Comparison of the Accuracy of The Bahasa Isyarat Indonesia (BISINDO) Detection System Using CNN and RNN Algorithm for Implementation on Android

Abstrak

Communication is a process of exchanging information that aims to establish relationships between humans. Communication difficulties are an obstacle for people with deaf disabilities or often called Deaf Friends, where they find it difficult to interact with friends around them. Sign language is the main medium of communication used worldwide by people with disabilities i.e. deaf and speech impaired. Communication between deaf people and those around them is often an obstacle because most people do not understand sign language which is often used as a medium of communication by deaf people. In dealing with this problem, researchers want to analyze the accuracy level of the Android-Based Bahasa Isyarat Indonesia Detection System (BISINDO) using the Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) methods in order to determine which methods can be implemented to an Android device. This study shows that Convolutional Neural Network (CNN) has a greater and more stable accuracy rate compared to the Recurrent Neural Network (RNN) model where the CNN model produces an accuracy rate of 89%, and indicates that the ability to recognize images based on the division of Bahasa Isyarat Indonesia (BISINDO) alphabetic classes is good..