Sistem Deteksi Kemurnian Beras berbasis Computer Vision dengan Pendekatan Algoritma YOLO

Nova Eka Budiyanta, Melisa Mulyadi, Harlianto Tanudjaja

Abstract


Penelitian ini bertujuan untuk menerapkan sistem deteksi kemurnian beras terhadap campuran kotoran untuk dapat digunakan sebagai parameter nilai untuk mensortir kotoran yang terdeteksi pada proses kontrol kualitas beras. Sistem yang dikembangkan pada penelitian ini berbasis computer vision menggunakan kamera sebagai sensor. Data citra yang didapat dari kamera selanjutnya diproses untuk mengenali objek beras yang murni dan objek kotoran yang tercampur pada kumpulan beras. Penelitian ini berfokus pada algoritma deteksi objek batu atau kerikil (gravel) pada proses produksi beras. Proses deteksi objek pada penelitian ini menggunakan metode You Only Look Once (YOLO) v3. Secara keseluruhan sistem deteksi objek pada penelitian ini berjalan baik. Proses pelatihan model berhasil meminimalisir loss secara signifikan dengan nilai loss sebesar 1.89 di iterasi ke 1000 menjadi 0.16 di iterasi ke 15000. Seiring dengan keberhasilan proses pelatihan model, pengujian model pada penerapan proses deteksi juga berjalan baik yang ditunjukkan dengan nilai rerata akurasi sebesar 86.11%.

Keywords


YOLO, Object Detecction, Computer Vision, Quality Control, Rice Production Quality

Full Text:

References


Maclean, J., Hardy, B., Hettel, G. “Rice Almanac”, 4th ed. International Rice Research Institute: Los Bahos, Philippines, 2013; ISBN 978-971-22-0300-8. 2013.

Nirmala Bandumula. “Rice Production in Asia: Key to Global Food Security”. Proceedings of the National Academy of Sciences, India - Section B: Biological Sciences. 2017.

I.K. Adegun, S.A. Adepoju and J.A. Aweda. “ A Mini Rice Processing Machine for Nigerian Farmers”. Journal of Agricultural Technology 2012 Vol. 8(4): 1207-1216. 2012.

Ojediran, et al. “Development of a motorized rice de-stoning machine”. AgricEngInt: CIGR Journal Open access at http://www.cigrjournal.org. Vol. 20, No. 4. 2018

Gurmandeep Singh, Atul Goyal, Vivek Aggarwal. “Performance Analysis of Paddy Separation System of a Rice Industry By Using Markov Process”. International Journal on Mechanical Engineering and Robotics (IJMER). Volume-6, Issue-1-2. 2018.

Muhammad Nur, Sjaeful Irwan, Danang Santosa. Identifikasi Visual Cacat Produk Menggunakan Neural Network Model Backpropagation. Jurnal Informatika: Jurnal pengembangan IT (JPIT), Vol.04 No.2-2, 2019.

Joseph Redmon, Santosh Kumar Divvala, Ross B. Girshick, dan Ali Farhadi. “You only look once: Unified, real-time object detection”. CoRR, abs/1506.02640, 2015.

Joseph Redmon, Ali Farhadi. "YOLO9000: Better, Faster, Stronger". The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 7263-7271. 2017.

Joseph Redmon, Ali Farhadi. "Yolov3: An incremental improvement". arXiv preprint arXiv:1804.02767. 2018.

Nova Eka Budiyanta, Catherine O. S., Lukas. P-D controller computer vision and robotics integration based for student’s programming comprehension improvement. TELKOMNIKA Telecommunication, Computing, Electronics and Control. Vol. 18, No. 2, pp. 899~906. 2020.

Jonathan Hui. "mAP (mean Average Precision) for Object Detection". Medium. [online]. 2018 Available: https://medium.com/@jonathan_

hui/map-mean-average-precision-for-object-detection-45c121a31173 [Accessed: 16-Oct-2020]

Sumardi, Muhammad T., Munawar A, “Street mark detection using Raspberry PI for Self-driving System,” TELKOMNIKA Telecommunication Computing Electronics and Control, vol. 16, pp. 629-634, 2018.

Dhanashree, V. M., Mrinal, R. B., “Real Time Object Detection and Tracking using Raspberry Pi,” International Journal of Engineering Science and Computing, vol. 7, no.6, 2017.

Ali A. A., Sara A. R., “Computer vision for object recognition and tracking based on Raspberry Pi,” International Conference on Change, Innovation, Informatics, and Disruptive Technology ICCIIDT’16. London, pp. 177-189, 2016.

Onkar R., et al., “Object Detection on Raspberry Pi,” International Journal of Engineering Science and Computing. vol. 7, no. 3, 2017.




DOI: https://doi.org/10.30591/jpit.v6i1.2309

Refbacks



Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

JPIT INDEXED BY

  
  

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.