KLASIFIKASI ALFABET BAHASA ISYARAT INDONESIA(BISINDO) DENGAN METODE TEMPLATE MATCHING DAN K-NEAREST NEIGHBORS (KNN)

Andika Dicky Saputra, . (2020) KLASIFIKASI ALFABET BAHASA ISYARAT INDONESIA(BISINDO) DENGAN METODE TEMPLATE MATCHING DAN K-NEAREST NEIGHBORS (KNN). Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf

Download (542kB)
[img] Text
AWAL.pdf

Download (2MB)
[img] Text
BAB 1.pdf

Download (703kB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only

Download (1MB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only

Download (834kB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only

Download (1MB)
[img] Text
BAB 5.pdf

Download (662kB)
[img] Text
DAFTAR PUSTAKA.pdf

Download (562kB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only

Download (450kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only

Download (2MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository UPNVJ Only

Download (999kB)

Abstract

In carrying out daily activities, humans must interact with each other by using language and communicating, but it is different from deaf people who communicate using sign language. To communicate with normal people who do not understand sign language requires an intermediary to translate sign language. This study aims to detect static and dynamic cue alphabets and classify them so that the output is a text that everyone can understand. This study uses a template matching method and the KNN algorithm. The data used is the result of video keyframe extraction consisting of 136 templates and 17 test images. The data then tested for compatibility using the template matching method and the final stage of classification using the KNN. In the compatibility test stage, the results were 85.04% for static sign alphabets, while dynamic sign alphabets were 84.65%. The KNN classification has an accuracy of 96.52%, so this study succeeded in classifying static and dynamic sign alphabets.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 1610511033] [Pembimbing 1: Jayanta] [Pembimbing 2: Ing. Artambo B. Pangaribuan] [Ketua Penguji: Ermatita] [Anggota Penguji: Henki Bayu Seta]
Uncontrolled Keywords: Communication, Indonesian Sign Language (BISINDO), Template Matching, K-Nearest Neighbors.
Subjects: Q Science > QA Mathematics > QA76 Computer software
Divisions: Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User: Andika Dicky Saputra
Date Deposited: 13 Jan 2022 02:06
Last Modified: 13 Jan 2022 02:06
URI: http://repository.upnvj.ac.id/id/eprint/6620

Actions (login required)

View Item View Item