dc.contributor.advisor | Solahudin, Mohamad | |
dc.contributor.author | Desrizal, Fahri | |
dc.date.accessioned | 2024-03-17T23:29:07Z | |
dc.date.available | 2024-03-17T23:29:07Z | |
dc.date.issued | 2024 | |
dc.identifier.uri | http://repository.ipb.ac.id/handle/123456789/141990 | |
dc.description.abstract | Evaluasi keragaan benih bawang merah memainkan peran krusial dalam
proses budidaya tanaman, mempengaruhi kualitas dan produktivitas. Fokus
penelitian ini adalah merancang sistem machine vision otomatis untuk
mengevaluasi keragaan benih bawang merah secara akurat. Penelitian melibatkan
beberapa tahapan, termasuk perancangan sistem pemantauan, perangkat semaian,
persiapan persemaian, dan uji kinerja sistem. Dua kamera ditempatkan di bagian
atas dan samping baki tanam, terhubung dengan program di Raspberry Pi. Program
ini dapat mengolah citra untuk menghitung parameter keragaan benih, seperti
jumlah bibit, daun, tinggi daun, dan diameter daun. Evaluasi sistem pada kamera 1
menunjukkan nilai error 2,4% untuk jumlah bibit, sedangkan pada kamera 2, nilai
error untuk jumlah daun, tinggi daun, dan diameter daun adalah masing-masing
2,6%, 2,3%, dan 2,7%. Sistem ini berhasil melakukan evaluasi otomatis setiap hari
pada jam 10 pagi selama masa persemaian. | id |
dc.description.abstract | The evaluation of shallot seed performance is a crucial aspect in the
cultivation process, influencing the quality and productivity of the crop. This
research focuses on designing an automated machine vision system to accurately
assess the performance of shallot seeds. The study involves several stages,
including the design of a monitoring system, seeding devices, seedling preparation,
and performance testing of the monitoring system. Two cameras are positioned at
the top and side of the planting tray, connected to a program on a Raspberry Pi. This
program processes images to calculate parameters such as the number of seedlings,
leaves, leaf height, and leaf diameter. The evaluation results from camera 1 show
an error rate of 2.4% for the number of seedlings, while on camera 2, the error rates
for the number of leaves, leaf height, and leaf diameter are 2.6%, 2.3%, and 2.7%,
respectively. The system successfully conducts automated evaluations every day at
10 AM during the seedling period. | id |
dc.language.iso | id | id |
dc.publisher | IPB University | id |
dc.title | Rancang Bangun Machine Vision untuk Evaluasi Keragaan Benih Bawang Merah dari True Shallot Seed (TSS) pada Lingkungan Terkendali | id |
dc.type | Undergraduate Thesis | id |
dc.subject.keyword | machine-vision | id |
dc.subject.keyword | monitoring | id |
dc.subject.keyword | raspberry-pi | id |
dc.subject.keyword | true shallot seed | id |