{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T06:04:04Z","timestamp":1789365844385,"version":"build-2803163510"},"reference-count":48,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T00:00:00Z","timestamp":1789344000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Accurate weight estimation in pig production is essential for optimizing management, feeding, and commercialization decisions; however, traditional weighing methods are invasive, time-consuming, and prone to operational errors. This study proposes a non-invasive computer vision\u2013based approach to estimate pig weight under real farm conditions in San Mart\u00edn, Peru.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A dataset of 3,800 lateral images paired with their corresponding ground-truth weights was collected. A computational pipeline was implemented, including geometric standardization, instance segmentation using YOLOv8n-seg, and feature extraction through EfficientNet-B0. The resulting embeddings were used as input for supervised regression models (SVR, XGBoost, and CatBoost), evaluated using repeated stratified cross-validation and an independent test set, with MAE, RMSE, and R\u00b2 as performance metrics. Statistical comparisons were conducted using the Friedman test followed by Wilcoxon post hoc analysis with Holm correction.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The results demonstrated strong predictive performance, with the SVR model achieving the best results (RMSE = 2.68 kg, MAE = 1.81 kg, R\n                      <jats:sup>2<\/jats:sup>\n                      = 0.85), showing statistically significant differences compared to the other models.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>These findings indicate that combining computer vision techniques with models capable of capturing non-linear relationships effectively models the relationship between animal morphology and body weight, providing a low-cost, non-invasive solution applicable to real-world production systems and supporting the advancement of precision livestock farming.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2026.1876396","type":"journal-article","created":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T05:39:46Z","timestamp":1789364386000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluation of hybrid models based on image segmentation and inference for pig weight estimation"],"prefix":"10.3389","volume":"9","author":[{"given":"Miguel Angel","family":"Valles-Coral","sequence":"first","affiliation":[{"name":"Grupo de Investigaci\u00f3n en Inteligencia Artificial, Facultad de Ingenier\u00eda de Sistemas e Inform\u00e1tica, Universidad Nacional de San Mart\u00edn","place":["Tarapoto, Peru"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kelvin Lleins","family":"Rojas-C\u00f3rdova","sequence":"additional","affiliation":[{"name":"Grupo de Investigaci\u00f3n en Inteligencia Artificial, Facultad de Ingenier\u00eda de Sistemas e Inform\u00e1tica, Universidad Nacional de San Mart\u00edn","place":["Tarapoto, Peru"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lloy","family":"Pinedo","sequence":"additional","affiliation":[{"name":"Grupo de Investigaci\u00f3n Transformaci\u00f3n Digital Empresarial, Facultad de Negocios, Universidad Privada Norbert Wiener","place":["Lima, Peru"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard","family":"Injante","sequence":"additional","affiliation":[{"name":"Grupo de Investigaci\u00f3n en Inteligencia Artificial, Facultad de Ingenier\u00eda de Sistemas e Inform\u00e1tica, Universidad Nacional de San Mart\u00edn","place":["Tarapoto, Peru"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pierre","family":"Vidaurre-Rojas","sequence":"additional","affiliation":[{"name":"Grupo de Investigaci\u00f3n Gesti\u00f3n ATEC, Facultad de Ciencias Econ\u00f3micas, Universidad Nacional de San Mart\u00edn","place":["Tarapoto, Peru"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jorge","family":"Saavedra-Ram\u00edrez","sequence":"additional","affiliation":[{"name":"Grupo de Investigaci\u00f3n Ganader\u00eda Amaz\u00f3nica Sustentable, Escuela Profesional de Ingenier\u00eda en Zootecnia, Facultad de Ingenier\u00eda y Ciencias, Universidad Nacional Aut\u00f3noma de Alto Amazonas","place":["Yurimaguas, Peru"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fernando","family":"Ruiz-Saavedra","sequence":"additional","affiliation":[{"name":"Grupo de investigaci\u00f3n, Innovaci\u00f3n Tecnol\u00f3gica en Ingenier\u00eda Civil y Arquitectura-INTEICA, Escuela de Ingenier\u00eda Civil, Facultad de Ingenier\u00eda Civil y Arquitectura, Universidad Nacional de San Martin","place":["Tarapoto, Peru"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Williams","family":"Ramirez","sequence":"additional","affiliation":[{"name":"Grupo de Investigaci\u00f3n en Manejo Forestal Sostenible, Escuela Profesional de Agronom\u00eda, Facultad de Ciencias Agrarias, Universidad Nacional de San Mart\u00edn","place":["Tarapoto, Peru"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,14]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"302","DOI":"10.3390\/ani11020302","article-title":"Management and feeding strategies in early life to increase piglet performance and welfare around weaning: a review","volume":"11","author":"Blavi","year":"2021","journal-title":"Animals"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"2247","DOI":"10.3390\/ani13142247","article-title":"Handling and training of wild animals: evidence and ethics-based approaches and best practices in the modern zoo","volume":"13","author":"Brando","year":"2023","journal-title":"Animals"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1093\/af\/vfac084","article-title":"Social aspects of livestock farming around the globe","volume":"13","author":"Busch","year":"2023","journal-title":"Anim. Front."