Automated evaluation of body condition score in goats with Mobile-NetV2 and Transfer Learning
DOI:
https://doi.org/10.48165/ijapm.2026.42.1.17Abstract
Body condition score (BCS) is a vital process for assessing body reserves in livestock, impacting their health and productivity. However, traditional BCS methods, based on observation and touching specific anatomical regions are subjective and labor-intensive, hindering their widespread adoption. Artificial intelligence (AI) techniques have emerged as promising solutions in this field, specifically convolutional neural networks (CNNs). We used Mobile NetV2 network and transfer learning technology to automate body condition assessment in goats using imaging data. The model was trained on 230 images depicting the dorsal view of the hind flank of a goat, achieving an overall accuracy of 98%, which is higher than other common deep learning architectures used in previous studies. The proposed Mobile-NetV2 lightweight CNN and transfer learning Architecture for estimating BCS in goats outperformed all methods used in previous studies. Furthermore, its feasibility and application onboard cameras, as they are autonomous and adaptable to environmental constraints, makes it a valuable tool for efficiently and sustainably estimating BCS in goats. We concluded that enabling goat farmers to achieve sound management of body reserves according to the different stages of reproductive and productive performance by applying artificial intelligence (AI) as an accurate tool in livestock breeding for the purpose of sustainably assessing BCS and meeting the nutritional needs of animals is of paramount importance for improving management methods and increasing goat productivity by supporting reliable evidence-based decision-making processes.References
An, Y., Song, Y., Meng, Z., Wang, Y., Wang, B., Liu, N., Qi, J., Xu, M., & An, X. (2025). Automated evaluation of dairy goat body condition and analysis of lumbar features, milk composition, and blood biochemical indicators. Small Ruminant Research, 248, 107504. https://doi.org/10.1016/j.smallrumres.2025.107504
Atoui, A., Carabaño, M. J. C., Lasoued, M., Laoussi, M., Abdennebi, M., Tlahig, S., Ben Salem, F., & Najari, S. (2023). Prediction of birth weight using body measurements of local caprine population kids under arid conditions. Tropical Animal Health and Production, 55(5), 1–9. https://doi.org/10.1007/s11250-023-03865-0
Atoui, A., Najari, S., Díaz, C., Ramón, M., Ragab, M., Laaroussi, A., Abdennebi, M., & Carabaño, M. J. (2024). Evaluating heat stress effects on growth in Tunisian kids. Animals, 14(19), 2846. https://doi.org/10.3390/ani14192846
Cevik, K. K. (2020). Deep learning-based real-time body condition score classification system. IEEE Access, 8, 213950–213957. https://doi.org/10.1109/ACCESS.2020.3040805
Datt, M., Bhateshwar, V., & Rai, D. C. (2023). Importance of body weight, age, and body condition in weaning of goat kids. Journal of Livestock Science, 14(1), 71–77. https://doi.org/10.33259/JLivestSci.2023.71-77
Desha, N. H., Asha, A. A. A., Jalil, M. A., Bhuiyan, A. K. F. H., & Amin, M. R. (2022). Genetic evaluation of Black Bengal goats. Bangladesh Journal of Livestock Research, 29(1–2), 21–33. https://doi.org/10.3329/bjlr.v29i1.72058
Figueiredo Filho, L. A. S., Sarmento, . L. R., Campelo, J. E. G., Almeida, M. J. O., Sousa Junior, A., Santos, N. P. S., Costa, M. S., Torres, T. S., & Sena, L. S. (2018). Genetic parameters for marbling and body score in goats. Asian-Australasian Journal of Animal Sciences, 31(9), 1407–1414. https://doi.org/10.5713/ajas.17.0490
Gafsi, N., Martin, O., Bidan, F., Grimard, B., & Puillet, L. (2025). Milk production, body weight, and reproductive success in dairy goats. Theriogenology, 234, 83–91. https://doi.org/10.1016/j.theriogenology.2024.12.005
Gallego-Calvo, L., Gatica, M. C., Guzmán, J. L., & Zarazaga, L. A. (2015). Body condition score and reproductive performance in goats. Animal Reproduction Science, 156, 51–57. https://doi.org/10.1016/j.anireprosci.2015.03.001
Ghosh, C. P., Datta, S., Mandal, D., Das, A. K., Roy, D. C., Roy, A., & Tudu, N. K. (2019). Body condition scoring in goats: Impact and significance. Journal of Entomology and Zoological Studies, 7(2), 554–560.
