The use of the likelihood ratio for evaluative and investigative purposes in comparative forensic handwriting examination

The classification of handwriting features of the Kazakh language written in Latin script

In 2017, the Republic of Kazakhstan began the phased transition of its alphabet from Cyrillic to Latin script. This transition has presented significant challenges to Kazakhstani document examiners, who have yet to develop appropriate methodologies for the analysis of handwriting samples written in the Kazakh language using Latin letters. This study aims to identify distinguishing macro and micro features of letters within Kazakh writing samples produced using the Latin alphabet and determine their frequencies of occurrence and discriminating power indices. Micro features were examined using the four most frequently appearing letters: "a", "y", "e" and "n". A comparative analysis of tested Latin letters with those of a similar configuration in Cyrillic demonstrated differences in the number of distinguishing features, as well as in the frequency of occurrence and discriminating power indices of similar features. These results show that separate statistical bases should be used for Latin and Cyrillic letters when analysing handwriting samples based on the frequencies of occurrence of micro and macro writing features.

An exploratory study on the handwritten allographic features of multi-ethnic population with different educational backgrounds

Ethnicity, native and/or foreign language knowledge, as well as the learned writing systems potentially influence the development of an individual’s handwriting. The unique education system consisting of National schools, Chinese-medium vernacular schools, Tamil-medium vernacular schools, and Islamic religious schools in Malaysia may have established specific characteristic handwritten allographic features that deserve investigation within the intelligence context. This study was aimed to explore handwritten allographic features of handwriting samples from 120 subjects (30 writers from four different educational backgrounds mentioned above). Characteristic features which could be attributed to the study groups were statistically analyzed and identified. In this study, thirteen allographic features, including letters "A", "B", "D", "H", "p", "T", "t", "w", "X" and "x", were found to be discriminative. Such information could serve to indicate the primary education system undergone by a writer; enabling the comparison of different handwriting profiles and allowing characterization of writers to a specific group of people.

Bayesian evaluation of dynamic signatures in operational conditions

Forensic handwriting examiners (FHE) activities are focused on comparative analysis of handwritten objects such as signatures. Their role is to provide and evaluate evidence for and against the authenticity of a questioned signature. In recent years, cases involving handwritten signatures captured on electronic devices have become more commonplace. These so-called 'dynamic signatures' (also known as 'digitally captured signatures') are much different from paper-based signatures. Not only does the medium of recording differ, but also the type, volume of data and features are different from the pattern-based evidence that makes up paper-based signatures. Recent developments in forensic science - including signature examination - have led to the adoption of evaluative probabilistic methodologies in many disciplines [see, e.g. ENFSI 1915 Guidelines]. In the current paper, a probabilistic model to evaluate signature evidence in the form of multivariate data, as proposed and described in Wacom Europe GmbH (2019), is adopted. Topics like data sparsity, joint evaluation of multiple features and feature selection are investigated. Performed experimental studies showed an accuracy rate above 90% even when a limited number (5) of reference signatures was available. The performances of a multivariate approach are compared with those characterizing a so-called multiplicative approach where variables (features) are taken as independent and the Bayes' factor (BF) is obtained as the product of univariate BFs associated to each selected feature. The simplicity of this latter approach is, however, accompanied by severe issues about the reliability of results. The use of a multivariate approach is therefore highly recommended. Finally, the evidential values in correspondence of alternative feature sets are compared. Results suggest that discriminative features are writer-related and necessitate a case-specific selection.

Digital evidence exceptionalism? A review and discussion of conceptual hurdles in digital evidence transformation

Forensic science is currently undergoing a transformation and expansion to include modern types of evidence, such as evidence generated by digital investigations. This development is said to raise a series of challenges, both in operational and conceptual dimensions. This paper reviews and discusses a series of convoluted conceptual hurdles that are encountered in connection with the use of digital evidence as part of evidence and proof processes at trial, in contradistinction to investigative uses of such types of evidence. As a recent example raising such hurdles, we analyse and discuss assertions and proposals made in the article "Digital Evidence Certainty Descriptors (DECDs)" by Graeme Horsman (32 Forensic Science International: Digital Investigation (2020) 200896).

The use of handwriting examinations beyond the traditional court purpose

Traditionally, forensic science has predominantly focused its resources and objectives on addressing court related questions. However, this view restricts the contribution of forensic science to one function and results in lost opportunities as investigative and intelligence roles are often overlooked. A change of perspective and expansion of the contributions of forensic science is required to take advantage of the benefits of abductive and inductive thought processes throughout the investigative and intelligence functions. One forensic discipline that has the potential to broaden its traditional focus is handwriting examination. Typically used in investigations that are focused on both criminal and civil cases, the examination procedure and outcome are time consuming and subjective, requiring a detailed study of the features of the handwriting in question. Traditionally, the major handwriting features exploited are characteristics that are often considered individual (or at least highly polymorphic) and habitual. However, handwriting can be considered as an information vector in an intelligence framework. One such example is the recognition of key elements related to the author's native language. This paper discusses the traditional method generally used around the world and proposes a theoretical approach to expand the application of handwriting examination towards gaining additional information for intelligence purposes. This concept will be designed and tested in a future research project.

Extraction and analysis of the width, gray scale and radian in Chinese signature handwriting

Forensic handwriting examination is a relevant identification process in forensic science. This research obtained ideas from the process of features detection and analysis in forensic handwriting examination. A Chinese signature database was developed and comprised original signatures, freehand imitation forgeries, random forgeries and tracing imitation forgeries. The features of width, gray scale and radian combined with stroke orders were automatically extracted after image processing. A correlation coefficient was used to precisely characterize and express the similarities between signatures. To validate the differences between writers, a multivariate analysis of the variance was employed. The canonical discriminant analysis was performed between the original and non-original signatures; the cross-validation estimated the discriminating power of the width, gray scale and radian data. It is suggested that the extraction and analysis of these properties in Chinese signatures is reasonable. Meanwhile, forensic handwriting examination using the quantitative feature extraction and statistical analysis methods in this research could be performed with a satisfactory result in the discriminant analysis.