PENGEMBANGAN DAN EVALUASI EKSPERIMENTAL SISTEM DETEKSI KUALITAS TELUR REAL-TIME BERBASIS PENGOLAHAN CITRA DIGITAL DAN MODEL YOLO PADA PERANGKAT EDGE

Iqbal May Aryanto; Syaiful Mansur; Ayu Sintianingrum; Ayang Kinasih; Eko Hari Tiarto

doi:10.46764/teknimedia.v7i1.384

Iqbal May Aryanto Politeknik Negeri Lampung
Syaiful Mansur Politeknik Negeri Lampung
Ayu Sintianingrum Politeknik Negeri Lampung
Ayang Kinasih Politeknik Negeri Lampung
Eko Hari Tiarto Politeknik Negeri Lampung

DOI: https://doi.org/10.46764/teknimedia.v7i1.384

Kata Kunci: Edge AI, Kualitas Telur, Raspberry Pi, Real-Time Detection, YOLOv8n

Abstrak

Permintaan telur ayam sebagai sumber protein hewani terus meningkat, namun adopsi teknologi inspeksi otomatis di peternakan skala kecil masih terbatas karena biaya tinggi. Penelitian ini mengembangkan prototipe sistem deteksi kualitas telur real-time yang mandiri dan murah berbasis paradigma edge computing. Sistem diimplementasikan pada Raspberry Pi 4 Model B menggunakan model deep learning YOLOv8n untuk mengklasifikasikan telur ke dalam tiga kategori: Baik, Retak, dan Pecah. Akuisisi data visual menggunakan Raspberry Pi Camera Module 3 dengan dukungan pencahayaan LED ring terkontrol pada jarak objek tetap 20 cm untuk mengatasi variasi intensitas cahaya lingkungan. Evaluasi eksperimental menggunakan 1.080 sampel menunjukkan sistem mencapai akurasi optimal sebesar 91,30% pada resolusi 320x320 piksel di bawah kondisi cahaya terkontrol. Secara teknis, sistem menunjukkan stabilitas dengan penggunaan CPU 43-76% dan suhu perangkat terjaga pada 48-51⁰C. Meskipun kecepatan pemrosesan berada pada 0,5-0,6 FPS, kemandirian sistem dari konektivitas awan menjadikannya solusi inspeksi objektif yang sangat aplikatif bagi peternak skala kecil di daerah dengan infrastruktur digital terbatas.