Gonçalves, M. A., Castro, M. S. M., Carrara, E. R., Raineri, C., Rennó, L. N., & Schultz, E. B. (2025). Prediction of body condition score using random forest. Animals, 15(10), 1449. https://doi.org/10.3390/ani15101449
Gupta, V., Farooqui, M. M., & Verma, A. (2023). Body condition score as a health assessment tool. The Science World, 3(4), 556–560. https://doi.org/10.5281/zenodo.7875455
Hassan, E. K., & Saud, J. H. (2023). 3D hand pose estimation for augmented reality. Journal of Intelligent Systems and Internet of Things, 10(2), 90–101. https://doi.org/10.54216/JISIoT.100208
Huang, X., Hu, Z., Wang, X., Yang, X., Zhang, J., & Shi, D. (2019). SSD method for body condition scoring in dairy cows. Animals, 9(7), 470. https://doi.org/10.3390/ani9070470
Iqbal, F., Waheed, A., & Faraz, A. (2022). Machine learning methods for predicting goat body weight. Pakistan Journal of Zoology, 54(1), 231–238. https://doi.org/10.17582/JOURNAL.PJZ/20191003081007
Koyuncu, M., & Altınçekiç, Ş. O. (2013). Importance of body condition score in dairy goats. Macedonian Journal of Animal Science, 3(2), 167–173. https://doi.org/10.54865/MJAS1332167K
Li, J., Zeng, P., Yue, S., Zheng, Z., Qin, L., & Song, H. (2025). YOLOv5-based body condition scoring system. Artificial Intelligence in Agriculture, 15(2), 350–362. https://doi.org/10.1016/j.aiia.2025.01.010
Li, K., & Teng, G. (2022). Deep learning-based body measurement in livestock. Electronics, 11(7), 993. https://doi.org/10.3390/electronics11070993
Liu, D., He, D., & Norton, T. (2020). Estimation of cattle body condition score using depth images. Biosystems Engineering, 194, 16–27. https://doi.org/10.1016/j.biosystemseng.2020.03.011
Liu, Z., Chen, X., Pan, B., Li, S., Yang, L., Ma, H., Liu, L., & Zhou, J. (2023). Pig body condition scoring using EfficientNet-B0. Academic Journal of Computing and Information Science, 6(6), 156–162.
Ma, W., Qi, X., Sun, Y., Gao, R., Ding, L., Wang, R., Peng, C., Zhang, J., Wu, J., Xu, Z., Li, M., Zhao, H., Huang, S., & Li, Q. (2024). Computer vision for livestock body measurement: A review. Agriculture, 14(2), 306. https://doi.org/10.3390/agriculture14020306
Makamua, T. C., Madikadike, M. K., Mokoena, K., & Tyasi, T. L. (2023). Body measurement traits and milk yield in goats. Revista Mexicana de Ciencias Pecuarias, 14(2), 423–433. https://doi.org/10.22319/rmcp.v14i2.6190
Martins, B. M., Mendes, A. L. C., Silva, L. F., Moreira, T. R., Costa, J. H. C., Rotta, P. P., Chizzotti, M. L., & Marcondes, M. I. (2020). Estimating body traits using 3D cameras. Livestock Science, 236, 104054. https://doi.org/10.1016/j.livsci.2020.104054
Misbah, F., Derese, M., & Haiyre, G. (2023). Prediction of goat body weight. Greener Journal of Agricultural Sciences, 13(4), 217–226.
