Image of Klasifikasi Sampah Organik Menggunakan Pencitraan Komputer Berbasis Algoritma Deteksi Objek Yolo
Penanda Bagikan

CD Skripsi

Klasifikasi Sampah Organik Menggunakan Pencitraan Komputer Berbasis Algoritma Deteksi Objek Yolo

ABSTRACT
Organic waste is still mixed with other types of waste in landfills. Waste segregation is important to process to facilitate the recycling process. Modern waste segregation method is required for less time and more effective than traditional methods. Modern waste segregation can be supported using computer vision. Computer vision consists of a combination of optical and non optical components. Computer vision utilizes the YOLO (You Only Look Once) object detection algorithm model to detect and classify types of organic waste. In this research, YOLO algorithm detects and classifies organic waste into two types, namely used beverage carton (UBC)/paper organic waste and non UBC/paper organic waste. The result of the YOLO testing process is a bounding box that contains the object name and its prediction accuracy by the system. Confusion matrix was used to evaluate the system in classifying. The confusion matrix shows that the system has succeeded in classifying organic waste with an accuracy of 98,77%. The Principal Component Analysis (PCA) was also used for waste classification by utilizing the sample RGB values. PCA results show a tendency to group samples with an accuracy of 96,93% data distribution. The results show that YOLO object detection algorithm is able detect and classify organic waste having the potential to use in modern waste segregation.
Keywords: Organic Waste, Computer Vision, Object Detection Algorithm, YOLO, Confusion Matrix

Ketersediaan

Tidak ada salinan data

Informasi Detail
Judul Seri
-
No. Panggil
1803111103
Penerbit
Pekanbaru : Universitas Riau - FMIPA - Fisika.,
Deskripsi Fisik
-
Bahasa
Indonesia
ISBN/ISSN
-
Klasifikasi
1803111103
Tipe Isi
-
Tipe Media
-
Tipe Pembawa
-
Edisi
-
Subjek
FISIKA
Info Detail Spesifik
-
Pernyataan Tanggungjawab
Versi lain/terkait

Tidak tersedia versi lain

Lampiran Berkas
Komentar
Anda harus masuk sebelum memberikan komentar