Handwriting identification is widely accepted as scientific evidence.However,its authenticity is questioned because it depends on the appraiser's professional skills and susceptibility to deliberate false identifi...Handwriting identification is widely accepted as scientific evidence.However,its authenticity is questioned because it depends on the appraiser's professional skills and susceptibility to deliberate false identification by expert witnesses.Consequently,there is an urgent need for an effective handwriting identification system(HWIS)that reduces reliance on the appraiser's skills and mitigates the risk of international false identification.Here,we report a HWIS that integrates a self-powered handwriting signal data acquisition device with an advanced deep learning architecture possessing powerful feature extraction ability and one-class classification function.The device successfully captures the characteristic differences in handwriting behavior between genuine writers and forgers,and the handwriting identification results demonstrate the excellent performance of our system,showcasing its powerful potential to solve the longstanding challenge of handwriting identification that has perplexed humans for a considerable period.Moreover,this work exhibits the system's capability for remote access and downloading the handwriting signal data through the data cloud,highlighting its practical value for fulfilling the requirements of handwriting recognition and identification applications,and it can effectively advance signature information security and ensure the protection of private information.展开更多
As a historic technology,handwriting identification,especially that of Chinese characters,plays an important role in judicial trials both in domestic and abroad.However,in recent decades,handwriting identification has...As a historic technology,handwriting identification,especially that of Chinese characters,plays an important role in judicial trials both in domestic and abroad.However,in recent decades,handwriting identification has feced a challenging situation;the scientificity of handwriting identification has been questioned.This article analyzes the reasons for questioning handwriting identification,focusing on the aspects of standards,methods,quantitative analysis of handwriting identification,and qualification,training,and assessment of document examiners.Besides,corresponding solutions for the above aspects and some other characteristics,such as systematic identification,cross-examination of expert opinions,and rule of corroboration,are proposed.展开更多
This article starts from the point of view that handwriting examination is dependent on empiricism and by analyzing the core steps ofhandwriting identification explains that it might be influenced by subjective bias.I...This article starts from the point of view that handwriting examination is dependent on empiricism and by analyzing the core steps ofhandwriting identification explains that it might be influenced by subjective bias.In practice,examiners cannot avoid biases in decision-making;instead,we must accept the existence of subjective bias in handwriting identification and then discuss its impact;for instance,feature selection in the process of comprehensive evaluation,which involves a comparison of the number and quality of similarities and differences between a questioned sample and the references.While we conclude that comprehensive evaluation is the most important step in the identification process,industries in China do not stipulate explicit and transparent criteria for it,making it hard to numerically quantify the characteristics ofhandwriting identification.In this article,forensic examiners5 opinions on handwriting identification were obtained through a survey.One finding was that most handwriting examiners believe that handwriting identification is subject to subjective bias.In addition,they believe that the subjective cognition of handwriting identification can somehow help actively produce the correct opinion;before the examination,most handwriting examiners think that they should understand the context and so on.Finally,through the questionnaire,which contained variations such as the same case with different background information,different cases with the same background information,and the same case with or without context,it was concluded that handwriting identification does have certain subjectivity.However,which kind of factors influence this subjectivity is not presently clear.Furthermore,it is difficult to control uncertainties when fbnnmg an opinion on identification.An alternative way is to perform scrutiny after the formulation ofhandwritmg opinions;for example,internal and external reviews such as appearing in court.展开更多
