A Harmonic Approach to Handwriting Style Synthesis Using Deep Learning

作     者：Mahatir Ahmed Tusher Saket Choudary Kongara Sagar Dhanraj Pande Seong Ki Kim Salil Bharany 

作者机构：School of Computer Science and EngineeringVIT-AP UniversityAmaravatiAndhra Pradesh522237India School of Engineering&TechnologyPimpri Chinchwad UniversityPuneMaharashtra412106India Department of Computer EngineeringChosun UniversityGwangju61452Republic of Korea Independent ResearcherAmritsarPunjab143001India 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2024年第79卷第6期

页      面：4063-4080页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Research Foundation of Korea(NRF)Grant funded by the Korean government(MSIT)(NRF-2023R1A2C1005950) 

主　　题：Recurrent neural network generative adversarial network style encoder fréchet inception distance geometric score character error rate mixture density network word error rate 

摘      要：The challenging task of handwriting style synthesis requires capturing the individuality and diversity of human *** majority of currently available methods use either a generative adversarial network(GAN)or a recurrent neural network(RNN)to generate new handwriting *** is why these techniques frequently fall short of producing diverse and realistic text pictures,particularly for terms that are not commonly *** resolve that,this research proposes a novel deep learning model that consists of a style encoder and a text generator to synthesize different handwriting *** network excels in generating conditional text by extracting style vectors from a series of style *** model performs admirably on a range of handwriting synthesis tasks,including the production of text that is *** works more effectively than previous approaches by displaying lower values on key Generative Adversarial Network evaluation metrics,such Geometric Score(GS)(3.21×10^(-5))and Fréchet Inception Distance(FID)(8.75),as well as text recognition metrics,like Character Error Rate(CER)and Word Error Rate(WER).A thorough component analysis revealed the steady improvement in image production quality,highlighting the importance of specific handwriting *** fields include digital forensics,creative writing,and document security.