인문학
사회과학
자연과학
공학
의약학
농수해양학
예술체육학
복합학
지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 저자정보
초록·키워드
This paper presents an intermediate result of an automatic multiple coin with mixed currencies identification using object detection. It is a part of the grand research with the final objective of developing a real-time object detection system that can simultaneously identify multiple coins and banknotes in mixed currencies in a mobile application. The system is intended for coin and banknotes in mixed currencies in a mobile application. The system is intended for coin and banknote collectors or tourists who have traveled to multiple countries to identify them. The dataset for this research is gathered from open-source platforms such as Kaggle and Google Images and is carefully curated to collect high-quality dataset. This paper will show the result of the trained You Only Look Once (YOLO)v5 algorithm running on a Windows PC using Jupyter Notebook to identify the United States Dollar, European Euro, and Chinese Yuan coin denominations. In the simulation, the model produced a precision score of 0.892, a recall score of 0.932, a map@0.5 score of 0.954, and a map@0.5:9.5 score of 0.837. These results show a promising performance that can be further enhanced by adding more countries to the model and implementing it as an application for the following research stage.
본문·목차
인공지능 문자 인식 모델을 통해 추출된 텍스트로, 일부 오타나 오류가 포함될 수 있으나 지속적으로 개선 중입니다.
오류를 발견하셨다면 해당 부분을 드래그한 후 ' 를 통해 신고해주세요.
오류를 발견하셨다면 해당 부분을 드래그한 후 ' 를 통해 신고해주세요.