{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:55:45Z","timestamp":1791914145798,"version":"4.3.4"},"reference-count":27,"publisher":"Oxford University Press (OUP)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,1,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The accurate identification of individual sheep is a crucial prerequisite for establishing digital sheep farms and precision livestock farming. Currently, deep learning technology provides an efficient and non-contact method for sheep identity recognition. In particular, convolutional neural networks can be used to learn features of sheep faces to determine their corresponding identities. However, the existing sheep face recognition models face problems such as large model size, and high computational costs, making it difficult to meet the requirements of practical applications. In response to these issues, we introduce a lightweight sheep face recognition model called YOLOv7-Sheep Face Recognition (YOLOv7-SFR). Considering the labor-intensive nature associated with manually capturing sheep face images, we developed a face image recording channel to streamline the process and improve efficiency. This study collected facial images of 50 Small-tailed Han sheep through a recording channel. The experimental sheep ranged in age from 1 to 3 yr, with an average weight of 63.1\u00a0kg. Employing data augmentation methods further enhanced the original images, resulting in a total of 22,000 sheep face images. Ultimately, a sheep face dataset was established. To achieve lightweight improvement and improve the performance of the recognition model, a variety of improvement strategies were adopted. Specifically, we introduced the shuffle attention module into the backbone and fused the Dyhead module with the\u00a0model's\u00a0detection head. By combining multiple attention mechanisms, we improved the\u00a0model's\u00a0ability to learn target features. Additionally, the traditional convolutions in the backbone and neck were replaced with depthwise separable convolutions. Finally, leveraging knowledge distillation, we enhanced its performance further by employing You Only Look Once version 7 (YOLOv7) as the teacher model and YOLOv7-SFR as the student model. The training results indicate that our proposed approach achieved the best performance on the sheep face dataset, with a mean average precision@0.5 of 96.9%. The model size and average recognition time were 11.3 MB and 3.6\u00a0ms, respectively. Compared to YOLOv7-tiny, YOLOv7-SFR showed a 2.1% improvement in mean average precision@0.5, along with a 5.8% reduction in model size and a 42.9% reduction in average recognition time. The research results are expected to drive the practical applications of sheep face recognition technology.<\/jats:p>","DOI":"10.1093\/jas\/skae066","type":"journal-article","created":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T02:58:40Z","timestamp":1710212320000},"source":"Crossref","is-referenced-by-count":15,"title":["Lightweight model-based sheep face recognition via face image recording channel"],"prefix":"10.1093","volume":"102","author":[{"given":"Xiwen","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Mechanical and Electrical Engineering, Inner Mongolia Agricultural University , Inner Mongolia, Hohhot 010018 , China"},{"name":"Inner Mongolia Engineering Research Center for Intelligent Facilities in Prataculture and Livestock Breeding , Inner Mongolia, Hohhot 010018 , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuanzhong","family":"Xuan","sequence":"additional","affiliation":[{"name":"College of Mechanical and Electrical Engineering, Inner Mongolia Agricultural University , Inner Mongolia, Hohhot 010018 , China"},{"name":"Inner Mongolia Engineering Research Center for Intelligent Facilities in Prataculture and Livestock Breeding , Inner Mongolia, Hohhot 010018 , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanhua","family":"Ma","sequence":"additional","affiliation":[{"name":"College of Mechanical and Electrical Engineering, Inner Mongolia Agricultural University , Inner Mongolia, Hohhot 010018 , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiyang","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Mechanical and Electrical Engineering, Inner Mongolia Agricultural University , Inner Mongolia, Hohhot 010018 , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Xue","sequence":"additional","affiliation":[{"name":"College of Mechanical and Electrical Engineering, Inner Mongolia Agricultural University , Inner Mongolia, Hohhot 010018 , China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,3,13]]},"reference":[{"key":"2024082905004213700_CIT0001","doi-asserted-by":"crossref","first-page":"106133","DOI":"10.1016\/j.compag.2021.106133","article-title":"Visual identification of individual Holstein-Friesian cattle via deep metric learning","volume":"185","author":"Andrew","year":"2021","journal-title":"Comput. Electron. Agric"},{"key":"2024082905004213700_CIT0003","doi-asserted-by":"crossref","first-page":"3758","DOI":"10.3390\/s21113758","article-title":"Machine learning in agriculture: a comprehensive updated review","volume":"21","author":"Benos","year":"2021","journal-title":"Sensors (Basel)"},{"key":"2024082905004213700_CIT0004","doi-asserted-by":"crossref","first-page":"116354","DOI":"10.1016\/j.eswa.2021.116354","article-title":"CORF3D contour maps with application to Holstein cattle recognition from RGB and thermal images","volume":"192","author":"Bhole","year":"2022","journal-title":"Expert Syst. Appl"},{"key":"2024082905004213700_CIT0005","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":"2024082905004213700_CIT0006","doi-asserted-by":"crossref","first-page":"9453","DOI":"10.1002\/ece3.5410","article-title":"Wildlife surveillance using deep learning methods","volume":"9","author":"Chen","year":"2019","journal-title":"Ecol. Evol"},{"key":"2024082905004213700_CIT0007","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1093\/jas\/skac147","article-title":"VTag: a semi-supervised pipeline for tracking pig activity with a single top-view camera","volume":"100","author":"Chen","year":"2022","journal-title":"J. Anim. Sci"},{"key":"2024082905004213700_CIT0008","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR46437.2021.00729","article-title":"Dynamic head: unifying object detection heads with attentions","author":"Dai","year":"2021"},{"key":"2024082905004213700_CIT0009","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1016\/j.compag.2007.07.010","article-title":"Assessment of retinal recognition technology as a biometric method for sheep identification","volume":"60","author":"Gonzales Barron","year":"2008","journal-title":"Comput. Electron. Agric"},{"key":"2024082905004213700_CIT0010","doi-asserted-by":"crossref","first-page":"108027","DOI":"10.1016\/j.compag.2023.108027","article-title":"Sheep face image dataset and DT-YOLOv5s for sheep breed recognition","volume":"211","author":"Guo","year":"2023","journal-title":"Comput. Electron. Agric"},{"key":"2024082905004213700_CIT0011","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.compind.2018.02.016","article-title":"Towards on-farm pig face recognition using convolutional neural networks","volume":"98","author":"Hansen","year":"2018","journal-title":"Comput. Ind"},{"key":"2024082905004213700_CIT0012","doi-asserted-by":"crossref","first-page":"2458","DOI":"10.3390\/ani13152458","article-title":"Sheep face detection based on an improved retinaface algorithm","volume":"13","author":"Hao","year":"2023","journal-title":"Animals (Basel)"},{"key":"2024082905004213700_CIT0013","doi-asserted-by":"crossref","first-page":"106713","DOI":"10.1016\/j.compag.2022.106713","article-title":"Biometric identification of sheep via a machine-vision system","volume":"194","author":"Hitelman","year":"2022","journal-title":"Comput. Electron. Agric"},{"key":"2024082905004213700_CIT0015","doi-asserted-by":"crossref","first-page":"119431","DOI":"10.1016\/j.eswa.2022.119431","article-title":"Automatic identification of individual yaks in in-the-wild images using part-based convolutional networks with self-supervised learning","volume":"216","author":"Li","year":"2023","journal-title":"Expert Syst. Appl"},{"key":"2024082905004213700_CIT0016","doi-asserted-by":"crossref","first-page":"120365","DOI":"10.1016\/j.eswa.2023.120365","article-title":"Algorithm for cattle identification based on locating key area","volume":"228","author":"Lu","year":"2023","journal-title":"Expert Syst. Appl"},{"key":"2024082905004213700_CIT0019","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1016\/j.eswa.2017.05.063","article-title":"Assessing machine learning classifiers for the detection of animals\u2019 behavior using