Abstract
Public services are available to all communities including people with disabilities. One obstacle that impedes persons with disabilities from participating in various community activities and enjoying the various public services available to the community is information and communication barriers. One way to communicate with people with disabilities is with hand gestures. Therefore, the hand gesture technology is needed, in order to facilitate the public to interact with the disability. This study proposes a reliable hand gesture recognition system using the convolutional neural network method. The first step, carried out pre-processing, to separate the foreground and background. Then the foreground is transformed using the discrete wavelet transform (DWT) to take the most significant subband. The last step is image classification with convolutional neural network. The amount of training and test data used are 400 and 100 images repectively, containing five classes namely class A, B, C, # 5, and pointing. This study engendered a hand gesture recognition system that had an accuracy of 100% for dataset A and 90% for dataset B.
Highlights
Nowadays the technology growth leads the development of human physical recognition, one of which is the hand recognition for nonverbal communication
Signaling is a form of nonverbal communication frequently used in sign language and symbols [1]
Gestures have a major role in braiding the communication because it unconsciously -used as supplemental hint to the information that cannot be said verbally [2]
Summary
Nowadays the technology growth leads the development of human physical recognition, one of which is the hand recognition for nonverbal communication. Past research was performed by taking two-dimensional hand gesture contours and converted it into one-dimensional signals using reference values. The four statistical properties of wavelet coefficients extracted and artificial neural networks (ANNs) were adopted to classify the gestures. It obtained the accuracy of 97% with 240 images collected from 20 people [3]. The fuzzy images made it more difficult for classifier to predict the movements performed, so camera type and light intensity are very important in this research. Using both hands for experiment is reduces accuracy
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
