TY - GEN
T1 - Finger spelling recognition using neural network
AU - Lim, Kian Ming
AU - Tan, Kok Seang
AU - Tan, Alan W.C.
AU - Tan, Shing Chiang
AU - Lee, Chin Poo
AU - Razak, Siti Fatimah Abdul
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015
Y1 - 2015
N2 - Finger spelling is a way of communication by expressing words using hand signs in order to ensure deaf and dumb community can communicate with others effectively. Therefore, a system that can understand finger spelling is needed. As a result of that, this work is conducted to primarily develop a tutoring system for finger spelling. To develop a robust real-time finger spelling tutoring system, it is necessary to ensure the accuracy of the finger spelling recognition. Even though there are existing solutions available for a decade, but most of them are just focusing on improving accuracy rate without implementing their solutions as a complete tutoring system for finger spelling. Consequently, it inspires this research project to develop a tutoring system for finger spelling. Microsoft Kinect sensor is used to acquire color images and depth images of the finger spells. Depth images are used to perform segmentation on the color images. After that, the segmented images are used as input and pass into a two hidden layers backpropagation neural network for classification.
AB - Finger spelling is a way of communication by expressing words using hand signs in order to ensure deaf and dumb community can communicate with others effectively. Therefore, a system that can understand finger spelling is needed. As a result of that, this work is conducted to primarily develop a tutoring system for finger spelling. To develop a robust real-time finger spelling tutoring system, it is necessary to ensure the accuracy of the finger spelling recognition. Even though there are existing solutions available for a decade, but most of them are just focusing on improving accuracy rate without implementing their solutions as a complete tutoring system for finger spelling. Consequently, it inspires this research project to develop a tutoring system for finger spelling. Microsoft Kinect sensor is used to acquire color images and depth images of the finger spells. Depth images are used to perform segmentation on the color images. After that, the segmented images are used as input and pass into a two hidden layers backpropagation neural network for classification.
KW - backpropagation neural network
KW - finger spelling recognition
KW - Miscrosoft Kinect sensor
UR - http://www.scopus.com/inward/record.url?scp=84966479862&partnerID=8YFLogxK
U2 - 10.1109/SCORED.2015.7449437
DO - 10.1109/SCORED.2015.7449437
M3 - Conference contribution
AN - SCOPUS:84966479862
T3 - 2015 IEEE Student Conference on Research and Development, SCOReD 2015
SP - 78
EP - 81
BT - 2015 IEEE Student Conference on Research and Development, SCOReD 2015
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - IEEE Student Conference on Research and Development, SCOReD 2015
Y2 - 13 December 2015 through 14 December 2015
ER -