{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T11:23:31Z","timestamp":1787829811918,"version":"build-2784847793"},"reference-count":25,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T00:00:00Z","timestamp":1787788800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Henan Province key research and development project","award":["251111110800"],"award-info":[{"award-number":["251111110800"]}]},{"name":"Leading Talents in Science and Technology Innovation of Luoyang City"},{"name":"Young Backbone Teachers Program of Henan University of Science and Technology","award":["13450009"],"award-info":[{"award-number":["13450009"]}]},{"award":["13450009"],"award-info":[{"award-number":["13450009"]}],"id":[{"id":"https:\/\/ror.org\/05d80kz58","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Animals"],"abstract":"<jats:p>Face detection serves as the prerequisite and foundation for individual sheep and goat identification. Considering the practical detection process, the facial region of sheep and goats shares similarities with the torso texture features, which could be easily interfered with by the background and other factors, along with the presence of varying face scales. RetinaFace was selected as the framework, with GhostNet used as the backbone for feature extraction, thereby significantly reducing model complexity and computational load. A new feature extraction unit\u2014SRM module\u2014was designed through the integration of the Multi-Source Domain Adaptation (MSDA) attention mechanism and Reparameterized Non-local Cross-scale Feature Exchange Layer 4 (RepNCSPELAN4) to mitigate the impact of environmental factors and enhance the fine-grained feature extraction of the sheep and goat\u2019s face. A new feature fusion network\u2014A_EFPN\u2014was designed through the com-bination of Efficient Reparameterized Generalized-FPN (RepGFPN) and Alterable Kernel Convolution (AKConv), thereby enhancing feature interaction and improving the model\u2019s multi-scale detection ability. An optimized multi-task joint loss function was employed to retain three facial key points: the left eye, right eye, and nose, thereby reducing the number of model regression parameters. Experimental results demonstrate that the proposed method achieved 96.15% Precision, 97.06% Recall, 96.60% F1 Score, 98.31% AP, 2.40% NME, 2.36 G FLOPs, 3.63 M Params, and a weight of 14.75 MB. It was demonstrated to be applicable to the rapid and accurate detection of sheep and goat faces in the actual breeding environment, providing the foundation for subsequent sheep and goat face recognition.<\/jats:p>","DOI":"10.3390\/ani16172685","type":"journal-article","created":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T10:58:21Z","timestamp":1787828301000},"page":"2685","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Scale Sheep and Goat Face Detection Network Based on Multi-Task Optimization"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5732-7598","authenticated-orcid":false,"given":"Fu","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Agricultural Equipment Engineering, Henan University of Science and Technology, Luoyang 471023, China"},{"name":"State Key Laboratory of Light Superalloys, Henan University of Science and Technology, Luoyang 471023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baoping","family":"Yan","sequence":"additional","affiliation":[{"name":"College of Agricultural Equipment Engineering, Henan University of Science and Technology, Luoyang 471023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaopeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Agricultural Equipment Engineering, Henan University of Science and Technology, Luoyang 471023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanling","family":"Fu","sequence":"additional","affiliation":[{"name":"College of Physical Engineering, Henan University of Science and Technology, Luoyang 471003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1851-761X","authenticated-orcid":false,"given":"Yakun","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Agricultural Equipment Engineering, Henan University of Science and Technology, Luoyang 471023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianhua","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Biological and Agricultural Engineering, Jilin University, Changchun 130025, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,27]]},"reference":[{"key":"ref_1","first-page":"161","article-title":"Development modes of animal husbandry and their future trends","volume":"25","author":"Zhang","year":"2023","journal-title":"Sci. Technol. Wind"},{"key":"ref_2","first-page":"2456009","article-title":"Automatic Face Detection of Farm Images Based on an Enhanced Lightweight Deep Learning Model","volume":"40","author":"Huang","year":"2026","journal-title":"Int. J. Pattern Recognit. Artif. Intell."},{"key":"ref_3","first-page":"1855","article-title":"From artificial to intelligent: Research progress in individual identification technology for cattle","volume":"50","author":"Peng","year":"2023","journal-title":"China Anim. Husb. Vet. Med."},{"key":"ref_4","first-page":"7","article-title":"Research progress of computer vision technology in intelligent sheep farms","volume":"7","author":"Yao","year":"2021","journal-title":"China Feed"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"794","DOI":"10.1111\/age.13259","article-title":"Recognition and segmentation of individual pigs based on Swin Transformer","volume":"53","author":"Lu","year":"2022","journal-title":"Anim. Genet."