Identification of Banana Fruit Types Using the Backpropagation Method

Dian Widodo; Achmad Fauzi; Arnes Sembiring

doi:10.59934/jaiea.v3i1.314

Authors

Dian Widodo STMIK Kaputama
Achmad Fauzi STMIK KAPUTAMA
Arnes Sembiring University of Medan Area

DOI:

https://doi.org/10.59934/jaiea.v3i1.314

Keywords:

Backpropagation, RGB (red green blue), metric and eccentricity.

Abstract

Identification of types of bananas and assessment of their maturity level is an important process in the agricultural and distribution industries. In an effort to automate this process, the authors propose an approach to identify bananas and their level of ripeness using a Backpropagation neural network. Through digital image processing, images or pictures of bananas will be extracted with images such as RGB (red green blue), metric and eccentricity (shape features). The results of the image data training process are as many as 55 image data input, obtained by the training process data on banana types with 11 iterations from the maximum input epoch 10000, target error or performance 0.00642 with an accuracy value of 80%. Furthermore, the training process obtained data on the maturity level of bananas with 4 iterations from the maximum input epoch 10000, the target error or performance is 0.00606 with an accuracy value of 90%. From the test image process that has been carried out, the system can identify the type of banana and its maturity level based on the feature extraction input from the image of the banana. This study also aims to test and determine the accuracy of the application of the Backpropagation method in identifying the types of bananas and their level of maturity.

Downloads

Download data is not yet available.

References

S. Y. Prabawati and A. G. Wijaya, “Utilization of Paddy Husk and Banana Pseudostem as Alternative Material of Paper Making,” J. Apl. llmu-ilmu Agama, vol. IX, no. 1, pp. 44–56, 2008.

A. W. Utami, “Desain Aplikasi Untuk Identifikasi Kematangan Stroberi Berbasis Pengolahan Citra Digital Dan Jaringan Syaraf Tiruan Backpropagation.” Universitas Brawijaya, 2018.

Difla Yustisia dan Safrina Rosmalinda, “admin,JARINGAN SYARAF TIRUAN LEARNING VECTOR QUANTIZATION UNTUK APLIKASI PENGENALAN TANDA TANGAN .”

Y. Permadi and . Murinto, “Aplikasi Pengolahan Citra Untuk Identifikasi Kematangan Mentimun Berdasarkan Tekstur Kulit Buah Menggunakan Metode Ekstraksi Ciri Statistik,” J. Inform., vol. 9, no. 1, 2015, doi: 10.26555/jifo.v9i1.a2044.

Y. N. Muslimin, “Aplikasi Untuk Mengidentifikasi Kematangan Buah Pisang Menggunakan Image Processing dengan Metode Jaringan Syaraf Tiruan Learning Vector Quantization Berbasis Android,” 2015.

S. Gustina, A. Fadlil, and R. Umar, “Identifikasi Tanaman Kamboja menggunakan Ekstraksi Ciri Citra Daun dan Jaringan Syaraf Tiruan,” vol, vol. 2, pp. 128–132, 2016.

P. Bangun and M. Sihombing, “Pengolahan Citra Untuk Identifikasi Kematangan Buah Jeruk Dengan Menggunakan Metode Backpropagation Berdasarkan Nilai Hsv,” J. Tek. Inform. Kaputama, vol. 5, no. 1, pp. 85–91, 2021.

S. Kusmaryanto, “Jaringan Saraf Tiruan Backpropagation untuk Pengenalan Wajah Metode Ekstraksi Fitur Berbasis Histogram,” J. EECCIS (Electrics, Electron. Commun. Control. Informatics, Syst., vol. 8, no. 2, pp. 193–198, 2014.

C. P. Iklima, M. Nasir, and H. T. Hidayat, “Klasifikasi Jenis Pisang Menggunakan Metode K- Nearest Neighbor ( KNN ),” Teknol. Rekayasa Inf. dan Komput., vol. 1, no. 1, pp. 11–14, 2017.