CD Skripsi

Deteksi Kualitas Brondolan Kelapa Sawit Berbasis Pencitraan Komputer Dan Algoritma Yolov8

---

This study aims to develop an automatic system for detecting the quality of loose fruit of the oil palm using the YOLOv8 algorithm based on digital imaging. A total of 200 loose fruit samples were classified into four quality categories: fresh, rotten, dry, and mouldy. Image acquisition was conducted using an RGB camera with a resolution of 640×480 pixels, resulting in 800 labeled images. The dataset was split into training (80%) and testing (20%) sets. The YOLOv8 model was trained for 20 epochs with a confidence score threshold of 0,7. The model’s performance was evaluated using a confusion matrix, achieving an average classification accuracy of 92,5% across the four classes. Additional analyses included RGB intensity measurements and fruit hardness testing using a penetrometer. RGB values exhibited distinctive patterns for each class, while hardness tests showed the highest average firmness in fresh loose fruits and the lowest in rotten ones. The findings demonstrate that this system can provide fast, objective, and accurate quality detection of oil palm loose fruits, with RGB and hardness analyses offering significant supporting parameters.
Keywords: loose fruit of the oil palm, quality detection, YOLOv8, RGB color analysis, image processing

---

Ketersediaan

Informasi Detail

Judul Seri

-

No. Panggil

2103112432

Penerbit

Pekanbaru : Universitas Riau FMIPA Fisika., 2025

Deskripsi Fisik

-

Bahasa

Indonesia

ISBN/ISSN

-

Klasifikasi

2103112432

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

FISIKA

Info Detail Spesifik

-

Pernyataan Tanggungjawab

Mutia

Versi lain/terkait

Lampiran Berkas

Komentar

---

Anda harus masuk sebelum memberikan komentar