Referensi

[1] L. Convit et al., “Eggs as a Nutrient-Rich Food with Potential Relevance to Sleep Metabolic Health , and Well-Being During the Menopausal Transition : A Narrative Review,” pp. 1–24, 2025.
[2] M. Myers, C. Helen, and S. Ruxton, “Eggs : Healthy or Risky ? A Review of Evidence from High Quality Studies on Hen ’ s Eggs,” pp. 1–28, 2023.
[3] Z. Gao and J. Zheng, “Research Progress and Technological Application Prospects of Comprehensive Evaluation Methods for Egg Freshness,” pp. 1–19, 2025.
[4] A. Yu, “Evolution of the Spatial Patterns of Global Egg Trading Networks in the 21 Century,” 2023.
[5] A. Theresia, M. Ikhsan, F. N. Kacaribu, and S. Sumarto, “Spillover Effect of Food Producer Price Volatility in Indonesia,” pp. 1–29, 2025.
[6] P. A. Vlaicu, R. P. Turcu, M. Dumitru, A. E. Untea, and A. G. Oancea, “Future Directions for Sustainable Poultry Feeding and Product Quality : Alternatives from Insects , Algae and Agro-Industrial Fermented By-Products,” pp. 1–38, 2026.
[7] Q. Wang, Z. Yang, C. Liu, R. Sun, and S. Yue, Research Progress on Non-Destructive Testing Technology and Equipment for Poultry Eggshell Quality. 2025.
[8] J. So, S. Y. Joe, S. H. Hwang, and S. J. Hong, “Current advances in detection of abnormal egg : a review,” vol. 64, no. 5, pp. 813–829, 2022.
[9] T. Rho and B. Cho, “Non-Destructive Evaluation of Physicochemical Properties for Egg Freshness : A Review,” 2024.
[10] T. Imaging, “Nondestructive Detection of Egg Freshness Based on Infrared Thermal Imaging,” 2023.
[11] “Comp Rev Food Sci Food Safe - 2023 - Ahmed - Non‐destructive optical sensing technologies for advancing the egg industry.pdf.”
[12] C. Deng, X. Fang, X. Wang, and K. Law, “SoFtware Orchestrated and Hardware Accelerated ArtiFicial Intelligence : Toward Low Latency Edge Computing,” no. August, pp. 110–117, 2022.
[13] V. B. Yucedag and I. Dalkiran, “A Raspberry Pi-based Hardware Implementation of Various Neuron Models,” pp. 19–28, 2024.
[14] E. Gamess, S. Hernandez, E. Gamess, and S. Hernandez, “Performance Evaluation of Different Raspberry Pi Models for a Broad Spectrum of Interests Performance Evaluation of Different Raspberry Pi Models for a Broad Spectrum of Interests,” vol. 13, pp. 819–829, 2022.
[15] M. Deniz and I. Bogrekci, “Real-Time Detection of Hole-Type Defects on Industrial Components Using Raspberry Pi 5,” no. Ml, pp. 1–26, 2025.
[16] D. Q. G. Dqg and L. W. V Fdxvdwlyh, “Price elasticity of hybrid chicken egg demand in Indonesia and Pamekasan and its causative factors”, doi: 10.1088/1742-6596/1872/1/012019.
[17] M. Hussain, “YOLO-v1 to YOLO-v8 , the Rise of YOLO and Its Complementary Nature toward Digital Manufacturing and Industrial Defect Detection,” 2023.
[18] A. Vijayakumar and S. Vairavasundaram, “YOLO-based Object Detection Models: A Review and its Applications,” Multimed. Tools Appl., vol. 83, no. 35, pp. 83535–83574, 2024, doi: 10.1007/s11042-024-18872-y.
[19] X. Song, S. Cao, J. Zhang, and Z. Hou, “Steel Surface Defect Detection Algorithm Based on YOLOv8,” 2024.
[20] L. Zhang, B. Li, Y. Cui, Y. Lai, and J. Gao, “Research on improved YOLOv8 algorithm for insulator defect detection,” J. Real-Time Image Process., vol. 21, no. 1, p. 22, 2024, doi: 10.1007/s11554-023-01401-9.
[21] H. Yi, B. Liu, B. Zhao, and E. Liu, “Small Object Detection Algorithm Based on Improved YOLOv8 for Remote Sensing,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 17, pp. 1734–1747, 2024, doi: 10.1109/JSTARS.2023.3339235.
[22] T. Jiang et al., “Improved YOLOv8 Model for Lightweight Pigeon Egg Detection,” Animals, vol. 14, no. 8, pp. 1–18, 2024, doi: 10.3390/ani14081226.
[23] M. Khazaal, A. Maaroof, and M. S. Bouhlel, “Real-Time Object Detection Using YOLO-8 Model : A Drone- Based Approach,” vol. 1, pp. 190–204, 2025, doi: 10.58346/JOWUA.2025.I1.011.
[24] M. C. Sahin, “Evaluation and Selection of Hardware and AI Models for Edge Applications : A Method and A Case Study on UAVs,” pp. 1–38, 2025.
[25] P. Setiaji, K. Adi, and B. Surarso, “Ingénierie des Systèmes d ’ Information Development of Classification Method for Determining Chicken Egg Quality Using GLCM- CNN Method,” vol. 29, no. 2, pp. 397–407, 2024.
[26] X. Yang, R. B. Bist, S. Subedi, and L. Chai, “A Computer Vision-Based Automatic System for Egg Grading and Defect Detection,” Animals, vol. 13, no. 14, 2023, doi: 10.3390/ani13142354.