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: 106,834,580

 Dynamic Gesture Classification for Vietnamese Sign Language Recognition
Tác giả hoặc Nhóm tác giả: Duc-Hoang Vo, Huu-Hung Huynh, Phuoc-Mien Doan and Jean Meunier
Nơi đăng: International Journal of Advanced Computer Science and Applications(IJACSA); Số: 8(3);Từ->đến trang: 415-420;Năm: 2017
Lĩnh vực: Công nghệ thông tin; Loại: Bài báo khoa học; Thể loại: Quốc tế
TÓM TẮT
This paper presents an approach of feature extraction and classification for recognizing continuous dynamic gestures corresponding to Vietnamese Sign Language (VSL).Input data are captured by the depth sensor of a Microsoft Kinect, which is almost not affected by the light of environment.In detail, each gesture is represented by a volume corresponding to a sequence of depth images. The feature extraction stage is performed by dividing such volume into a 3D grid of same-size blocks in which each one is then converted into a scalar value.This step is followed by the process of classification. The well-known method Support Vector Machine (SVM) is employed in this work, and the Hidden Markov Model (HMM) technique is also applied in order to provide a comparison on recognition accuracy. Besides, a dataset of 3000 samples corresponding to30 dynamic gestures in VSL was created by 5 volunteers. The experiments on this dataset to validate the approach and that shows the promising results with average accuracy up to 95%.
ABSTRACT
This paper presents an approach of feature extraction and classification for recognizing continuous dynamic gestures corresponding to Vietnamese Sign Language (VSL).Input data are captured by the depth sensor of a Microsoft Kinect, which is almost not affected by the light of environment.In detail, each gesture is represented by a volume corresponding to a sequence of depth images. The feature extraction stage is performed by dividing such volume into a 3D grid of same-size blocks in which each one is then converted into a scalar value.This step is followed by the process of classification. The well-known method Support Vector Machine (SVM) is employed in this work, and the Hidden Markov Model (HMM) technique is also applied in order to provide a comparison on recognition accuracy. Besides, a dataset of 3000 samples corresponding to30 dynamic gestures in VSL was created by 5 volunteers. The experiments on this dataset to validate the approach and that shows the promising results with average accuracy up to 95%.
© Đại học Đà Nẵng
 
 
Địa chỉ: 41 Lê Duẩn Thành phố Đà Nẵng
Điện thoại: (84) 0236 3822 041 ; Email: dhdn@ac.udn.vn