Universitas Stikubank (Unisbank) Semarang Repository

PENGENALAN BAHASA ISYARAT MENGGUNAKAN OPENCV

Pertiwi, Anisa Dewi (2021) PENGENALAN BAHASA ISYARAT MENGGUNAKAN OPENCV. Undergraduate thesis, Universitas Stikubank.

[thumbnail of HLM JUDUL] PDF (HLM JUDUL)
Download (2MB)
[thumbnail of ABSTRAK] PDF (ABSTRAK)
Download (175kB)
[thumbnail of BAB I] PDF (BAB I)
Download (104kB)
[thumbnail of BAB II] PDF (BAB II)
Restricted to Repository staff only

Download (148kB)
[thumbnail of BAB III] PDF (BAB III)
Restricted to Repository staff only

Download (1MB)
[thumbnail of BAB IV] PDF (BAB IV)
Restricted to Repository staff only

Download (6MB)
[thumbnail of BAB V] PDF (BAB V)
Restricted to Repository staff only

Download (78kB)
[thumbnail of DAFTAR PUSTAKA] PDF (DAFTAR PUSTAKA)
Download (105kB)
[thumbnail of LAMPIRAN] PDF (LAMPIRAN)
Restricted to Repository staff only

Download (2MB)

Abstract

isyarat merupakan bahasa yang mengutamakan gerak tubuh dan ekspresi wajah, biasanya digunakan oleh tunarungu untuk berkomunikasi. Perbedaan bahasa membuat tunarungu sulit untuk berkomunikasi dengan masyarakat pada umumnya. Tujuan penelitian ini adalah membaca deteksi gerak tubuh dan ekspresi wajah manusia secara real-time. Penelitian menggunakan teknologi mediapipe holistic dan algoritma klasifikasi random forest yang diaplikasikan dalam bahasa pemrograman Python menghasilkan akurasi training 100%. Hasil uji dengan mendeteksi alfabet BISINDO memperoleh akurasi rata-rata 94,7%. Dapat disimpulkan bahwa telah dibuat sistem pendeteksi bahasa isyarat sehingga dapat dikembangkan menjadi media pembelajaran bagi tunarungu dan masyarakat. Sign language is a language that prioritizes gestures and facial expressions, usually used by the deaf to communicate. Language differences make it difficult for the deaf to communicate with the general public. The purpose of this study is to read the detection of human body movements and facial expressions in real-time. Research using holistic mediapipe technology and random forest classification algorithm applied in the Python programming language resulted in 100% training accuracy. The test results by detecting the BISINDO alphabet obtained an average accuracy of 94,7%. It can be concluded that a sign language detection system has been created so that it can be developed into a learning medium for the deaf and the community.

Item Type: Thesis (Undergraduate)
Additional Information: SKR.I.05.01.2039 NIM 17.01.53.0162
Uncontrolled Keywords: Bahasa isyarat, Mediapipe holistic,Random forest,Python, Real-time Sign language, Mediapipe holistic, Random Forest, Python, Real-time.
Subjects: Q Science > QA Mathematics > QA76 Computer software
Faculty / Institution: Fakultas Teknologi Informasi > Program Studi Teknik Informatika
Depositing User: Teteh Hayati
Date Deposited: 11 Nov 2021 01:34
Last Modified: 11 Nov 2021 01:34
URI: https://eprints.unisbank.ac.id/id/eprint/8044

Actions (login required)

View Item View Item