HISNET-FF:Hierarchical identification of species using a network with fused cranial and dental featuresOA
Accurate taxonomic identification based on mammalian craniodental features remains critical for evolutionary,ecological,and paleontological research,yet conventional approaches are time-intensive and demand expert input.To overcome these limitations,a deep learning framework,HISNET-FF,was developed with a dual-stream architecture that integrates global cranial morphology with local diagnostic signals from teeth and auditory bullae.The model operates within a hierarchical classification pipeline,processing from genus-level discrimination to species-level resolution.Evaluation on an extensive image dataset encompassing 51 species across 18 genera of Talpidae achieved exceptional accuracy at both the genus(99.6%±0.4%)and species(96.5%±1.3%)levels.This species-level performance substantially exceeded that of single-stream models employing either flat(91.2%±2.3%)or hierarchical(93.9%±2.1%)strategies.To support endto-end automation,a YOLO-based annotation module was implemented to localize key morphological traits with 97.8%recall,97.9%precision,and 81.5%mean average precision(mAP@[.50:.95]).Incorporating this module incurred only a marginal reduction of 1.9%in identification accuracy.Thus,HISNET-FF offers a robust and accurate framework that accelerates morphology-based species identification and enables automated taxonomic classification,with strong potential for broader implementation across diverse biological research domains.
Zhong Cao;Qiu-Le Tang;Wei-Qi Zeng;Kun-Hui Wang;Quentin Martinez;Ze-Ling Zeng;Si-Ning Xie;Qiu-Qin Lu;Shi-Yun Liu;Xiao-Yun Zheng;Wen-Hua Yu;Jun-Jie Hu;Zhong-Zheng Chen;Shao-Ying Liu;Song Li;Fei-Yun Tu;Zi-Wen Hong;Ming Bai;Kai He
School of Electronics and Communication Engineering,Guangzhou University,Guangzhou,Guangdong 510006,ChinaSchool of Computer Science and Cyber Engineering,Guangzhou University,Guangzhou,Guangdong 510006,ChinaSchool of Electronics and Communication Engineering,Guangzhou University,Guangzhou,Guangdong 510006,ChinaSchool of Electronics and Communication Engineering,Guangzhou University,Guangzhou,Guangdong 510006,China School of Advanced Interdisciplinary Sciences,University of Chinese Academy of Sciences,Beijing 101400,ChinaStaatliches Museum für Naturkunde Stuttgart,Stuttgart 70191,GermanySouth China Biodiversity Research Center,School of Life Sciences,Guangzhou University,Guangzhou,Guangdong 510006,ChinaSouth China Biodiversity Research Center,School of Life Sciences,Guangzhou University,Guangzhou,Guangdong 510006,ChinaSouth China Biodiversity Research Center,School of Life Sciences,Guangzhou University,Guangzhou,Guangdong 510006,ChinaSouth China Biodiversity Research Center,School of Life Sciences,Guangzhou University,Guangzhou,Guangdong 510006,ChinaSouth China Biodiversity Research Center,School of Life Sciences,Guangzhou University,Guangzhou,Guangdong 510006,ChinaSouth China Biodiversity Research Center,School of Life Sciences,Guangzhou University,Guangzhou,Guangdong 510006,ChinaSouth China Biodiversity Research Center,School of Life Sciences,Guangzhou University,Guangzhou,Guangdong 510006,ChinaCollaborative Innovation Center of Recovery and Reconstruction of Degraded Ecosystem in Wanjiang Basin Co-founded by Anhui Province and Ministry of Education,School of Ecology and Environment,Anhui Normal University,Wuhu,Anhui 241002,ChinaSichuan Academy of Forestry,Chengdu,Sichuan 610081,ChinaState Key Laboratory of Genetic Evolution&Animal Models,Kunming Institute of Zoology,Chinese Academy of Sciences,Kunming,Yunnan 650023,ChinaMinistry of Education Key Laboratory for Ecology of Tropical Islands,Key Laboratory of Tropical Animal and Plant Ecology of Hainan Province,College of Life Sciences,Hainan Normal University,Haikou,Hainan 571158,ChinaSchool of Electronics and Communication Engineering,Guangzhou University,Guangzhou,Guangdong 510006,ChinaState Key Laboratory of Animal Biodiversity Conservation and Integrated Pest Management,Institute of Zoology,Chinese Academy of Sciences,Beijing 100101,China Academy of Plateau Science and Sustainability,Qinghai Normal University,Xining,Qinghai 810016,China Hebei Key Laboratory of Animal Diversity,Langfang Normal University,Langfang,Hebei 065000,ChinaSouth China Biodiversity Research Center,School of Life Sciences,Guangzhou University,Guangzhou,Guangdong 510006,China
生物科学
Craniodental morphologyDeep learningFeature fusionHierarchical classificationSpecies identification
《Zoological Research》 2026 (2)
P.404-413,10
supported by the National Natural Science Foundation of China(32170452)Guangdong Basic and Applied Basic Research Foundation(2022B1515020033)Key Program of the National Natural Science Foundation of China Regional Innovation and Development Joint Fund(U23A20161)Open Project of Ministry of Education Key Laboratory for Ecology of Tropical Islands,Hainan Normal University(HNSF-OP-2024-3)Guangzhou Higher Education Teaching Quality and Teaching Reform Engineering Special Talent Training Plan Project(2022ZXRCPR007)Bundesministerium für Bildung und Forschung(BMBF Project KI-Morph 05D2022)National Key R&D Program of China(2022YFC2601200)。
评论