CD Skripsi

Analisa Perbandingan Performa Algoritma Convolutional Neural Network Dalam Klasifikasi Gambar Abjad Bahasa Isyarat Indonesia

---

This study compares the background clutter and green in the image for the
modeling process, background clutter is generally more common than a plain
green background. This study aims to see whether the image background affects
the performance of the convolutional neural network algorithm in classifying the
Indonesian Sign Language Alphabet (BISINDO). This deep learning model uses
2860 images for each background with a total dataset of 5720 images, the data
that has been collected is divided into training, validation and testing, 3x3 filter
size, and a learning rate of 0.001 and 50 epochs. of 0.983, validation of 0.823 and
testing of 0.67 for model 1 (Green Background), while for model 2 (Background
Clutter) the training accuracy is 0.971, validation is 0.529 and testing is 0.38. It
can be concluded that background clutter affects the accuracy of the model.
Keywords : BISINDO, CNN, Classification, Model, Clutter, Background.

---

Ketersediaan

Informasi Detail

Judul Seri

-

No. Panggil

1803113330

Penerbit

Pekanbaru : Universitas Riau – FMIPA – Sistem Informasi., 2022

Deskripsi Fisik

-

Bahasa

Indonesia

ISBN/ISSN

-

Klasifikasi

1803113330

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

SISTEM INFORMASI

Info Detail Spesifik

-

Pernyataan Tanggungjawab

NADYA

Versi lain/terkait

Lampiran Berkas

Komentar

---

Anda harus masuk sebelum memberikan komentar