Open AccessPerancangan Sistem Deteksi Isyarat BISINDO Dengan Metode Adaptive Neuro-Fuzzy Inference System (ANFIS)
Author(s) -
Nadia Intan Pratiwi,
Ida Widaningrum,
Dyah Mustikasari
Publication year - 2019
Publication title -
jurnal komtekinfo
Language(s) - English
Resource type - Journals
ISSN - 2502-8758
DOI - 10.35134/komtekinfo.v6i1.41
Subject(s) - computer science , sign language , adaptive neuro fuzzy inference system , sign (mathematics) , indonesian , artificial intelligence , process (computing) , sign system , indonesian government , histogram , inference , fuzzy logic , speech recognition , pattern recognition (psychology) , fuzzy control system , image (mathematics) , mathematics , linguistics , communication , programming language , psychology , mathematical analysis , philosophy
Deafness is a condition where an individual's hearing cannot function normally. So, sign language was created which was used as a solution to the problem. In Indonesia, the sign languages that are known are SIBI (Indonesian Sign Language System) and BISINDO (Indonesian Sign Language). Although SIBI has been recognized by the Indonesian government, in its use it is less desirable. This research was conducted to identify empty hand signals. Where it will help the user naturally without additional assistance. Experiments carried out using a dataset that was demonstrated by 1 display. In the process, the characteristics of the hand are taken using the Histogram Oriented Gradient (HOG) method. Whereas to separate it from the background image, color segmentation is used. The results of the process are then taken to classify. The classification process uses the Adaptive Neuro-Fuzzy Inference System method. The results of the tests carried out resulted in an accuracy of 78.31%. The problem is done.