Recognizing Cow Muzzle Patterns using the Convolution Neural Network (CNN) Algorithm

Sulthon Zamroni, Giri Wahyu Wiriasto, Bulkis Kanata

Abstract


In today's digital era, any task or problem can be solved with minimal effort, especially in livestock identification such as cattle. Numerous systems and algorithms have been developed to recognize cattle, ranging from body shape, fur patterns, to specific parts of the cattle. This research aims to develop a cattle muzzle identification system using convolutional neural networks method with Alexnet architecture and to identify the factors that can decrease the accuracy of prediction results. The results of this research can help cattle farmers manage their livestock data more effectively, as traditional identification methods can cause discomfort and stress to the cattle. This research also serves as a reference for future researchers in developing cattle recognition research. Additionally, this research can be used to support insurance programs such as Cattle Farming Insurance (AUTS) to protect farmers from losses due to cattle theft and death. Cattle recognition through their muzzles using the CNN method can produce relatively high results. By slightly modifying the AlexNet architecture, this system can recognize cattle with an accuracy of 85%..

Full Text:

PDF

References


A I Awad, “From classical methods to animal biometrics: A review on cattle identification and tracking,” Computers and Electronics in Agriculture, vol 123, 2016

M Vlad, R A Parvulet, M S Vlad et al, “A survey of livestock identification systems,” in Proceedings of the 13th WSEAS International Conference on Automation and Information,(ICAI12) Iasi, Romania: WSEAS Press, 2012.

D Petrovska-Delacretaz, A Edwards, J Chiassoli, G Chollet, and D S ´ Pilliod, “A reference system for animal biometrics: Application to the northern leopard frog,” in 2014 1st International Conference on Advanced Technologies for Signal and Image Processing (ATSIP) IEEE, 2014

A Johnston and D Edwards, “Welfare implications of identification of cattle by ear tags,” Veterinary Record, vol 138, no 25, pp 612–614, 1996.

G H Collins, S L Petersen, C A Carr, and L Pielstick, “Testing vhf/gps collar design and safety in the study of free-roaming horses,” PloS one, vol 9, no 9, p e103189, 2014.

Gatc, J, “Image segmentation of cattle muzzle using region merging statistical technic”, Journal of Computer Science and Technology, 12(3), 11-20, 2015.

Arrofiqoh, E N, & Harintaka, H., “Implementasi Metode Convolutional Neural Network Untuk Klasifikasi Tanaman Pada Citra Resolusi Tinggi” Geomatika, 2018.

Abror, Z F, & Zaki, “Klasifikasi Citra Kebakaran dan Non Kebakaran Menggunakan Convolutional Neural Network”, Jurnal Ilmiah Teknologi dan Rekayasa, 24(2), 1-10, 2019.

Bello, Rw, Talib, AZH, Mohamed, ASAB, “Deep learning-based architectures for recognition of cow using cow nose image pattern”, Gazi University Journal of Science 33, 831–844, 2020.

Sanjel, A B, “Non-invasive muzzle matching for cattle identification using deep learning Journal of Animal Science”, 99(3), 123-145, 2023.

Krizhevsky, A, Sutskever, I, Hinton, GE “ImageNet classification with deep convolutional neural networks,” Adv Neural Inf Process Syst (NIPS) 2012.

Xiaobing Han, Yanfei Zhong, Liqin Cao, & Liangpei Zhang “Pre-Trained AlexNet Architecture with Pyramid Pooling and Supervision for High Spatial Resolution Remote Sensing Image Scene Classification,” Wuhan University, China, 2017.

Giri Wahyu Wiriasto, Misbahuddin, A. Sjamjiar Rachman, Muhamad Syamsu Iqbal, Djul Fikry Budiman, Lalu Ahmad Syamsul Irfan Akbar, Bagi Hartawan, and Eko Prasetyo Wicaksono. “Studi Pengembangan Sistem Pengenalan Individu Sapi Berbasis Biometrik Muzzle Menggunakan Model Mobilenetv2”, Journal of Computer Science and Informatics Engineering 8, no. 1 (2024): 84-93.

https://doi.org/10.29303/jcosine.v8i1.594.

Ali Shojaeipour, Greg Falzon, Paul Kwan, Nooshin Hadavi, Frances C. Cowley, dan David Paul. “Automated Muzzle Detection and Biometric Identification via Few-Shot Deep Transfer Learning of Mixed Breed Cattle”, Agronomy 11, no. 11 (2021): 2365. https://doi.org/10.3390/agronomy11112365.

Bello, Rw, Talib, AZH, Mohamed, A.S.A., Olubummo, D.A., Otobo, F.N., 2020a. “Image-based Individual Cow Recognition using Body Pattern”, (IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 11, No. 3, 2020.

Achour, B., Belkadi, M., Filali, I., Laghrouche, M., Lahdir, M., “Image Analysis For Individual Identification And Feeding Behaviour Monitoring Of Dairy Cows Based On Convolutional Neural Networks (CNN) ”, Biosystems Engineering 198, 31–49, 2020.

Yang, Z., Xiong, H., Chen, X., Liu, H., Kuang, Y., Gao, Y., “Dairy cow tiny face recognition based on convolutional neural networks”, in Chinese Conference on Biometric Recognition, Springer. pp. 216–222, 2019.

Guan, H., Motohashi, N., Maki, T., Yamaai, T., “Cattle identification and activity recognition by surveillance camera”. Electronic Imaging 2020, 174–1, 2020.

Andrew, W., Greatwood, C., Burghardt, T., “Visual localisation and individual identification of holstein friesian cattle via deep learning”, in Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 2850–2859, 2017.

Wang, X., Cheng, X., Chen, Z., Xu, F., “A method for individual identification of dairy cows based on deep learning”, in: Proceedings of the 2020 2nd International Conference on Robotics, Intelligent Control and Artificial Intelligence, pp. 186–191, 2020.

Zhou, Hao, and Jiashi Feng. “Overfitting Mechanism and Avoidance in Deep Neural Networks”, arXiv preprint arXiv:1901.06566, 2019.

Auliaddina, Siti, and Toni Arifin. "Penggunaan data augmentasi dan hyperparameter tuning dalam klasifikasi jenis batik menggunakan model CNN." SISTEMASI: Jurnal Sistem Informasi, vol. 13, no. 1, 2024, pp. 114-128. https://doi.org/10.32520/stmsi.v13i1.3395.




DOI: https://doi.org/10.32520/stmsi.v13i6.4598

Article Metrics

Abstract view : 71 times
PDF - 10 times

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.