View Item 
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Faculty of Agriculture
      • UT - Agronomy and Horticulture
      • View Item
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Faculty of Agriculture
      • UT - Agronomy and Horticulture
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Sistem Identifikasi Varietas Padi Berbasis Citra Drone untuk Mendukung Proses Sertifikasi Benih

      Thumbnail
      View/Open
      Cover (1.031Mb)
      Fulltext (2.447Mb)
      Lampiran (1.188Mb)
      Date
      2022
      Author
      Ardiyansah, Ardo
      Zamzami, Ahmad
      Wulandari
      Metadata
      Show full item record
      Abstract
      Proses sertifikasi benih di Indonesia dihadapkan dengan tantangan semakin berkurangnya petugas Pengawas Benih Tanaman (PBT) dan beban kerja yang meningkat dalam hal pengawasan benih bersertifikat. Pemanfaatan teknologi menjadi suatu hal yang penting dalam meningkatkan efisiensi pada pemeriksaan lapangan, salah satu pemeriksaan tersebut adalah pemeriksaan kebenaran varietas tanaman padi yang disertifikasi. Penelitian ini dilakukan untuk mengembangkan sistem identifikasi varietas tanaman padi pada pemeriksaan lapangan sertifikasi benih berbasis citra drone dengan menerapkan algoritme Convolutional Neural Network (CNN). Penelitian ini dilakukan dengan mengidentifikasi dua varietas padi yang berbeda berdasarkan karakter agronomisnya, kemudian membangun model CNN untuk mengotomatisasi identifikasi varietas tersebut berbasis citra drone. Hasil analisis data pada karakter agronomis yang diamati menjustifikasi bahwa kedua varietas yang digunakan berbeda, baik pada karakter tinggi tanaman, jumlah anakan, warna daun, jumlah anakan produktif, panjang malai, dan jumlah gabah per malai. Penelitian ini menghasilkan tiga jenis model CNN yang mampu mengidentifikasi secara akurat varietas IPB 3S dan Inpari 32 dengan tingkat akurasi antara 99,52% sampai 100%.
       
      The seed certification process in Indonesia is faced with the challenge of a decreasing number of seed inspectors and an increasing workload in supervising certified seeds. The utilization of technology becomes an important thing in increasing the efficiency of field inspections, one of these inspections is checking the correctness of certified rice varieties. This research was conducted to develop a rice varietal identification system for field inspection of drone image-based seed certification by applying the Convolutional Neural Network (CNN) algorithm. This research was conducted by identifying two varieties different rice varieties based on their agronomic characters, then building a CNN model to automate the identification of these varieties based on drone imagery. The results of data analysis on the observed agronomic characters justified that the two varieties used were different, in terms of plant height, number of tillers, leaf color, number of productive tillers, panicle length, and number of grains per panicle. This study produced three types of CNN models that could accurately identify the varieties of IPB 3S and Inpari 32 with an accuracy rate of 99.52% to 100%.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/114773
      Collections
      • UT - Agronomy and Horticulture [3082]

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository
        

       

      Browse

      All of IPB RepositoryCollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

      My Account

      Login

      Application

      google store

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository