Winanda, Teddy
Unknown Affiliation

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Klasifikasi Kualitas Mutu Daun Gambir Ladang Rakyat Menggunakan Metode Convolutional Neural Network Winanda, Teddy; Yunus, Yuhandri; Hendrick, H
Jurnal Sistim Informasi dan Teknologi 2021, Vol. 3, No. 3
Publisher : Rektorat Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/jsisfotek.v3i3.156

Abstract

Indonesia is one of the countries which have the best Gambier quality in the world. Those are a few areas in Indonesia which have best gambier quality such as Aceh, Riau, North Sumatera, Bengkulu, South Sumatera and West Sumatra. Kabupaten 50 Kota is one of the regencies in west Sumatra that supplies gambier in Indonesia. The gambier leaf selection is mostly done by manual inspection or conventional method. The leaf color, thickness and structure are the important parameters in selecting gambier leaf quality. Farmers usually classify the quality of gambier leaves into good and bad. Computer Vision can help farmers to classify gambier leaves automatically. To realize this proposed method, gambier leaves are collected to create a dataset for training and testing processes. The gambier image leaves is captured by using DLSR camera at Kabupaten 50 Koto manually. 60 images were collected in this research which separated into 30 images with good and 30 images with bad quality. Furthermore, the gambier leaves image is processed by using digital image processing and coded by using python programming language. Both TensorFlow and Keras were implemented as frameworks in this research. To get a faster processing time, Ubuntu 18.04 Linux is selected as an operating system. Convolutional Neural Network (CNN) is the basis of image classification and object detection. In this research, the miniVGGNet architecture was used to perform the model creation. A quantity of dataset images was increased by applying data augmentation methods. The result of image augmentation for good quality gambier produced 3000 images. The same method was applied to poor quality images, the same results were obtained as many as 3000 images, with a total of 6000 images. The classification of gambier leaves produced by the Convolutional Neural Network method using miniVGGNet architecture obtained an accuracy rate of 0.979 or 98%. This method can be used to classify the quality of Gambier leaves very well.