2026-10-14T21:18:15Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33904520 2026-09-17T17:35:23Z category_7 category_12 category_14 category_21 category_734 portal_5 item_type_3 month_year_09_2026

<p>Statistics of original data. Train Set, Validation Set, Test Set denote the number of users or fonts in those datasets, respectively. Total Image is the total Chinese character image number belong to the user or font. The symbol “*” indicates that the invalid or blank images are excluded.</p> Li Zhu (67404) Long Tang (700109) Huaqing Mao (8230416) Medicine Cell Biology Molecular Biology Biotechnology Biological Sciences not elsewhere classified single biometric pattern informative region automatically false acceptance rate extensive experiments show experimental results demonstrates baseline svm method model &# 8217 attention convolutional layers 78 %, representing unlike signature verification 000 character images fonts model achieves channel cnns model general handwriting comparison accuracy fluctuates widely chinese character handwriting proposed methods extract multiple characters susceptible handwriting comparison proposed model model outputs multiple spatial existing methods channel receives attention mechanisms 50 fonts 36 %, proposed clasn comparison feature signature comparisons entire signature character level whole sentence two characters reduced sensitivity paragraph level enabling finer data noise currently available approximately 48 approach operates analyzes text alignment variations additional information 800 users <p>Statistics of original data. Train Set, Validation Set, Test Set denote the number of users or fonts in those datasets, respectively. Total Image is the total Chinese character image number belong to the user or font. The symbol “*” indicates that the invalid or blank images are excluded.</p> 2026-09-17T17:35:09Z Dataset Dataset 10.1371/journal.pone.0353503.t001 https://figshare.com/articles/dataset/_p_Statistics_of_original_data_Train_Set_Validation_Set_Test_Set_denote_the_number_of_users_or_fonts_in_those_datasets_respectively_Total_Image_is_the_total_Chinese_character_image_number_belong_to_the_user_or_font_The_symbol_indicates_that/33904520 CC BY 4.0