure and fast processing time and performance. The proposed network has an excellent accuracy of 96.33% and a short processing time of 0.527 msec, showing excellent performance in learning time and performance compared to other CNN networks, confirming its practicality. In addition, it was confirmed that efficient learning is possible by increasing a small number of image data through a rotation conversion method.
목차
ABSTRACT 1. 서론 2. 궐련 담배 제조 공정 및 CNN 연구 2.1 궐련 담재 제조 공정 2.3 CNN을 이용한 이미지 분류 3. 자료수집 및 제안된 네트워크 구조 3.1 학습 자료수집 3.2 데이터 증강 3.3 제안된 네트워크 구조 4. 실험결과 및 평가 4.1 실험 설정 4.2 네트워크 학습 결과 비교 4.3 네트워크 성능 평가 및 결과 5. 결론 References
키워드
공장자동화궐련 담배 검출컨볼루션 신경망데이터 증강Factory automationCigarette detectionConvolutional neural networkData augmentation
저자
박희문 [ Hee-Mun Park | Dept. of Computer ad Mechatronics Eng, Gyeongsang National University ]
김민 [ Min Kim | Dept. of Mechatronics Eng, Gyeongsang National University ]
전향식 [ Hyang-Sig Jun | Unmanned Aircraft System Research Division, KARI ]
황광복 [ Kwang-Bok Jung | Dept. of Smart Software Eng, Yonam Institute of Tech. ]
박진현 [ Jin-Hyun Park | Member, Dept. of Mechatronics Eng, Gyeongsang National University ]
Corresponding Author