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Li, X., Du, J., Yang, J., and Li, S. (2022). When mobilenetv2 meets transformer: A balanced sheep face recognition model. Agriculture, 12.","DOI":"10.3390\/agriculture12081126"},{"key":"ref_7","first-page":"1","article-title":"Pig face recognition based on trapezoid normalized pixel difference feature and trimmed mean attention mechanism","volume":"72","author":"Xu","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Wang, R., Gao, R., Li, Q., and Dong, J. (2023). Pig face recognition based on metric learning by combining a residual network and attention mechanism. Agriculture, 13.","DOI":"10.3390\/agriculture13010144"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"106675","DOI":"10.1016\/j.compag.2021.106675","article-title":"CattleFaceNet: A cattle face identification approach based on RetinaFace and ArcFace loss","volume":"193","author":"Xu","year":"2022","journal-title":"Comput. Electron. Agric."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Kawagoe, Y., Kobayashi, I., and Zin, T.T. (2023). Facial region analysis for individual identification of cows and feeding time estimation. Agriculture, 13.","DOI":"10.3390\/agriculture13051016"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"101079","DOI":"10.1016\/j.animal.2024.101079","article-title":"Biometric identification of dairy cows via real-time facial recognition","volume":"18","author":"Bergman","year":"2024","journal-title":"Animal"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"3375394","DOI":"10.1155\/2021\/3375394","article-title":"Open set sheep face recognition based on Euclidean space metric","volume":"2021","author":"Xue","year":"2021","journal-title":"Math. Probl. Eng."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"106730","DOI":"10.1016\/j.compag.2022.106730","article-title":"Real-time goat face recognition using convolutional neural network","volume":"194","author":"Billah","year":"2022","journal-title":"Comput. Electron. Agric."},{"key":"ref_14","first-page":"267","article-title":"Sheep face recognition method based on improved MobileFaceNet","volume":"53","author":"Zhang","year":"2022","journal-title":"J. Agric. Mach."},{"key":"ref_15","first-page":"331","article-title":"Recognition method for dairy goat faces based on improved YOLOv5s","volume":"54","author":"Ning","year":"2023","journal-title":"J. Agric. Mach."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"100886","DOI":"10.1016\/j.animal.2023.100886","article-title":"A high-precision facial recognition method for small-tailed Han sheep based on an optimised Vision Transformer","volume":"17","author":"Zhang","year":"2023","journal-title":"Animal"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Yu, F., Ting, L., and Yang, Y. (2026). Color-adaptive sheep face recognition method based on retinex-guided gradient perception convolution. Agriculture, 16.","DOI":"10.3390\/agriculture16121335"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Zhang, F., Zhao, X., Wang, S., Qiu, Y., Fu, S., and Zhang, Y. (2025). Research on herd sheep facial recognition based on multi-dimensional feature information fusion technology in complex environment. Front. Vet. Sci., 12.","DOI":"10.3389\/fvets.2025.1404564"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"28","DOI":"10.54254\/2755-2721\/22\/20231163","article-title":"Research progress on 3D face recognition","volume":"59","author":"Liu","year":"2023","journal-title":"J. Comput. Eng. Appl."},{"key":"ref_20","first-page":"2250","article-title":"A review of progress in occluded face recognition","volume":"40","author":"Zhang","year":"2023","journal-title":"Comput. Appl. Res."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Zhong, J., Chen, T., and Yi, L. (2023). Face expression recognition based on NGO-BILSTM model. Front. Neurorobot., 17.","DOI":"10.3389\/fnbot.2023.1155038"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2356004","DOI":"10.1142\/S0218001423560049","article-title":"Algorithm Analysis of Face Recognition Robot Based on Deep Learning","volume":"37","author":"Mu","year":"2023","journal-title":"Int. J. Pattern Recognit. Artif. Intell."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Ververas, E., Kotsia, I., and Zafeiriou, S. (2020). Retinaface: Single-shot multi-level face localisation in the wild. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"8906","DOI":"10.1109\/TMM.2023.3243616","article-title":"Dilateformer: Multi-scale dilated transformer for visual recognition","volume":"25","author":"Jiao","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"ref_25","unstructured":"Zhang, X., Song, Y., Song, T., Yang, D., Ye, Y., Zhou, J., and Zhang, L. (2023). AKConv: Convolutional kernel with arbitrary sampled shapes and arbitrary number of parameters. arXiv."}],"container-title":["Animals"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2076-2615\/16\/17\/2685\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T11:11:49Z","timestamp":1787829109000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2076-2615\/16\/17\/2685"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,27]]},"references-count":25,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["ani16172685"],"URL":"https:\/\/doi.org\/10.3390\/ani16172685","relation":{},"ISSN":["2076-2615"],"issn-type":[{"value":"2076-2615","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,27]]}}}