ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술지 Pill Detection Model for Medicine Inspection Based on Deep Learning
Cited 0 time in scopus Download 8 time Share share facebook twitter linkedin kakaostory
저자
권혁주, 김휘강, 이성학
발행일
202201
출처
Chemosensors, v.10 no.1, pp.1-17
ISSN
2227-9040
출판사
MDPI
DOI
https://dx.doi.org/10.3390/chemosensors10010004
협약과제
21ZD1100, 대경권 지역산업 기반 ICT 융합기술 고도화 지원사업, 문기영
초록
This paper proposes a deep learning algorithm that can improve pill identification performance using limited training data. In general, when individual pills are detected in multiple pill images, the algorithm uses multiple pill images from the learning stage. However, when there is an increase in the number of pill types to be identified, the pill combinations in an image increase exponentially. To detect individual pills in an image that contains multiple pills, we first propose an effective database expansion method for a single pill. Then, the expanded training data are used to improve the detection performance. Our proposed method shows higher performance improvement than the existing algorithms despite the limited imaging and data set size. Our proposed method will help minimize problems, such as loss of productivity and human error, which occur while inspecting dispensed pills.
키워드
Data augmentation, Deep learning, Mask R-CNN, Object class, Object region, Pill detection
KSP 제안 키워드
As loss, Data Augmentation, Data sets, Detection model, Higher performance, Human error, Identification performance, Learning Stage, Object class, Object region, Pill identification
본 저작물은 크리에이티브 커먼즈 저작자 표시 (CC BY) 조건에 따라 이용할 수 있습니다.
저작자 표시 (CC BY)