Identify the Color and Shape of Eggplant Using Back Propagation Method

Identify the Color and Shape of Eggplant Using Back Propagation Method

Neural Networks, Back Propagation, Accuracy, Eggplants

Currently, artificial neural networks are being developed as a tool that can help human tasks. The problem so far in identifying
and detecting eggplants carried out by a vegetable shop is still mostly using the manual method based on direct visual
observation which is strongly influenced by the subjectivity of the sorting operator, so that under certain conditions the
identification process is inconsistent. The main purpose of this study is to identify the structure of eggplants from the shape
and color of some eggplants using a back propagation neural network learning method, so that the vegetable shop can
distinguish the types of eggplant. The data is obtained from an image that will be entered into the program. The data used in
the identification process are two photos containing two types of eggplant, the first eggplant is green and round in shape and
the next eggplant is purple and oval in shape. The results of the identification process using this back propagation from the
tests that have been done previously, the highest calculation results obtained with the best results using a learning rate of 0.7
and epoch iterations of 500 and producing an accuracy of 73.33%.

Siswanto1
, Yuhefizar2
, M. Anif3
, Basuki Hari Prasetyo4
, Ari Saputro5

Universitas Budi Luhur

31-10-2022

Fajar bagus W

PDF

Indonesia

Text