Institusion
Institut Teknologi Perusahaan Listrik Negara
Author
Sabbih, Syekh Alam
Agtriadi, Herman Bedi
Dody, S, Dody, S
Subject
Teknik Informatika
Datestamp
2023-06-22 07:05:41
Abstract :
This study was conducted to find out how to classify the image, the results of the
maturity classification, and find out the level of accuracy obtained in the maturity
classification in mango fruits. The methods used in this study are the Convolutional
Neural Network method for classifying manga fruits, and the confusion matrix to measure
the accuracy of the maturity classification in mango fruits whether the fruit is raw, ripe
or rotten. The data used in this study amounted to 389 data. The results obtained from this
study are the creation of a model for classifying mango fruit images using Convolutional
Neural Network with convolution layer filters, activation of relu and softmax and fully
connected layers. It got the accuracy rate by using a confusion matrix of 81%, precision
of 82% and recall of 89%.