Sign Language Detection System Using Adaptive Neuro Fuzzy Inference System (ANFIS) Method

Abstract

Sign language is a language that prioritizes communication with hands, body language, and lip movements to communicate. The deaf are the main group who use this language, often combining hand shape, hand, arm and body orientation and movement, and facial expressions to express their thoughts. The sign language detection system is designed using the Adaptive Neuro Fuzzy Inference System (ANFIS). This study uses data from the kaggle.com dataset, which is a site that provides research data on artificial intelligence. This study was conducted to recognize empty hand signals. Where it will help users naturally without any additional help. The test is carried out using a data set as evidenced by 1 display. In this process, The characteristics of the hand were carried out using the Histogram Oriented Gradient (HOG) method. Meanwhile, to separate it from the background image, it is used with color segmentation. The results of the process are then taken for classification. The classification process uses the Adaptive Neuro Fuzzy Inference System method. The results of the tests carried out for accuracy are as much as