Mullins, I. L., Truman, C. M., Campler, M. R., Bewley, J. M., & Costa, J. H. C. (2019). Validation of automated BCS system. Animals, 9(6), 287. https://doi.org/10.3390/ani9060287
Okere, C., Abrahamsen, F., & Gurung, N. (2022). Body condition score and reproductive performance in goats. International Journal of Agricultural Research, Innovation and Technology, 12(2), 64–73.
Rodríguez Álvarez, J., Arroqui, M., Mangudo, P., et al. (2018). Body condition estimation using CNN. Computers and Electronics in Agriculture, 155, 12–22. https://doi.org/10.1016/j.compag.2018.09.039
Rodríguez Álvarez, J., Arroqui, M., Mangud, P., et al. (2019). BCS estimation using deep learning. Agronomy, 9(2), 90. https://doi.org/10.3390/agronomy9020090
Sahoo, S., Ghosh, C. P., & Datta, S. (2022a). BCS and reproductive performance in goats. The Pharma Innovation Journal, 11(11), 1690–1694.
Sahoo, S., Ghosh, C. P., & Datta, S. (2022b). Condition scoring as a management tool. Indian Journal of Animal Health, 61(1), 38–45.
Sahoo, S. R., Ghosh, C. P., & Datta, S. (2023). BCS and physical attributes in goats. International Journal of Bio-resource and Stress Management, 14(4), 540–545.
Shirke, V. G., Kandalkar, Y. B., & Tanpure, M. U. (2024). Nutritional status assessment using BCS. International Journal of Veterinary Sciences and Animal Husbandry, 9(3), 128–130.
Temenos, A., Voulodimos, A., Korelidou, V., et al. (2024). Goat-CNN for BCS estimation. Journal of Agriculture and Food Research, 16, 101174. https://doi.org/10.1016/j.jafr.2024.101174
Tesema, Z., Deribe, B., Tilahun, M., et al. (202). Genetic parameters of goats. PLOS ONE, 20(1), e0318864. https://doi.org/10.1371/journal.pone.0318864
Vall, E., Blanchard, M., Sib, O., et al. (2025). Standardized BCS system for tropical animals. Tropical Animal Health and Production, 57(2), 106.
Veliz-Deras, F. G., Meza-Herrera, C. A., et al. (2023). Body condition and reproductive fitness. Agriculture, 13(7), 1337.
Venkata Reshma, C. H., Anitha, A., Jagadeeswara Rao, S., & Muralidhar, M. (2021). BCS and postpartum changes in goats. International Journal of Current Microbiology and Applied Sciences, 10(1), 2639–2645.
Venkata Reshma, C. H., Anitha, A., Jagadeeswara Rao, S., & Muralidhar, M. (2022). BCS and body measurements in goats. International Journal of Bio-resource and Stress Management, 13(2), 131–136.
Vieira, A., Brandão, S., Monteiro, A., Ajuda, I., & Stilwell, G. (2015). Visual BCS system for dairy goats. Journal of Dairy Science, 98(9), 6597–6608.
Widiyono, I., Sarmin, S., & Yanuartono, Y. (2020). Influence of BCS on metabolic and reproductive status. Journal of Applied Animal Research, 48(1), 201–206
Xiong, Y., Condotta, I. C. F. S., Musgrave, J. A., et al. (2023). Estimating body weight and BCS in cows. Translational Animal Science, 7, txad085.
Yukun, S., Pengju, H., Yujie, W., et al. (2019). Automatic monitoring system for dairy cows. Journal of Dairy Science, 102(11), 10140–10151.
Zhang, A. L., Wu, P., Jiang, C. X. H., et al. (2018). Visual image analysis for sheep body size. Journal of Applied Animal Research, 46(1), 1004–1015.
Zhao, K., Zhang, M., Shen, W., et al. (2023). Automatic BCS using EfficientNet. Computers and Electronics in Agriculture, 205, 107588.
