Automated evaluation of body condition score in goats with Mobile-NetV2 and Transfer Learning
DOI:
https://doi.org/10.48165/ijapm.2026.42.01.18Keywords:
Deep Learning, CNN, BCS, goatAbstract
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 differences in 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., Laroussi, M., Abdennebi, M., Tlahig, S., Ben Salem, F., & Najari, S. (2023). Prediction of birth weight using body measurements of local caprine population kids raised in a low-input breeding mode under arid environment. 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 local kids: Enhancing breeding strategies for arid environments. 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: A review. 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 goat for reproductive traits. Bangladesh Journal of Livestock Research, 29(1–2), 21–33. https://doi.org/10.3329/bjlr.v29i1.72058
Figueiredo Filho, L. A. S., Sarmento, J. 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 Anglo-Nubian goats using Bayesian inference via threshold and linear models. 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). Exploring how milk production, body weight and body condition dynamics affect reproductive success after artificial insemination 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). Reproductive performance response to the male effect in goats is improved when doe live weight/body condition score is increasing. 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 goat: 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 weight and body condition score of dairy goats using random forest algorithm and digital imaging data. Animals, 15(10), 1449. https://doi.org/10.3390/ani15101449
Gupta, V., Farooqui, M. M., & Verma, A. (2023). Body condition score: A tool for health assessment in goats. The Science World, 3(4), 556–560. https://doi.org/10.5281/zenodo.7875455
Hassan, E. K., & Saud, J. H. (2023). 3D hand pose and shape estimation from single RGB image 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). An improved single shot multibox detector method applied in body condition score for dairy cows. Animals, 9(7), 470. https://doi.org/10.3390/ani9070470
Iqbal, F., Waheed, A., & Faraz, A. (2022). Comparing the predictive ability of machine learning methods in predicting the live body weight of Beetal goats of Pakistan. 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). Automatic body condition scoring system for dairy cows in group state based on improved YOLOv5 and video analysis. Artificial Intelligence in Agriculture, 15(2), 350–362. https://doi.org/10.1016/j.aiia.2025.01.010
Li, K., & Teng, G. (2022). Study on body size measurement method of goat and cattle under different backgrounds based on deep learning. Electronics, 11(7), 993. https://doi.org/10.3390/electronics11070993
Liu, D., He, D., & Norton, T. (2020). Automatic estimation of dairy cattle body condition score from depth image using ensemble model. 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). Study on pig body condition scoring based on deep learning model EfficientNet-B0. Academic Journal of Computing and Information Science, 6(6), 156–162. https://doi.org/10.25236/AJCIS.2023.060625
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-based measurement techniques for livestock body dimension and weight: A review. Agriculture, 14(2), 306. https://doi.org/10.3390/agriculture14020306
Makamua, T. C., Madikadike, M. K., Mokoena, K., & Tyasi, T. L. (2023). Relationship between body measurement traits, udder measurement traits and milk yield of Saanen goats in Capricorn district of South Africa. 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 weight, body condition score, and type traits in dairy cows using three-dimensional cameras and manual body measurements. Livestock Science, 236, 104054. https://doi.org/10.1016/j.livsci.2020.104054
Misbah, F., Derese, M., & Haiyre, G. (2023). Prediction of Afar goat breed live body weight to facilitate breed improvement and husbandry practice. 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 a commercial automated body condition scoring system on a commercial dairy farm. Animals, 9(6), 287. https://doi.org/10.3390/ani9060287
Okere, C., Abrahamsen, F., & Gurung, N. (2022). Relationships between body weight, body condition score at breeding and reproductive and progeny performance in Kiko meat goats over two breeding cycles. International Journal of Agricultural Research, Innovation and Technology, 12(2), 64–73. https://doi.org/10.3329/ijarit.v12i2.64088
Rodríguez Álvarez, J., Arroqui, M., Mangudo, P., Toloza, J., Jatip, D., Rodríguez, J. M., Teyseyre, A., Sanz, C., Zunino, A., Machado, C., & Mateos, C. (2018). Body condition estimation on cows from depth images using convolutional neural networks. Computers and Electronics in Agriculture, 155, 12–22. https://doi.org/10.1016/j.compag.2018.09.039
Rodríguez Álvarez, J., Arroqui, M., Mangudo, P., Toloza, J., Jatip, D., Rodríguez, J. M., Teyseyre, A., Sanz, C., Zunino, A., Machado, C., & Mateos, C. (2019). Estimating body condition score in dairy cows from depth images using convolutional neural networks, transfer learning and model ensembling techniques. Agronomy, 9(2), 90. https://doi.org/10.3390/agronomy9020090
Sahoo, S., Ghosh, C. P., & Datta, S. (2022a). Assessment of body condition scoring (BCS) in relation to reproductive performances of Ganjam goats. The Pharma Innovation Journal, 11(11), 1690–1694.
