{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["12(1)"],"submitter":["Liu X"],"pubmed_abstract":["Ancient character recognition is not only important for the study and understanding of ancient history but also has a profound impact on the inheritance and development of national culture. In order to reduce the study of difficult professional knowledge of ancient characters, and meanwhile overcome the lack of data, class imbalance, diversification of glyphs, and open set recognition problems in ancient characters, we propose a Siamese similarity network based on a similarity learning method to directly learn input similarity and then apply the trained model to establish one shot classification task for recognition. Multi-scale fusion backbone structure and embedded structure are proposed in the network to improve the model's ability to extract features. We also propose the soft similarit"],"journal":["Scientific reports"],"pagination":["14820"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC9436983"],"repository":["biostudies-literature"],"pubmed_title":["One shot ancient character recognition with siamese similarity network."],"pmcid":["PMC9436983"],"pubmed_authors":["Liu X","Xiong Y","Gao W","Li R","Chen S","Tang X"],"additional_accession":[]},"is_claimable":false,"name":"One shot ancient character recognition with siamese similarity network.","description":"Ancient character recognition is not only important for the study and understanding of ancient history but also has a profound impact on the inheritance and development of national culture. In order to reduce the study of difficult professional knowledge of ancient characters, and meanwhile overcome the lack of data, class imbalance, diversification of glyphs, and open set recognition problems in ancient characters, we propose a Siamese similarity network based on a similarity learning method to directly learn input similarity and then apply the trained model to establish one shot classification task for recognition. Multi-scale fusion backbone structure and embedded structure are proposed in the network to improve the model's ability to extract features. We also propose the soft similarit","dates":{"release":"2022-01-01T00:00:00Z","publication":"2022 Sep","modification":"2025-04-21T14:25:58.821Z","creation":"2025-04-21T14:25:58.821Z"},"accession":"S-EPMC9436983","cross_references":{"pubmed":["36050362"],"doi":["10.1038/s41598-022-18986-z"]}}