CD Skripsi

Implementasi Yolov8 Untuk Mengklasifikasi Kualitas Telur Berdasarkan Warna Dan Tekstur Cangkang Cover

---

ABSTRACT
Egg quality is a crucial aspect in the food industry, particularly to ensure the safety and quality of products distributed to consumers. Manual egg quality classification often faces challenges such as subjective assessment, time constraints, and inconsistency risks. External factors such as shell color and texture are key indicators in evaluating egg quality. This study develops an egg quality classification system based on Artificial Intelligence (AI) using a Deep Learning approach with the Convolutional Neural Network (CNN) method and the You Only Look Once (YOLOv8) algorithm. The system is designed to classify eggs into three categories: good, fairly good, and poor quality, based on egg shell images. The dataset used is a combination of directly captured images and online sources, totaling 1,417 images, which underwent preprocessing and labeling stages. The training results show that the model can detect egg quality with a precision of 0.95, recall of 0.98, and F1-score of 0.97. The system supports real-time detection using a camera and can assist the poultry industry in automating the egg sorting process quickly and consistently. Future work includes expanding dataset variety and testing newer detection algorithms to improve system accuracy.
Keywords: YOLOv8, Convolutional Neural Network, Pengujian Real-time

---

Ketersediaan

Informasi Detail

Judul Seri

-

No. Panggil

2007136210

Penerbit

Pekanbaru : Universitas Riau – F.TEKNIK – INFORMATIKA., 2025

Deskripsi Fisik

-

Bahasa

Indonesia

ISBN/ISSN

-

Klasifikasi

2007136210

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

TEKNIK INFORMATIKA

Info Detail Spesifik

-

Pernyataan Tanggungjawab

daus

Versi lain/terkait

Lampiran Berkas

Komentar

---

Anda harus masuk sebelum memberikan komentar