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

      Development of Realtime Veneer Color Matching Device Prototype on Sketch Veneer Line Using YOLOv7 at PT Corinthian Industries Indonesia

      Thumbnail
      View/Open
      Cover (1.017Mb)
      Full text (1.557Mb)
      Appendix (754.8Kb)
      Date
      2022
      Author
      Wibowo, Muhamad Rafly Hafizh
      Djatna, Taufik
      Metadata
      Show full item record
      Abstract
      Veneer color matching is an activity to equalize the colors in the veneer sketch process according to the established rules. Veneer color matching activities carried out manually will cause color mismatch due to the human eye's limitations in distinguishing colors, affecting the quality of the product itself or becoming defective. By using the Computational Thinking approach, a solution is obtained in the form of a real-time color matching system using YOLOv7 with a custom veneer color standard of PT Corinthian Industries Indonesia. The live videos taken by the camera were then processed in YOLOv7 with the veneer color standard dataset. The camera is connected with a mini HDMI cable to the video capture and the output is displayed on the monitor screen. The dataset mAP is 68%, which is sufficient because the system works with an adjusted color matching threshold, +1 or -1, from the first veneer color placed on the sketch table.
       
      Color matching veneer merupakan kegiatan untuk menyamakan warna dalam proses sketsa veneer sesuai dengan aturan yang telah ditetapkan. Kegiatan pencocokan warna veneer yang dilakukan secara manual akan menimbulkan ketidaksesuaian warna karena keterbatasan mata manusia dalam membedakan warna, mempengaruhi kualitas produk itu sendiri atau menjadi cacat. Dengan menggunakan pendekatan Computational Thinking, diperoleh solusi berupa sistem pencocokan warna secara real-time menggunakan YOLOv7 dengan standar warna custom veneer PT Corinthian Industries Indonesia. Video langsung yang diambil oleh kamera kemudian diproses di YOLOv7 dengan dataset standar warna veneer. Kamera terhubung dengan kabel mini HDMI untuk merekam video dan output ditampilkan di layar monitor. Dataset mAP adalah 68%, yang cukup karena sistem bekerja dengan ambang pencocokan warna yang disesuaikan, +1 atau -1, dari warna veneer pertama yang ditempatkan pada meja sketsa.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/114592
      Collections
      • UT - Agro-Industrial Engineering [2774]

      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