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"e53","DOI":"10.56926\/repia.v3i1.53","article-title":"Determination of the physicochemical and hygienic-sanitary quality of raw milk considering different milking systems and types of feeding","volume":"3","author":"Ca\u00f1ar-Ramos","year":"2024","journal-title":"Rev. Peru. Investig. Agropecu."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"100419","DOI":"10.1016\/j.atech.2024.100419","article-title":"Use of machine learning approaches for body weight prediction in Peruvian Corriedale sheep","volume":"7","author":"Canaza-Cayo","year":"2024","journal-title":"Smart Agric. Technol."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"e565","DOI":"10.51252\/revza.v5i1.565","article-title":"Effective evaluation and productive behavior of hormonally castrated versus surgically castrated weaned piglets in the San Mart\u00edn regions","volume":"5","author":"Carranza-Serna","year":"2025","journal-title":"Revista de Veterinaria y Zootecnia Amaz\u00f3nica"},{"key":"ref7","first-page":"785","article-title":"XGBoost: A Scalable Tree Boosting System Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Chen","year":"2016"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"253","DOI":"10.3390\/agriculture13020253","article-title":"Live pig-weight learning and prediction method based on a multilayer RBF network","volume":"13","author":"Chen","year":"2023","journal-title":"Agriculture"},{"key":"ref9","first-page":"358","article-title":"Automated Cattle Classification and Counting Using Hybridized Mask R-CNN and YOLOv3 Algorithms","author":"Devi Priya","year":"2022"},{"key":"ref10","first-page":"155","article-title":"Support vector regression machines NIPS\u201996: proceedings of the 10th international conference on neural information processing systems","author":"Drucker","year":"1996"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1080\/01621459.1937.10503522","article-title":"The use of ranks to avoid the assumption of normality implicit in the analysis of variance","volume":"32","author":"Friedman","year":"1937","journal-title":"J. Am. Stat. Assoc."},{"key":"ref12","first-page":"18932","article-title":"Revisiting deep learning models for tabular data","author":"Gorishniy","year":"2021"},{"key":"ref13","first-page":"507","article-title":"Why do tree-based models still outperform deep learning on typical tabular data?","author":"Grinsztajn","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"6944","DOI":"10.3390\/app13126944","article-title":"Determination of the live weight of farm animals with deep learning and semantic segmentation techniques","volume":"13","author":"Guvenoglu","year":"2023","journal-title":"Appl. Sci."},{"key":"ref15","first-page":"65","article-title":"A simple sequentially rejective multiple test procedure","volume":"6","author":"Holm","year":"1979","journal-title":"Scand. J. Stat."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"1614","DOI":"10.3390\/ani14111614","article-title":"Improving efficiency: automatic intelligent weighing system as a replacement for manual pig weighing","volume":"14","author":"Hou","year":"2024","journal-title":"Animals"},{"key":"ref17","article-title":"Statistical compendium, San Mart\u00edn 2023","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"2122","DOI":"10.3390\/ani14142122","article-title":"Pig weight estimation method based on a framework combining mask R-CNN and ensemble regression model","volume":"14","author":"Jiang","year":"2024","journal-title":"Animals"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"e2539","DOI":"10.1002\/vetr.2539","article-title":"Sow mortality in a pig production system in the midwestern USA: reasons for removal and factors associated with increased mortality","volume":"192","author":"Kikuti","year":"2023","journal-title":"Vet. Rec."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"863","DOI":"10.3389\/fpsyg.2013.00863","article-title":"Calculating and reporting effect sizes to facilitate cumulative science: a practical primer for t-tests and ANOVAs","volume":"4","author":"Lakens","year":"2013","journal-title":"Front. Psychol."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1492","DOI":"10.3390\/s21041492","article-title":"Practices and applications of convolutional neural network-based computer vision systems in animal farming: a review","volume":"21","author":"Li","year":"2021","journal-title":"Sensors"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"7730","DOI":"10.3390\/s23187730","article-title":"Body weight estimation for pigs based on 3D hybrid filter and convolutional neural network","volume":"23","author":"Liu","year":"2023","journal-title":"Sensors"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"306","DOI":"10.3390\/agriculture14020306","article-title":"Computer vision-based measurement techniques for livestock body dimension and weight: a review","volume":"14","author":"Ma","year":"2024","journal-title":"Agriculture"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"76336","DOI":"10.52202\/075280-3337","article-title":"When Do Neural Nets Outperform Boosted Trees on Tabular Data?","volume":"36","author":"McElfresh","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","article-title":"Monthly statistical bulletin \u201cAgriculture in Figures\u201d - 2023","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"3523","DOI":"10.1109\/TPAMI.2021.3059968","article-title":"Image segmentation using deep learning: a survey","author":"Minaee","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"e117","DOI":"10.56926\/repia.v4i1.117","article-title":"Characterization and classification of high mountain cattle farming systems in Valle del Cauca: foundations for sustainable production","volume":"4","author":"Molina-Benavides","year":"2025","journal-title":"Rev. Peru. Investig. Agropecu."