This paper describes the authors’ development and testing of a machine-learning technique for determining the authenticity of the signature on a document.
Signature verification is a common task in forensic document analysis. It is one of determining whether a questioned signature matches known signature samples. From the viewpoint of automating the task it can be viewed as one that involves machine learning from a population of signatures. There are two types of learning to be accomplished. In the first, the training set consists of “genuines” and forgeries from a general population. In the second there are genuine signatures in a given case. The two learning tasks are called person-independent (or general) learning and person-dependent (or special) learning. General learning is from a population of genuine and forged signatures of several individuals, where the differences between genuines and forgeries across all individuals are learned. The general learning model allows a questioned signature to be compared to a single genuine signature. In special learning, a person’s signature is learned from multiple samples of only that person’s signature– where within-person similarities are learned. When a sufficient number of samples are available, special learning performs better than general learning (5% higher accuracy). With special learning, verification accuracy increases with the number of samples. (Published abstract provided)
Similar Publications
- Assessing the Strength of Trace Evidence Fracture Fits through a Comprehensive, Systematic and Quantifiable Approach
- Characterizing the Natural Genetic and Epigenetic Diversity of Human Populations
- Post-burn and Post-blast Rapid Detection of Trace and Bulk Energetics by 3D-printed Cone Spray Ionization Mass Spectrometry