Search

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.

A class of computationally efficient approximations to a set of natural U-statistics and related U-processes that arise in forensic and biometric comparisons have been developed. This paper details...

A National Research Council report on strengthening forensic science raised concern over the lack of scientific studies supporting the validity of examining and interpreting forensic evidence. However, establishing the foundational validity of subjective methods can be challenging. The present study aimed to establish the scientific validity of expert writership opinions and the two-stage approach to evidence interpretation using measures derived from research on handwriting motor control. Regression-based procedures were used to address two experimental questions: 1) what are the relative contributions of kinematic and pressure features in predicting examiner support for alternate writership propositions when examining pairs of questioned handwriting samples; and 2) to what extent does information about the rarity of the kinematic feature dissimilarity scores improve the accuracy of a predictive model based on dissimilarity alone. Regarding the first question, we identified a multifactor model consisting of feature dissimilarity scores and their population distributions having correlation coefficients (R2) of 0.84 and 0.88 for the same-writer and different-writers propositions, respectively. Temporal features contributed up to 21% to the predictive value of the model, whereas spatial features contributed only 9% and pen pressure contributed up to 17%. When we compared models reflecting a single-stage process (based on feature dissimilarities) of forming opinions with models reflecting a two-stage process (based on feature dissimilarities and rarity) we found that the two-stage models had an average of 15.25% greater predictive value than single-stage models. These findings support the scientific validity of FDE writership determinations and underscore the importance of the two-stage approach for evidence interpretation.

The two-stage evaluative process is an established framework utilized by forensic document examiners (FDEs) for reaching a conclusion about the source(s) of handwritten evidence. In the second, or discrimination, stage, the examiner attempts to estimate the rarity of observations in a relevant background population. Unfortunately, control samples from a relevant background population are often unavailable, leaving the FDE to reach this determination based on subjective experience. Automated handwriting feature recognition systems are capable of performing both feature comparison and discrimination, yet these systems have not been subjected to empirical validation studies. In the present study, we repurposed a commercially available automated system to generate empirical distributions for ranking feature dissimilarity scores among pairs of handwritten phrases. The blinded results of this automated process were used to survey an international cohort of 36 FDEs regarding their strength of support for same- and different-writer propositions. The survey served to cross-validate FDE decision-making under the two-stage approach. Results from the survey demonstrated a clear pattern of response consistent with ground truth. Predictive regression analyses indicated that the automated feature dissimilarity scores and the log of their cumulative distribution functions accounted for 72% of the variability in FDE opinions. This study demonstrated that feature dissimilarity scores acquired using automated processes and their distributions are closely aligned with FDE decision-making processes supporting the heuristic value of the two-stage evaluative framework.