Perbandingan Klasifikasi Jenis Apel Berkulit Merah Menggunakan Algoritma Linear Discriminant Analysis dan K-Nearest Neighbor
Keywords:
Klasifikasi, Apel, KNN, LDA, GLCMAbstract
Buah apel merupakan salah satu buah yang
mempunyai rasa dominan manis segar dan memiliki vitamin C
tinggi. Apel dibudidayakan untuk tujuan konsumsi, obat maupun
industri. Dalam industry, apel digunakan sebagai bahan baku
pembuatan berbagai macam bentuk makanan dan minuman
misalnya sirup, jenang, wingko, dodol, manisan, asinan, keripik,
dan sari apel. Jenis apel yang beragam dan kebutuhan waktu
pendistribusian berdasarkan jenis apel memerlukan banyak
waktu dan berhubungan dengan kemampuan mata manusia
dalam proses sorting manual. Kebutuhan teknologi seperti
computer vision melalui teknik pengolahan citra dapat
diimplementasikan untuk proses sorting khususnya klasifikasi
jenis apel. Dalam penelitian ini, digunakan apel dengan kulit
berwarna merah sebagai dataset. Kesamaan warna kulit dan
bentuk apel yang hampir sama, menjadi salah satu isu penting
untuk proses klasifikasi citra. K Nearest Neighbor (KNN) dan
Linear Discriminant Analysis (LDA) dipilih karena kemampuan
klasifikasi citra dengan dataset kecil. Dalam penelitian ini telah
dilakukan proses perbandingan hasil akurasi antara KNN dan
LDA berdasarkan 400 dataset yang berasal dari 8 jenis apel
merah antara lain Cameo, Honeycrips, Pink Lady, Red Delicious,
Royal Gala, Macintosh, Empire, Fuji. KNN dan LDA tanpa
menggunakan ekstraksi fitur GLCM menghasilkan akurasi yang
hampir sama yaitu 99,25% dan 99% sedangkan apabila tidak
menggunakan fitur ekstraksi apapun dihasilkan akurasi 99,25%
dan 99%. Dengan demikian diketahui bahwa KNN menghasilkan
akurasi lebih tinggi dibanding PCA, meskipun hanya terdapat
sedikit selisih akurasi.
References
Ferdian Wahyu Prianggara, Ahmad Bagus Setiawan, and Intan Nur Farida,
“Indetifikasi Jenis Buah Apel Berdasarkan Ekstraksi Bentuk dan Warna,” in
Seminar Nasional Inovasi Teknologi, 2020, pp. 215–219.
Arun C, Akshatha Prabhu, Mohammed Zeeshan, and N. Shobha Rani, “A Study
on Various Classifier Techniques Used in Image Processing,” 2020.
P. Moallem, A. Serajoddin, and H. Pourghassem, “Computer vision
-based apple grading for golden delicious apples based on surface features,” Information
Processing in Agriculture, vol. 4, no. 1, pp. 33–40, 2017, doi:10.1016/j.inpa.2016.10.003.
X. Wu, B. Wu, J. Sun, M. Li, and H. Du, “Discrimination of Apples Using Near
Infrared Spectroscopy and Sorting Discriminant Analysis,” International Journal
of Food Properties, vol. 19, no. 5, pp. 1016–1028, May 2016, doi:
1080/10942912.2014.971181.
W. Huang, J. Li, Q. Wang, and L. Chen, “Development of a multispectral imaging
system for online detection of bruises on apples,” Journal of Food Engineering,
vol. 146, pp. 62–71, Feb. 2015, doi: 10.1016/j.jfoodeng.2014.09.002.
X. Yue and N. Tian, “Research on Apple Classification System Based on Hybrid
Kernel Function and Multi-Feature Fusion,” in Proceedings- 2020 International Conference on Computer Engineering and Application, ICCEA 2020, Mar. 2020,pp. 589–593. doi: 10.1109/ICCEA50009.2020.00129.
Y. Tian, E. Li, L. Yang, and Z. Liang, “An image processing method for green
apple lesion detection in natural environment based on GA-BPNN and SVM,”Proceedings of 2018 IEEE International Conference on Mechatronics and
Automation, ICMA 2018, pp. 1210–1215, 2018, doi:10.1109/ICMA.2018.8484631.
A. Bhargava and A. Bansal, “Classification and Grading of Multiple Varieties of
Apple Fruit,” Food Analytical Methods, 2021, doi: 10.1007/s12161-021-01970-0.
K. Sabanci and M. Fahri ÜNLERŞEN, “Different Apple Varieties Classification
Using kNN and MLP Algorithms,” IJISAE (International Journal of Intelligent
Systems and Applications in Engineering), no. 4, pp. 166–169, 2016, [Online].
Available: www.atscience.org/IJISAE
P. Boniecki et al., “Neural Identification of Chosen Apple Pests Using Algorithm
LVQ,” in HAICTA, 2017, pp. 293
–303.
Y. Li, X. Feng, Y. Liu, and X. Han, “Apple quality identification and
classification by image processing based on convolutional neural networks,”
Scientific Reports, vol. 11, no. 1, pp. 1–15, 2021, doi: 10.1038/s41598-021-96103-2.
Abdulhamid Haidar, Haiwei Dong, and Nikolaos Mavridis, “Image
-Based Date
Fruit Classification,” in IV International Congress on Ultra Modern
Telecommunications and Control Systems 2012, 2012, pp. 357
–363.
O. Rena Indriani, C. Atika Sari, E. Jaya Kusuma, E. Hari Rachmawanto, and D.
Rosal Ignatius Moses Setiadi, “Tomatoes Classification Using K
-NN Based on
GLCM and HSV Color Space,” 2017.
X. Yang, R. Zhang, Z. Zhai, Y. Pang, and Z. Jin, “Machine learning for cultivar
classification of apricots (Prunus armeniaca L.) based on shape features,” Scientia
Horticulturae, vol. 256, Oct. 2019, doi: 10.1016/j.scienta.2019.05.051.
H. Manickam, P. L. Chithra, and M. Henila, “Fruit Classification using image
processing techniques Fruits Classification Using Image Processing Techniques,”
International Journal of Computer Sciences and Engineering Open Access
Research Paper, no. 5, 2019, doi: 10.26438/ijcse/v7si5.131135.
