Elucidating the relationships between two automated handwriting feature quantification systems for multiple pairwise comparisons. Issue 2 (11th October 2021)

• Record Type: Journal Article
• Authors: Fuglsby, Cami; Saunders, Christopher; Ommen, Danica M.; Buscaglia, JoAnn; Caligiuri, Michael P.
• Is Part Of: Journal of forensic sciences. Volume 67:Issue 2(2022)
• Page Start: 642
• Page End: 650
• Publication Date: 2021-10-11
• Subjects: automated handwriting system -- black box system -- handwriting -- questioned documents -- statistical modeling -- validity -- white box system; Medical jurisprudence -- Periodicals; Forensic sciences -- Periodicals; Forensic Medicine -- Periodicals; Gerechtelijke geneeskunde; Gerechtelijke chemie; Gerechtelijke psychiatrie; 363.2505
• DOI: 10.1111/1556-4029.14914
• Languages: English
• ISSNs: 0022-1198

Abstract

Abstract: Recent advances in complex automated handwriting identification systems have led to a lack of understandability of these systems' computational processes and features by the forensic handwriting examiners that they are designed to support. To mitigate this issue, this research studied the relationship between two systems: FLASH ID ®, an automated handwriting/black box system that uses measurements extracted from a static image of handwriting, and MovAlyzeR ®, a system that captures kinematic features from pen strokes. For this study, 33 writers each wrote 60 phrases from the London Letter using cursive writing and handprinting, which led to thousands of sample pairs for analysis. The dissimilarities between pairs of samples were calculated using two score functions (one for each system). The observed results indicate that dissimilarity scores based on kinematic spatial‐geometric pen stroke features (e.g., amplitude and slant) have a statistically significant relationship with dissimilarity scores obtained using static, graph‐based features used by the FLASH ID ® system. Similar relationships were observed for temporal features (e.g., duration and velocity) but not pen pressure, and for both handprinting and cursive samples. These results strongly imply that both the current implementation of FLASH ID ® and MovAlyzeR ® rely on similar features sets when measuring differences in pairs of handwritten samples. These results suggest that studies of biometric discrimination using MovAlyzeR ®, specifically those based on the spatial‐geometric feature set, support the validity of biometric matching algorithms based on FLASH ID ® output.