Record Details

KLASIFIKASI AKASARA JAWA DENGAN CNN

Jurnal Teknika

View Archive Info
 
 
Field Value
 
Title KLASIFIKASI AKASARA JAWA DENGAN CNN
 
Creator Wijaya, Edo Prasetyo N. A
 
Subject Teknik Informatika
Classification, Convolution Neural Network, Javanesse Letter
Teknik Informatika
 
Description It is common knowledge that CNN is a significant method in image classification. This is because CNN can classify Latin letters with a high degree of accuracy. Lenet5 in CNN is tasked with converting 2D features from an image into a convolutional network continuously. CNN architecture consists of several layers, including the Convolution Layer, Relu layer, Subsampling layer, Fully Connected Layer. In this research, CNN is used to classify Javanese script images into 20 classes. These classes include ha, na, ca, ra, ka, da, ta, wa, la, pa, dha, ja, yes, nya, ma, ga, ba, tha, nga. Javanese script used in this research is Ngalena Javanese script. The precision values for each class range from 0.5 to 0.6.
 
Publisher Universitas Islam Lamongan
 
Contributor
 
Date 2020-09-20
 
Type info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion



 
Format application/pdf
 
Identifier https://jurnalteknik.unisla.ac.id/index.php/teknika/article/view/479
10.30736/jt.v13i2.479
 
Source Teknika; Vol 12, No 2 (2020): Bersinergi untuk kemajuan dan perkembangan teknologi bangsa indonesia; 61-64
Jurnal Teknika; Vol 12, No 2 (2020): Bersinergi untuk kemajuan dan perkembangan teknologi bangsa indonesia; 61-64
2620-4770
2085-0859
10.30736/jt.v13i2
 
Language ind
 
Relation https://jurnalteknik.unisla.ac.id/index.php/teknika/article/view/479/342
 
Rights ##submission.copyrightStatement##
https://creativecommons.org/licenses/by/4.0