Apple Freshness Classification Based on Images Using Wavelet and K-Nearest Neighbors Techniques
Downloads
An essential component of fruit marketing and the agriculture sector is determining the freshness of fresh apples. Additionally, the majority Hindu population of Bali uses apples for religious rituals, therefore determining the apples' freshness aids in their selection of high-quality apples. In this study, we provide a k-Nearest Neighbors strategy for apple classification. Using a dataset of apple photos, this study attempts to identify the freshness of apples. Pre-processing and classification of images are among the methods employed. After processing fruit photos to improve contrast, wavelets are used to extract key features. The k-Nearest Neighbors classification algorithm uses these features as input. It is expected that the findings of this study will demonstrate the accuracy of the classification results produced by the k-Nearest Neighbors (k-NN) algorithm. The application is developed using the Python programming language, which is capable of processing image datasets to classify fresh fruit images. This application can be used as a tool to assist in selecting high-quality apples. When the k-NN method was used to evaluate the freshness classification of apples, it performed better at test size training parameter 0.2, with an accuracy value of 0.96 and a precision value of 0.93 for fresh apples and 1 for rotten apples.
U. Satrya Darmawan Putra Bahari, “Klasifikasi Buah Segar dengan Menggunakan Teknik Computer Vision Untuk Pendeteksian Kualitas dan Kesegaran Buah,” Jurnal Mahasiswa Teknik Informatika, vol. 7, no. 3, pp. 1567–1573, 2023.
F. E. N. Kholiq Prajatama, “Deteksi Kualitas Buah Apel Malang Manalagi Menggunakan Algoritma Naive Bayes,” JURNAL SISTEM INFORMASI DAN TEKNOLOGI INFORMASI, vol. 8, no. 1, 2019.
A. Soedarmaji and R. Ediati, “Identifikasi Kematangan Buah Tropika Berbasis Sistem Penciuman Elektronik Menggunakan Deret Sensor Gas Semikonduktor Dengan Metode Jaringan Syaraf Tiruan,” Jurnal Keteknikan Pertanian, vol. 25, no. 1, 2011.
R. Siskandar, N. A. Indrawan, B. R. Kusumah, S. H. Santosa, I. Irmansyah, and I. Irzaman, “PENERAPAN REKAYASA MESIN SORTIR SEBAGAI PENENTU KEMATANGAN BUAH JERUK DAN TOMAT MERAH BERBASIS IMAGE PROCESSING,” Jurnal Teknik Pertanian Lampung (Journal of Agricultural Engineering), vol. 9, no. 3, 2020, doi: 10.23960/jtep-l.v9i3.222-236.
C. L. Prinzky, “Klasifikasi Buah Segar dan Busuk Menggunakan Convolutional Neural Network Berbasis Android,” Jurnal Ilmu Komputer dan Sistem Informasi, vol. 10, no. 2, 2022.
T. A. M. Fani Nurona Cahya, Rangga Pebrianto, “Klasifikasi Buah Segar dan Busuk Menggunakan Ekstraksi Fitur Hu-Moment , Haralick dan Histogram,” Indonesian Journal on Computer and Information Technology, vol. 6, no. 1, 2021.
R. P. P. Stifani Napitu, “Klasifikasi Buah Jeruk Segar dan Busuk Berdasarkan RGB dan HSV Menggunakan Metode KNN,” Jurnal SAINTEKOM, vol. 1, no. 2, 2023.
D. F. K. Gom-os, “Fruit Classification using Colorized Depth Images,” International Journal of Advanced Computer Science and Applications, vol. 14, no. 5, 2023,
doi: 10.14569/IJACSA.2023.01405106.
S. Khansa, “Penerapan Ekstraksi Ciri Transformasi Wavelet Dalam Pembuatan Model Klasifikasi Kesegaran Ikan Selar,” Senamika, 2020.
A. Pamungkas, “Model Ruang Warna Pengolahan Citra.” Accessed: Dec. 22, 2021. [Online]. Available: https://pemrogramanmatlab.com/2016/06/08/model-ruang-warna-pengolahan-citra/
M. Oni, B. Kanata, and D. Ratnasari, “Menentukan Luas Objek Citra Dengan Teknik Segmentasi Berdasarkan Warna Pada Ruang Warna HSV,” Dielektrika, vol. 8, no. 2, p. 138, 2021, [Online]. Available: https://dielektrika.unram.ac.id/index.php/dielektrika/article/view/274
R. Rahmadewi, G. L. Sari, and H. Firmansyah, “Pendeteksian Kematangan Buah Jeruk Dengan Fitur Citra Kulit Buah Menggunakan Transformasi Ruang Warna HSV,” JTEV (Jurnal Teknik Elektro dan Vokasional), vol. 5, no. 1.1, 2019,
doi: 10.24036/jtev.v5i1.1.107560.
M. A. Gilbert, N. H. Shabrina, A. Wijaya, and J. P. Wijaya, “Perbandingan Pola Sinyal Penyakit Myocardial Infarction dengan Jantung Normal Menggunakan Metode Wavelet Symlet,” Ultima Computing : Jurnal Sistem Komputer, vol. 12, no. 1, 2020, doi: 10.31937/sk.v12i1.1631.
A. al-Qerem, F. Kharbat, S. Nashwan, S. Ashraf, and khairi blaou, “General model for best feature extraction of EEG using discrete wavelet transform wavelet family and differential evolution,” Int J Distrib Sens Netw, vol. 16, no. 3, 2020,
doi: 10.1177/1550147720911009.
