Thông tin chung

  English

  Đề tài NC khoa học
  Bài báo, báo cáo khoa học
  Hướng dẫn Sau đại học
  Sách và giáo trình
  Các học phần và môn giảng dạy
  Giải thưởng khoa học, Phát minh, sáng chế
  Khen thưởng
  Thông tin khác

  Tài liệu tham khảo

  Hiệu chỉnh

 
Số người truy cập: 53,147,710

 Building Product Classification System on Bottle Conveyor using Image Processing Techniques
Tác giả hoặc Nhóm tác giả: Huỳnh Hữu Hưng, Phạm Xuân Diệu, Nguyễn Hoàng Hữu
Nơi đăng: Kỷ yếu hội thảo Câu lạc bộ khoa học công nghệ các trường đại học kĩ thuật; Số: 1;Từ->đến trang: 328-331;Năm: 2014
Lĩnh vực: Công nghệ thông tin; Loại: Báo cáo; Thể loại: Trong nước
TÓM TẮT
Nowadays, automation is a necessary factor in the production process. The application of image processing in the automated production line helps to save time and manpower. In this paper, an approach is proposed to detect water bottle that water level is unsatisfactory using Principal Component Analysis method combined with k-nearest neighbor algorithm. At first, the bottle is captured by a webcam, then some preprocessing steps are taken to improve the image quality; after that, we determine a new space to represent the bottle with fewer dimensions than the original space and bottle's characteristics are kept, the last step is using Euclidean distance. Our solution has low computational cost and can execute in real-time. The proposed approach has been tested with high accuracy and is promising.
ABSTRACT
Nowadays, automation is a necessary factor in the production process. The application of image processing in the automated production line helps to save time and manpower. In this paper, an approach is proposed to detect water bottle that water level is unsatisfactory using Principal Component Analysis method combined with k-nearest neighbor algorithm. At first, the bottle is captured by a webcam, then some preprocessing steps are taken to improve the image quality; after that, we determine a new space to represent the bottle with fewer dimensions than the original space and bottle's characteristics are kept, the last step is using Euclidean distance. Our solution has low computational cost and can execute in real-time. The proposed approach has been tested with high accuracy and is promising.
© Đại học Đà Nẵng
 
 
Địa chỉ: 41 Lê Duẩn Thành phố Đà Nẵng
Điện thoại: (84) 0236 3822 041 ; Email: dhdn@ac.udn.vn