Handwriting analysis is a crucial forensic tool used for identifying individuals,authenticating documents,and detecting forgeries in both civil and criminal investigations.The increasing globalization and multilingual...Handwriting analysis is a crucial forensic tool used for identifying individuals,authenticating documents,and detecting forgeries in both civil and criminal investigations.The increasing globalization and multilingual nature of societies pose significant challenges for forensic handwriting examiners due to variations in script structures,linguistic influences,and handwriting habits of bilingual and multilingual writers.This review explores the fundamentals of multilingual handwriting analysis,the differences in writing systems such as Latin,Devanagari,Arabic,Chinese,Cyrillic,and Hebrew,and the challenges associated with analyzing these scripts.Traditional forensic handwriting comparison methods rely on expert visual analysis of handwriting characteristics,including slant,pressure,loops,spacing,and baseline consistency.However,recent advancements in artificial intelligence(AI),deep learning,optical character recognition,and convolutional neural networks have significantly improved multilingual handwriting identification.Despite these advancements,automatic multilingual script recognition(AMSR)remains a challenge,especially for handwritten documents,as most existing AMSR systems primarily focus on printed text.This study highlights emerging technologies and advanced methodologies that enhance forensic handwriting analysis,including gray‑level co‑occurrence matrix,local binary pattern,and deep learning‑based models.It also emphasizes the need for standardized forensic handwriting examination protocols and large‑scale multilingual handwriting databases to improve accuracy and consistency.Future perspectives in multilingual handwriting analysis include AI‑driven handwriting authentication,blockchain‑based document verification,and augmented reality(AR)applications in forensic investigations.By integrating traditional forensic techniques with modern computational approaches,forensic handwriting analysis can achieve greater precision in script recognition,writer identification,and forgery detection,ensuring the reliability and admissibility of handwriting evidence in legal contexts.展开更多
Handwriting expertise,as a form of forensic evidence,was once considered by most courts under the Anglo-American law system to be infallible,but this position was significantly challenged by the Daubert case(1993)and ...Handwriting expertise,as a form of forensic evidence,was once considered by most courts under the Anglo-American law system to be infallible,but this position was significantly challenged by the Daubert case(1993)and further by the President’s Council of Advisors on Science and Technology report published in 2016.In China,handwriting expertise has often been accepted as forensic evidence.However,this does not mean that there is no need to review the reliability of handwriting expertise.In this study,we analyze the current situation in China regarding the reliability of handwriting identification using cases from China’s judicial judgment database.We intend to identify the reasons for rejection of handwriting expertise,analyze the outcomes of applications for re-examination,and examine the court’s evaluation of different forensic opinions in relation to a given case.We also propose ways to strengthen the reliability of handwriting identification in China.展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.52105206,62241308,and 92271201)Guangdong Basic and Applied Basic Research Foundation(2023A1515240050)+1 种基金China Postdoctoral Science Foundation(Grant No.BX2021230)the Opening Project of National and local joint Engineering Research Center for industrial friction and lubrication technology(Grant No.2023-GD-0001).
文摘Handwriting identification is widely accepted as scientific evidence.However,its authenticity is questioned because it depends on the appraiser's professional skills and susceptibility to deliberate false identification by expert witnesses.Consequently,there is an urgent need for an effective handwriting identification system(HWIS)that reduces reliance on the appraiser's skills and mitigates the risk of international false identification.Here,we report a HWIS that integrates a self-powered handwriting signal data acquisition device with an advanced deep learning architecture possessing powerful feature extraction ability and one-class classification function.The device successfully captures the characteristic differences in handwriting behavior between genuine writers and forgers,and the handwriting identification results demonstrate the excellent performance of our system,showcasing its powerful potential to solve the longstanding challenge of handwriting identification that has perplexed humans for a considerable period.Moreover,this work exhibits the system's capability for remote access and downloading the handwriting signal data through the data cloud,highlighting its practical value for fulfilling the requirements of handwriting recognition and identification applications,and it can effectively advance signature information security and ensure the protection of private information.
基金Program for school-level Research in China University of Political Science and Law(16ZFQ82008).
文摘As a historic technology,handwriting identification,especially that of Chinese characters,plays an important role in judicial trials both in domestic and abroad.However,in recent decades,handwriting identification has feced a challenging situation;the scientificity of handwriting identification has been questioned.This article analyzes the reasons for questioning handwriting identification,focusing on the aspects of standards,methods,quantitative analysis of handwriting identification,and qualification,training,and assessment of document examiners.Besides,corresponding solutions for the above aspects and some other characteristics,such as systematic identification,cross-examination of expert opinions,and rule of corroboration,are proposed.
