Innovative Methods for Non-Destructive Inspection of Handwritten Documents
This addresses the need for objective and replicable forensic analysis of handwritten documents for law enforcement agencies, though it is incremental as it builds on existing methods with new applications.
The paper tackled the problem of subjective and non-replicable authorship verification of handwritten documents by developing a framework that extracts intrinsic measures like text line heights and character sizes using image processing and deep learning, achieving state-of-the-art performance in objectively determining authorship across traditional and digital writing media.
Handwritten document analysis is an area of forensic science, with the goal of establishing authorship of documents through examination of inherent characteristics. Law enforcement agencies use standard protocols based on manual processing of handwritten documents. This method is time-consuming, is often subjective in its evaluation, and is not replicable. To overcome these limitations, in this paper we present a framework capable of extracting and analyzing intrinsic measures of manuscript documents related to text line heights, space between words, and character sizes using image processing and deep learning techniques. The final feature vector for each document involved consists of the mean and standard deviation for every type of measure collected. By quantifying the Euclidean distance between the feature vectors of the documents to be compared, authorship can be discerned. Our study pioneered the comparison between traditionally handwritten documents and those produced with digital tools (e.g., tablets). Experimental results demonstrate the ability of our method to objectively determine authorship in different writing media, outperforming the state of the art.