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

      Aplikasi Deep Learning untuk Pengklasifikasian Bunga Melon

      Thumbnail
      View/Open
      Cover (543.9Kb)
      Fulltext (1.757Mb)
      Lampiran (132.9Kb)
      Date
      2025
      Author
      Mahatama, Satrio Pandu
      Subrata, I Dewa Made
      Metadata
      Show full item record
      Abstract
      Melon (Cucumis melo sp.) merupakan komoditas hortikultura yang sangat penting bagi masyarakat Indonesia dan bernilai ekonomis, tetapi memerlukan usaha yang intensif untuk membudidayakannya. Penyerbukan yang dilakukan secara manual umumnya cukup melelahkan dan merepotkan terutama apabila tenaga kerja yang terlibat sedikit pada kebun yang luas. Penelitian ini bertujuan membuat dan mengaplikasikan deep learning sebagai deteksi objek untuk mengklasifikasikan jenis kelamin bunga pada melon secara akurat dalam berbagai kondisi lingkungan serta menemukan informasi posisi koordinat piksel objek pada citra relatif terhadap gambarnya untuk polinasi otomatis. Metode penelitian yang digunakan meliputi: pengumpulan data berupa citra gambar, penganotasian, training model, dan validasi serta evaluasi performa model. Data yang dikumpulkan merupakan citra-citra sekunder yang diambil dari berbagai sumber dan pemotretan lapangan pada kebun lokal. Hasil penelitian menunjukkan model dapat mendeteksi objek dengan cukup baik, didapatkan evaluasi performa dengan nilai metrik precision 0,97, recall 0,84, mAP50 0,84, dan mAP50-95 0,65. Berdasarkan penelitian ini, dapat disimpulkan bahwa model cukup baik dan stabil dalam pendeteksian dan pengklasifikasian bunga melon.
       
      Melon (Cucumis melo sp.) is a horticultural commodity that is very important for the Indonesian people and has economic value, but requires intensive efforts to cultivate it. Manual pollination is generally quite tiring and troublesome, especially when the workforce is small in large gardens. This study aims to create and apply deep learning as object detection to accurately classify the sex of melon flowers in various environmental conditions and find information on the position of object pixel coordinates in the image relative to the image for automatic pollination. The research methods used include: data collection in the form of images, annotation, model training, and validation and evaluation of model performance. The data collected are secondary images taken from various sources and field photography in local gardens. The results show that the model can detect objects quite well, obtained performance evaluation with precision metric values of 0,97, 0,84 recall, mAP50 0,84, and mAP50-95 0,65. Based on this study, it can be concluded that the model is quite good and stable in detecting and classifying melon flowers.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/171395
      Collections
      • UT - Agricultural and Biosystem Engineering [3588]

      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