Sign language-Thai alphabet conversion based on Electromyogram (EMG)

Communication and sign-language learning of the people with hearing disabilities in Thailand has been problematic due to limited number of sign-language experts. To facilitate the sign-language learning and communication between the hearing disability and ordinary people, the sign language-to-alphabet spelling conversion was developed based on electromyography (EMG) signal recorded from the forearm muscles. The EMG signal of 10 different Thai sign-language gestures were recorded with the electrode arrangement similar to the Myo device from Thalmic Labs and analyzed. To extract the distinct features of the EMG signals, moving variance and mean absolute value (MAV) were chosen. The extracted output data was processed with the classification algorithm via non-linear model (artificial neural networks (ANN)) to confirm that the EMG signal for each alphabet gesture is accurately matched with the actual spelling alphabet. The system is able to measure the match of the output with total accuracy of more than 95%.

I. Introduction

The statistics of National Office for Empowerment of Persons with Disabilities (NEP) of Thailand reported in 2012 that among 1.3 million people with disabilities, there are at least 230,000 deaf people [1]. The number of deaf person is ranked No.2 or about 17% of the total people with disabilities. Sign language is commonly used to communicate among people with hearing disabilities. However, the communication for deaf people in Thailand is based on four main sign languages; that are the gesture language, home sign language, Thai Grammar sign language and Thai sign language [2]. The most natural and commonly used language among deaf people themselves is the Thai sign language. On the other hand, when deaf people communicate with other people, they tend to use Thai written language and Thai grammar spelling sign language via handwriting or smartphone writing application. To do this, they have to understand the normal written Thai language, which is often taught in the school for deaf people nationwide.