depth-based tracking","volume":"86","author":"Pons","year":"2017","journal-title":"Expert Syst. Appl"},{"key":"2024082905004213700_CIT0020","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.11834\/jig.200619","article-title":"Joint loss optimization based high similarity identification for milch goats","volume":"27","author":"Shang","year":"2022","journal-title":"J. Image Graph"},{"key":"2024082905004213700_CIT0021","doi-asserted-by":"crossref","first-page":"1465","DOI":"10.3390\/ani12111465","article-title":"Using pruning-based YOLOv3 deep learning algorithm for accurate detection of sheep face","volume":"12","author":"Song","year":"2022","journal-title":"Animals (Basel)"},{"key":"2024082905004213700_CIT0022","doi-asserted-by":"crossref","first-page":"380","DOI":"10.1016\/j.compag.2009.07.009","article-title":"A complete farm management system based on animal identification using RFID technology","volume":"70","author":"Voulodimos","year":"2010","journal-title":"Comput. Electron. Agric"},{"key":"2024082905004213700_CIT0023","doi-asserted-by":"crossref","first-page":"1957","DOI":"10.3390\/ani13121957","article-title":"Sheep face recognition model based on deep learning and bilinear feature fusion","volume":"13","author":"Wan","year":"2023","journal-title":"Animals (Basel)"},{"key":"2024082905004213700_CIT0024","article-title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","author":"Wang","year":"2022"},{"key":"2024082905004213700_CIT0025","doi-asserted-by":"crossref","first-page":"133714","DOI":"10.1016\/j.jclepro.2022.133714","article-title":"Sequential air pollution emission estimation using a hybrid deep learning model and health-related ventilation control in a pig building","volume":"371","author":"Xie","year":"2022","journal-title":"J. Clean Prod"},{"key":"2024082905004213700_CIT0026","doi-asserted-by":"crossref","first-page":"108200","DOI":"10.1016\/j.compag.2023.108200","article-title":"A deep learning-based detection method for pig body temperature using infrared thermography","volume":"213","author":"Xie","year":"2023","journal-title":"Comput. Electron. Agric"},{"key":"2024082905004213700_CIT0029","doi-asserted-by":"crossref","first-page":"105754","DOI":"10.1016\/j.compag.2020.105754","article-title":"Automatic recognition of dairy cow mastitis from thermal images by a deep learning detector","volume":"178","author":"Zhang","year":"2020","journal-title":"Comput. Electron. Agric"},{"key":"2024082905004213700_CIT0030","doi-asserted-by":"crossref","first-page":"107452","DOI":"10.1016\/j.compag.2022.107452","article-title":"Biometric facial identification using attention module optimized YOLOv4 for sheep","volume":"203","author":"Zhang","year":"2022","journal-title":"Comput. Electron. Agric"},{"key":"2024082905004213700_CIT0031","doi-asserted-by":"crossref","first-page":"24971","DOI":"10.1007\/s00521-023-08413-3","article-title":"Research on sheep face recognition algorithm based on improved AlexNet model","volume":"35","author":"Zhang","year":"2023","journal-title":"Neural Comput. Appl"},{"key":"2024082905004213700_CIT0032","doi-asserted-by":"crossref","first-page":"1824","DOI":"10.3390\/ani13111824","article-title":"LSR-YOLO: a high-precision, lightweight model for sheep face recognition on the mobile end","volume":"13","author":"Zhang","year":"2023","journal-title":"Animals (Basel)"},{"key":"2024082905004213700_CIT0033","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"}],"container-title":["Journal of Animal Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jas\/advance-article-pdf\/doi\/10.1093\/jas\/skae066\/56962235\/skae066.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jas\/article-pdf\/doi\/10.1093\/jas\/skae066\/58955462\/skae066.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jas\/article-pdf\/doi\/10.1093\/jas\/skae066\/58955462\/skae066.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,13]],"date-time":"2024-11-13T23:17:38Z","timestamp":1731539858000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jas\/article\/doi\/10.1093\/jas\/skae066\/7628030"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1093\/jas\/skae066","relation":{},"ISSN":["0021-8812","1525-3163"],"issn-type":[{"value":"0021-8812","type":"print"},{"value":"1525-3163","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024]]},"published":{"date-parts":[[2024]]},"article-number":"skae066"}}