Klasifikasi Karakteristik Fisik Biji Pinang Belah Kering (Areca catechu) Menggunakan Pengolahan Citra Digital

Ria Desianti Br Sitepu, Rahmat Fadhil, Indera Sakti Nasution

Abstract


Abstrak. Klasifikasi biji pinang belah merupakan penyortiran biji pinang belah berdasarkan mutu maupun karakteristiknya. Penelitian ini bertujuan untuk mengklasifikasi biji pinang belah kering menggunakan pengolahan citra dengan metode K-Nearest Neighbor berdasarkan karakteristik parameter bentuk dan tekstur. Biji pinang belah kering dengan 8 klasifikasi yaitu biji bagus telungkup, biji bagus telentang, biji busuk telungkup, biji busuk telentang, biji pecah telungkup, biji pecah telungkup, benda asing telentang, dan benda asing telentang. Sebanyak 1.920 biji pinang belah ditangkap dengan menggunakan kamera kinect v2, di mana data latih menggunakan 1.280 biji pinang belah dan untuk data uji ada sebanyak 640 biji. Fitur yang digunakan yaitu area, perimeter, kontras, korelasi, energi, dan homogenitas yang di ekstraksi menggunakan pengolahan citra. Hasilnya menunjukkan bahwa fitur yang digunakan cukup mampu membedakan beberapa klasifikasi biji pinang. Tingkat akurasi klasifikasi karakteristik fisik biji pinang belah kering yaitu sebesar 84,21%.

Classification of Physical Characteristics of Dried Slit Areca Seeds (Areca catechu) Using Digital Image Processing

Abstract. The classification of split betel nuts is sorting split betel nuts based on their quality and characteristics. This study aims to classify dry split areca nut using image processing with the K-Nearest Neighbor method based on the characteristics of the shape and texture parameters. Dry split areca seeds with 8 classifications, namely good seeds face down, good seeds on their back, rotten seeds face down, rotten seeds on their backs, seeds cracked face down, seeds cracked face down, foreign bodies on their back, and foreign bodies on their back. A total of 1,920 split betel nuts were captured using the Kinect v2 camera, where the training data used 1,280 split areca nut and for the test data there were 640 seeds. The features used are area, perimeter, contrast, correlation, energy, and homogeneity which are extracted using image processing. The results show that the features used are quite capable of distinguishing several classifications of areca nut. The level of accuracy of the classification of the physical characteristics of dry split areca nut is 84.21%.



Keywords


Klasifikasi; biji pinang; pengolahan citra; K-NN ; Classification; Areca catechu; image processing; K-NN

Full Text:

PDF

References


Hartono, P dan Trismiyati. 2016. Klasifikasi Biji Pinang Belah pada Pengembangan Mesin Sortir Pinang menggunakan Pengolahan Citra Digital. Jurnal Riset Industri. 10(2): 61–82.

Hasiri, E. M., Asniati dan Wiwin. 2017. Sistem Kontrol Otomatis Pada Penyortiran Buah Tomat Menggunakan Sensor Warna Tcs3200 Dan Mikrokontroler Atmega 2560. Jurnal Informatika. 6(1): 1–7.

Effendi, M., Fitriyah dan U. Effendi. 2017. Identifikasi Jenis dan Mutu Teh Menggunakan Pengolahan Citra Digital dengan Metode Jaringan Syaraf Tiruan. Jurnal Teknotan. 11(2): 67. https://doi.org/10.24198/jt.vol11n2.7

Faridah., O.F. Parikesit., dan Ferdiansjah. 2011. Coffeee Bean Grade Determination Based on Image Parameter. Jurnal Telkomnika. 9(3). 547-554.

Faucett, T. 2006. Introduction to ROC Analisys. Pattern Recognit.Lett. 27: 861-874. https://doi.org/10.1016/J.PATREC.2005.10.010

Nasution, I.S dan K. Gusriyan. 2019. Nutmeg Grading System Using Computer Vision Techniques. 1-7. https:// doi:10.1088/1755-1315/365/1/012003

Plataniotis dan Venetsanopoulos. 2000. Color Image Processing and Applications. Springer-Verlag, New York.

Prehanto, D.R., A.D. Indriyanti., I.K.D. Nuryanadan G.S. Permadi. 2021. Classification based on K- Nearest Neighbor and Logistic

Regression method of coffee using Electronic Nose. IOP Conference Series: Materials Science and Engineering. 1098(3).1-7. https://doi.org/10.1088/1757-899x/1098/3/03208

Rahmadianto, R., E. Mulyanto dan T. Sutojo. 2019. Implementasi Pengolahan Citra dan Klasifikasi K- Nearest Neighbor untuk Mendeteksi Kualitas Telur Ayam. Jurnal VOI (Voice Of Informatics). 8(1): 45–54.

Sakurai, S., H. Uchiyama., A. Shimada., D. Arita., R. Taniguchi dan ichiro. 2018. Two-step transfer learning for semantic plant segmentation, in: ICPRAM 2018 - Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods. SciTePress, pp. 332–339.https://doi.org/10.5220/0006576303320339

Sitorus, E. 2018. Klasifikasi Buah Pepaya (Carica papaya L.) Berdasarkan Sifat Fisik Permukaan dan Warna Menggunakan Teknologi Pengolahan Citra Digital dan Metode K- Nearest Neighbor (K- NN). Skripsi. Program Studi Teknik Pertanian, Fakultas Pertanian, Universitas Syiah Kuala, Banda Aceh.

Zhongheng, Z. 2016. Introduction to Machine Learning: K- Nearest Neighbors. Department of Critical Care Medicine, Jinhua Municipal Central Hospital, Jinhua Hospital of Zhejiang University. China.




DOI: https://doi.org/10.17969/jimfp.v7i2.19860

Refbacks

  • There are currently no refbacks.


 


JIM Agribisnis|JIM Agroteknologi|JIM Peternakan|JIM Teknologi Hasil Pertanian|JIM Teknik Pertanian|
JIM Ilmu Tanah|JIM Proteksi Tanaman|JIM Kehutanan


E-ISSN: 2614-6053 2615-2878 Statistic Indexing | Citation


Alamat Tim Redaksi:
Fakultas Pertanian,Universitas Syiah Kuala
Jl. Tgk. Hasan Krueng Kalee No. 3, Kopelma Darussalam,
Banda Aceh, 23111, Indonesia.
Email:jimfp@unsyiah.ac.id