Classification the melon rinds using convolutional neural network

Masykur, Fauzan, Mahmud, Azkiya, Cobantoro, Adi Fajaryanto, Prasetyo, Angga, Setyawan, Mohammad Bhanu and Litanianda, Yovi (2021) Classification the melon rinds using convolutional neural network. In: 3RD BOROBUDUR INTERNATIONAL SYMPOSIUM ON SCIENCE AND TECHNOLOGY 2021, 15 December 2021, Magelang, Indonesia.

Text 11 cp_Classification Melon.pdf Download (1MB)

Abstract

The first signal that a melon is getting ripe is the colour that the rind changes. Unfortunately, it is not the best indicator since the colour is not significantly different between the ripe ones and those that are not. This article verifies the classification between 2 types of melons, young melons and ripe melons, using the Convolutional Neural Network (CNN) method with a dataset of 500 images of the fruits. The dataset is classified into 2 parts, training data and testing data. While the classification method using 2 groups of datasets have been prepared results the accuracy value 99%, the latest melon image dataset input produces an accuracy of 52%. The difference of classification accuracy is 47% since the images are taken at different times and lighting conditions. Therefore, it produces different images and results in different accuracy values.

Item Type:	Conference or Workshop Item (Paper)
Subjects:	T Technology > T Technology (General)
Divisions:	Faculty of Engineering
Depositing User:	Library Umpo
Date Deposited:	02 Oct 2023 01:50
Last Modified:	02 Oct 2023 01:50
URI:	http://eprints.umpo.ac.id/id/eprint/12938

Actions (login required)

View Item