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"1557600","DOI":"10.3389\/fdata.2025.1557600","article-title":"Machine vision model using nail images for non-invasive detection of iron deficiency anemia in university students","volume":"8","author":"Navarro-Cabrera","year":"2025","journal-title":"Front. Big Data"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1016\/j.biosystemseng.2023.01.005","article-title":"Towards rapid weight assessment of finishing pigs using a handheld, mobile RGB-D camera","volume":"226","author":"Nguyen","year":"2023","journal-title":"Biosyst. Eng."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"700","DOI":"10.3390\/ani14050700","article-title":"Animal welfare assessment and meat quality through assessment of stress biomarkers in fattening pigs with and without visible damage during slaughter","volume":"14","author":"Ogawa","year":"2024","journal-title":"Animals"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"e614","DOI":"10.51252\/rcsi.v4i1.614","article-title":"Application of the convolutional network mask R-CNN for the estimation of the body weight of the guinea pig","volume":"4","author":"Orme\u00f1o-Ayala","year":"2024","journal-title":"Revista Cient\u00edfica de Sistemas e Inform\u00e1tica"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1016\/j.aiia.2023.08.007","article-title":"Low-cost livestock sorting information management system based on deep learning","volume":"9","author":"Pan","year":"2023","journal-title":"Artif. Intell. Agric."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"31","DOI":"10.3390\/ani14010031","article-title":"Deep learning models to predict finishing pig weight using point clouds","volume":"14","author":"Paudel","year":"2023","journal-title":"Animals"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"6178","DOI":"10.3168\/jds.2023-24065","article-title":"A dynamic individual method for yak heifer live body weight estimation using the YOLOv8 network and body parameter detection algorithm","volume":"107","author":"Peng","year":"2024","journal-title":"J. Dairy Sci."},{"key":"ref35","doi-asserted-by":"publisher","first-page":"1283","DOI":"10.1017\/S175173111900346X","article-title":"Herd-level factors associated with piglet weight at weaning, kilograms of piglets weaned per sow per year and sow feed conversion","volume":"14","author":"Pierozan","year":"2020","journal-title":"Animal"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"6639","DOI":"10.5555\/3327757.3327770","article-title":"CatBoost: unbiased boosting with categorical features","volume":"31","author":"Prokhorenkova","year":"2018","journal-title":"NIPS\u201918"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"995724","DOI":"10.3389\/fvets.2022.995724","article-title":"Identification of body size characteristic points based on the mask R-CNN and correlation with body weight in Ujumqin sheep","volume":"9","author":"Qin","year":"2022","journal-title":"Front. Vet. Sci."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"skac142","DOI":"10.1093\/jas\/skac142","article-title":"Impact of housing environment and management on pre\u2212\/post-weaning piglet productivity","volume":"100","author":"Ramirez","year":"2022","journal-title":"J. Anim. Sci."},{"key":"ref39","article-title":"Peru: pork production grows in the first quarter of 2024","year":"2024"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1016\/B978-0-323-85676-8.00015-8","volume-title":"Advances in Pig Welfare","author":"Siegford","year":"2024"},{"key":"ref41","first-page":"6105","article-title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","volume-title":"Proceedings of the 36th International Conference on Machine Learning, PMLR.","author":"Tan","year":"2019"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1007\/s10462-025-11198-7","article-title":"A comprehensive survey of loss functions and metrics in deep learning","volume":"58","author":"Terven","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"ref43","doi-asserted-by":"publisher","first-page":"53","DOI":"10.3991\/ijoe.v20i14.50141","article-title":"Non-invasive detection of iron deficiency anemia in young adults through finger-tip video image analysis","volume":"20","author":"Valles-Coral","year":"2024","journal-title":"IJOE"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"105491","DOI":"10.1016\/j.infrared.2024.105491","article-title":"Instance segmentation of pigs in infrared images based on INPC model","volume":"141","author":"Wang","year":"2024","journal-title":"Infrared Phys. Technol."},{"key":"ref45","doi-asserted-by":"publisher","first-page":"80","DOI":"10.2307\/3001968","article-title":"Individual comparisons by ranking methods","volume":"1","author":"Wilcoxon","year":"1945","journal-title":"Biom. Bull."},{"key":"ref46","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/j.aiia.2024.03.001","article-title":"A novel approach based on a modified mask R-CNN for the weight prediction of live pigs","volume":"12","author":"Xie","year":"2024","journal-title":"Artif. Intell. Agric."},{"key":"ref47","doi-asserted-by":"publisher","first-page":"1299169","DOI":"10.3389\/frai.2024.1299169","article-title":"Intelligent weight prediction of cows based on semantic segmentation and back propagation neural network","volume":"7","author":"Xu","year":"2024","journal-title":"Front. Artif. Intellig."},{"key":"ref48","doi-asserted-by":"publisher","first-page":"1199","DOI":"10.3390\/electronics12051199","article-title":"Techniques and challenges of image segmentation: a review","volume":"12","author":"Yu","year":"2023","journal-title":"Electronics"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1876396\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T05:39:47Z","timestamp":1789364387000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1876396\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,14]]},"references-count":48,"alternative-id":["10.3389\/frai.2026.1876396"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1876396","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,14]]},"article-number":"1876396"}}