Cattle Breed Classification Using ResNet-50 Hyperparameter Optimization Based on Transfer Learning
DOI:
https://doi.org/10.70609/jusifor.v5i1.8778Keywords:
Klasifikasi, Ras Sapi, ResNet-50, Transfer Learning, Hyperparameter TuningAbstract
Cattle breed identification presents a challenge in modern livestock
management, particularly for breeds exhibiting high morphological
similarities. This study aims to optimize cattle breed image classification
performance using the ResNet-50 Convolutional Neural Network (CNN)
architecture. The research methodology begins with preprocessing, which
includes image resizing to 224×224 pixels, normalization, and the application
of Data Augmentation to enhance training data diversity. The model was
trained using the Adam optimizer with specific hyperparameter setting
scenarios. The primary focus of this research is to evaluate the effectiveness of
the Transfer Learning method compared to training from scratch. The dataset
consists of 1,251 morphological images distributed across 5 breed classes
(Ayrshire, Brown Swiss, Holstein Friesian, Jersey, and Red Dane). Experimental
results demonstrate a significant performance disparity. The model trained
from scratch achieved a maximum accuracy of only 81%, whereas the Transfer
Learning-based model attained an accuracy of 95%. This 14% accuracy
improvement demonstrates that utilizing pre-trained weights combined with
Data Augmentation is highly effective in recognizing the visual characteristics
of cattle breeds with high precision.
References
[1] J. Xu, B. Gu, dan G. Tian, “Review of agricultural IoT technology,” 1 Januari 2022, KeAi Communications Co. doi: 10.1016/j.aiia.2022.01.001.
[2] S. Zamroni dkk., “Sistemasi: Jurnal Sistem Informasi Identifikasi Moncong Sapi menggunakan Metode Jaringan Saraf Tiruan Konvolusional (CNN),” Sistemasi: Jurnal Sistem Informasi, vol. 13, no. 6, hlm. 2479–2493, 2024, [Daring]. Tersedia pada: http://sistemasi.ftik.unisi.ac.id
[3] K. Komposisi Populasi Sapi Potong Berdasarkan Bangsa, J. Kelamin, dan Tingkat Umur di Daerah Suliki Kabupaten Lima Puluh Kota, F. Lismanto Syaiful, A. Fernando dan Khasrad, dan K. Kunci, “A Study of Beef Cattle Population Composition Based on Breed, Gender, and Age Levels in the Suliki Area of the Lima Puluh Kota District,” Journal of Livestock and Animal Health JLAH, vol. 7, no. 2, hlm. 32–41, 2024, doi: 10.32530/jlah.v7i2.47.
[4] Y. Qiao, C. Clark, S. Lomax, H. Kong, D. Su, dan S. Sukkarieh, “Automated Individual Cattle Identification Using Video Data: A Unified Deep Learning Architecture Approach,” Frontiers in Animal Science, vol. 2, 2021, doi: 10.3389/fanim.2021.759147.
[5] L. Alzubaidi dkk., “Review of deep learning: concepts, CNN architectures, challenges, applications, future directions,” J Big Data, vol. 8, no. 1, Des 2021, doi: 10.1186/s40537-021-00444-8.
[6] B. Xu dkk., “Evaluation of deep learning for automatic multi‐view face detection in cattle,” Agriculture (Switzerland), vol. 11, no. 11, Nov 2021, doi: 10.3390/agriculture11111062.
[7] L. Maramis, I. Nurtanio, dan H. Zainuddin, “Klasifikasi Sapi Perah dan Non-Perah Menggunakan Algoritma Convolutional Neural Network,” MALCOM: Indonesian Journal of Machine Learning and Computer Science, vol. 5, no. 2, hlm. 664–674, Apr 2025, doi: 10.57152/malcom.v5i2.1824.
[8] M. Akbar, A. S. Purnomo, dan S. Supatman, “Multi-Scale Convolutional Networks untuk Pengenalan Rambu Lalu Lintas di Indonesia,” Jurnal Sisfokom (Sistem Informasi dan Komputer), vol. 11, no. 3, hlm. 310–315, Des 2022, doi: 10.32736/sisfokom.v11i3.1452.
[9] M. Shafiq dan Z. Gu, “Deep Residual Learning for Image Recognition: A Survey,” 1 September 2022, MDPI. doi: 10.3390/app12188972.
[10] F. Yalda Sulistia dan A. Vatresia, “Penerapan Deep Learning Menggunakan Convolutional Neural Network (CNN) Untuk Klasifikasi Daging Ayam Menggunakan Arsitektur Resnet-50,” Journal of Information Technology and Computer Science (INTECOMS), vol. 7, no. 3, 2024.
[11] A. Salim dan M. Akbar, “Klasifikasi Ras Sapi Menggunakan Convolutional Neural Network,” Jurnal Sains Informatika Terapan (JSIT), vol. 4, no. 3, hlm. 664–673, 2025.
[12] M. Agil Izzulhaq, “Indonesian Journal of Mathematics and Natural Sciences Penerapan Algoritma Convolutional Neural Network Arsitektur ResNet50V2 Untuk Mengidentifikasi Penyakit Pneumonia,” 2024. [Daring]. Tersedia pada: https://journal.unnes.ac.id/journals/JM/index
[13] D. Tribuana, Hazriani, dan A. L. Arda, “Image Preprocessing Approaches Toward Better Learning Performance with CNN,” Jurnal RESTI, vol. 8, no. 1, hlm. 1–9, Feb 2024, doi: 10.29207/resti.v8i1.5417.
[14] I. A. P. F. Imawati, M. Sudarma, I. K. G. Darma Putra, I. P. A. Bayupati, dan M. Jo, “Training VGG16, MobileNetV1 and Simple CNN Models from Scratch for Balinese Inscription Recognition,” Lontar Komputer : Jurnal Ilmiah Teknologi Informasi, vol. 15, no. 03, hlm. 149, Jan 2025, doi: 10.24843/lkjiti.2024.v15.i03.p01.
[15] L. Alzubaidi dkk., “Deepening into the suitability of using pre-trained models of ImageNet against a lightweight convolutional neural network in medical imaging: an experimental study,” PeerJ Comput Sci, vol. 7, hlm. 1–27, 2021, doi: 10.7717/peerj-cs.715.
[16] M. B. Hossain, S. M. H. S. Iqbal, M. M. Islam, M. N. Akhtar, dan I. H. Sarker, “Transfer learning with fine-tuned deep CNN ResNet50 model for classifying COVID-19 from chest X-ray images,” Inform Med Unlocked, vol. 30, Jan 2022, doi: 10.1016/j.imu.2022.100916.
[17] C. Shorten dan T. M. Khoshgoftaar, “A survey on Image Data Augmentation for Deep Learning,” J Big Data, vol. 6, no. 1, Des 2019, doi: 10.1186/s40537-019-0197-0.
[18] J. A1 dan S. Sanjaya, “Optimalisasi Convolutional Neural Network Menggunakan Augmentasi dan Hyperparameter untuk Klasifikasi Daging Sapi dan Daging Babi,” JUSTIN (Jurnal Sistem dan Teknologi Informasi), vol. 12, no. 4, hlm. 623–629, 2024, doi: 10.26418/justin.v12i4.80337.
[19] A. Danang Krismawan, “Tomato Leaf Diseases Classification using Convolutional Neural Networks with Transfer Learning Resnet-50,” Computer Network, Computing, Electronics, and Control Journal, vol. 9, no. 2, hlm. 149–158, 2024.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Adz Dzikri Tamyizur Rijal, Bain Khusnul Khotimah
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