基金Youth Scientist Program of CUPL Science Research Project(2016),Grant No.16ZFQ82009.
文摘This article starts from the point of view that handwriting examination is dependent on empiricism and by analyzing the core steps ofhandwriting identification explains that it might be influenced by subjective bias.In practice,examiners cannot avoid biases in decision-making;instead,we must accept the existence of subjective bias in handwriting identification and then discuss its impact;for instance,feature selection in the process of comprehensive evaluation,which involves a comparison of the number and quality of similarities and differences between a questioned sample and the references.While we conclude that comprehensive evaluation is the most important step in the identification process,industries in China do not stipulate explicit and transparent criteria for it,making it hard to numerically quantify the characteristics ofhandwriting identification.In this article,forensic examiners5 opinions on handwriting identification were obtained through a survey.One finding was that most handwriting examiners believe that handwriting identification is subject to subjective bias.In addition,they believe that the subjective cognition of handwriting identification can somehow help actively produce the correct opinion;before the examination,most handwriting examiners think that they should understand the context and so on.Finally,through the questionnaire,which contained variations such as the same case with different background information,different cases with the same background information,and the same case with or without context,it was concluded that handwriting identification does have certain subjectivity.However,which kind of factors influence this subjectivity is not presently clear.Furthermore,it is difficult to control uncertainties when fbnnmg an opinion on identification.An alternative way is to perform scrutiny after the formulation ofhandwritmg opinions;for example,internal and external reviews such as appearing in court.
文摘Handwriting analysis is a crucial forensic tool used for identifying individuals,authenticating documents,and detecting forgeries in both civil and criminal investigations.The increasing globalization and multilingual nature of societies pose significant challenges for forensic handwriting examiners due to variations in script structures,linguistic influences,and handwriting habits of bilingual and multilingual writers.This review explores the fundamentals of multilingual handwriting analysis,the differences in writing systems such as Latin,Devanagari,Arabic,Chinese,Cyrillic,and Hebrew,and the challenges associated with analyzing these scripts.Traditional forensic handwriting comparison methods rely on expert visual analysis of handwriting characteristics,including slant,pressure,loops,spacing,and baseline consistency.However,recent advancements in artificial intelligence(AI),deep learning,optical character recognition,and convolutional neural networks have significantly improved multilingual handwriting identification.Despite these advancements,automatic multilingual script recognition(AMSR)remains a challenge,especially for handwritten documents,as most existing AMSR systems primarily focus on printed text.This study highlights emerging technologies and advanced methodologies that enhance forensic handwriting analysis,including gray‑level co‑occurrence matrix,local binary pattern,and deep learning‑based models.It also emphasizes the need for standardized forensic handwriting examination protocols and large‑scale multilingual handwriting databases to improve accuracy and consistency.Future perspectives in multilingual handwriting analysis include AI‑driven handwriting authentication,blockchain‑based document verification,and augmented reality(AR)applications in forensic investigations.By integrating traditional forensic techniques with modern computational approaches,forensic handwriting analysis can achieve greater precision in script recognition,writer identification,and forgery detection,ensuring the reliability and admissibility of handwriting evidence in legal contexts.
基金This research was funded by the Youth Scientist Program of the CUPL Science Research Project(2016),Grant No.16ZFQ82009.
文摘Handwriting expertise,as a form of forensic evidence,was once considered by most courts under the Anglo-American law system to be infallible,but this position was significantly challenged by the Daubert case(1993)and further by the President’s Council of Advisors on Science and Technology report published in 2016.In China,handwriting expertise has often been accepted as forensic evidence.However,this does not mean that there is no need to review the reliability of handwriting expertise.In this study,we analyze the current situation in China regarding the reliability of handwriting identification using cases from China’s judicial judgment database.We intend to identify the reasons for rejection of handwriting expertise,analyze the outcomes of applications for re-examination,and examine the court’s evaluation of different forensic opinions in relation to a given case.We also propose ways to strengthen the reliability of handwriting identification in China.
