A new data glove approach for Malaysian sign language detection

• Main Authors: Shukor, Ahmad Zaki, Miskon, Muhammad Fahmi, Jamaluddin, Muhammad Herman, Ali @ Ibrahim, Fariz, Asyraf, Mohd Fareed, Bahar, Mohd Bazli
• Format: Article
• Language: English
• Published: Elsevier B.V. 2015
• Online Access: http://eprints.utem.edu.my/id/eprint/18122/2/JournalScopus-Main-Procedia2015iris.pdf; http://eprints.utem.edu.my/id/eprint/18122/; http://www.sciencedirect.com/science/article/pii/S1877050915037771; http://dx.doi.org/10.1016/j.procs.2015.12.276
• Institution: Universiti Teknikal Malaysia Melaka

A normal human being sees, listens, and reacts to his/her surroundings. There are some individuals who do not have this important blessing. Such individuals, mainly deaf and dumb, depend on communication via sign language to interact with others. However, communication with ordinary individuals is a major concern for them since not everyone can comprehend their sign language. Furthermore, this will cause a problem for the deaf and dumb communities to interact with others, particularly when they attempt to involve with educational, social and work environments. In this research, the objectives are to develop a sign language translation system in order to assist the hearing or speech impaired people to communicate with normal people, and also to test the accuracy of the system in interpreting the sign language. As a first step, the best method in gesture recognition was chosen after reviewing previous researches. The configuration of the data glove includes 10 tilt sensors to capture the finger flexion, an accelerometer for recognizing the motion of the hand, a microcontroller and Bluetooth module to send the interpreted information to a mobile phone. Firstly the performance of the tilt sensor was tested. Then after assembling all connections, the accuracy of the data glove in translating some selected alphabets, numbers and words from Malaysian Sign Language is performed. The result for the first experiment shows that tilt sensor need to be tilted more than 85 degree to successfully change the digital state. For the accuracy of 4 individuals who tested this device, total average accuracy for translating alphabets is 95%, numbers is 93.33% and gestures is 78.33%. The average accuracy of data glove for translating all type of gestures is 89%. This fusion of tilt sensors and accelerometer could be improved in the future by adding more training and test data as well as underlying frameworks such as Hidden Markov Model.