Sahoo, S., Ghosh, C. P., & Datta, S. (2022b). An overview of condition scoring as a management tool in goats. Indian Journal of Animal Health, 61(1), 38–45. https://doi.org/10.36062/ijah.2022.00822
Sahoo, S. R., Ghosh, C. P., & Datta, S. (2023). Assessment of body condition score of Ganjam doe and its relationship with physical attributes. International Journal of Bio-resource and Stress Management, 14(4), 540–545. https://doi.org/10.23910/1.2023.3453
Shirke, V. G., Kandalkar, Y. B., & Tanpure, M. U. (2024). Assessment of body condition score as an indicator of nutritional status in Sangamneri goats. International Journal of Veterinary Sciences and Animal Husbandry, 9(3), 128–130.
Temenos, A., Voulodimos, A., Korelidou, V., Gelasakis, A., Kalogeras, D., Doulamis, A., & Doulamis, N. (2024). Goat-CNN: A lightweight convolutional neural network for pose-independent body condition score estimation in goats. Journal of Agriculture and Food Research, 16, 101174. https://doi.org/10.1016/j.jafr.2024.101174
Tesema, Z., Deribe, B., Tilahun, M., Kefale, A., Alebachew, G. W., Alemayehu, K., Getachew, T., Kebede, D., Taye, M., & Gizaw, S. (2025). Correction: Estimation of crossbreeding and genetic parameters for reproductive traits of Boer × Central Highland goats in Ethiopia. PLOS ONE, 20(1), e0318864. https://doi.org/10.1371/journal.pone.0318864
Vall, E., Blanchard, M., Sib, O., Cormary, B., & Gonzalez-Garcia, E. (2025). Standardized body condition scoring system for tropical farm animals (large ruminants, small ruminants, and equines). Tropical Animal Health and Production, 57(2), 106. https://doi.org/10.1007/s11250-025-04328-4
Veliz-Deras, F. G., Meza-Herrera, C. A., De Santiago-Miramontes, A., Santos-Alvarado, A., Bustamante-Andrade, J. A., Flores-Salas, J. M., Arellano-Rodríguez, F., & Mellado, M. (2023). An enhanced body condition improved sexual behavior, ovarian structure and function, and reproductive fitness in rangeland-crossbred dairy goats. Agriculture, 13(7), 1337. https://doi.org/10.3390/agriculture13071337
Venkata Reshma, C. H., Anitha, A., Jagadeeswara Rao, S., & Muralidhar, M. (2021). Relationship between body condition score and postpartum changes in local goats under field conditions. International Journal of Current Microbiology and Applied Sciences, 10(1), 2639–2645. https://doi.org/10.20546/ijcmas.2021.1001.307
Venkata Reshma, C. H., Anitha, A., Jagadeeswara Rao, S., & Muralidhar, M. (2022). Body condition score and its relation to body weight and measurements of local goats of Andhra Pradesh under field conditions. International Journal of Bio-resource and Stress Management, 13(2), 131–136. https://doi.org/10.23910/1.2022.2636
Vieira, A., Brandão, S., Monteiro, A., Ajuda, I., & Stilwell, G. (2015). Development and validation of a visual body condition scoring system for dairy goats with picture-based training. Journal of Dairy Science, 98(9), 6597–6608. https://doi.org/10.3168/jds.2015-9428
Widiyono, I., Sarmin, S., & Yanuartono, Y. (2020). Influence of body condition score on the metabolic and reproductive status of adult female Kacang goats. Journal of Applied Animal Research, 48(1), 201–206. https://doi.org/10.1080/09712119.2020.1764361
Xiong, Y., Condotta, I. C. F. S., Musgrave, J. A., Brown-Brandl, T. M., & Mulliniks, J. T. (2023). Estimating body weight and body condition score of mature beef cows using depth images. Translational Animal Science, 7, txad085. https://doi.org/10.1093/tas/txad085
Yukun, S., Pengju, H., Yujie, W., Ziqi, C., Yang, L., Baisheng, D., Runze, L., & Yonggen, Z. (2019). Automatic monitoring system for individual dairy cows based on a deep learning framework that provides identification via body parts and estimation of body condition score. Journal of Dairy Science, 102(11), 10140–10151. https://doi.org/10.3168/jds.2018-16164
Zhang, A. L., Wu, P., Jiang, C. X. H., Xuan, D. C. Z., Ma, E. Y. H., & Zhang, F. Y. A. (2018). Development and validation of visual image analysis for monitoring the body size of sheep. Journal of Applied Animal Research, 46(1), 1004–1015. https://doi.org/10.1080/09712119.2018.1450257
Zhao, K., Zhang, M., Shen, W., Liu, X., Ji, J., Dai, B., & Zhang, R. (2023). Automatic body condition scoring for dairy cows based on EfficientNet and convex hull features of point clouds. Computers and Electronics in Agriculture, 205, 107588. https://doi.org/10.1016/j.compag.2022.107588
