非破坏性手写文档检查的新数据集

本数据集由卡塔尼亚大学数学与计算机科学系创建，旨在通过非破坏性检查方法分析手写文档。数据集包含两部分：第一部分是21份通过传统‘笔和纸’方法书写的文档，后被数字化；第二部分是362份由124位不同人士手写的文档，通过特定流程获取。数据集不仅包括作者的原始书法，还记录了他们尝试模仿他人书法的情况。此数据集的应用领域主要集中在法医手写文档分析，旨在通过机器学习和深度学习模型提高手写文档的分析准确性和客观性。

This dataset was developed by the Department of Mathematics and Computer Science, University of Catania, for the analysis of handwritten documents using non-destructive inspection methods. The dataset is divided into two parts: the first part consists of 21 handwritten documents created via traditional pen-and-paper methods and subsequently digitized; the second part includes 362 handwritten documents obtained from 124 distinct individuals through a standardized procedure. In addition to the original handwriting of the authors, the dataset also records instances where the authors attempted to mimic others' handwriting. The primary application domain of this dataset is forensic handwritten document analysis, aiming to improve the accuracy and objectivity of handwritten document analysis through machine learning and deep learning models.