Digital color analysis and machine learning for ballpoint pen ink clustering and aging investigation.

Fraudulent activities often involve document manipulation, which poses a significant challenge to forensic science. To address this issue, a novel method was developed that combines intended artificial UV pre-degradation, digital color analysis (DCA) of stroke images, and various machine learning (ML) models. This method can cluster blue ballpoint pen inks and predict their photodegradation time.

Classification of ballpoint pen inks based on selective extraction and subsequent digital color and cluster analyses.

Here, we propose a novel approach to the classification of blue ballpoint pen inks based on a combination of selective extraction of coloring components from a paper carrier, digital color analysis (DCA) of the remaining traces, and hierarchical cluster analysis of DCA results. Since most documents of high importance are still produced in hard copies, the proposed method, being highly time- and cost-efficient, could be a significant contribution to forensic science in the field of authenticating handwritten documents. Several commonly used solvents were applied in parallel as extractants to the replicate strokes produced by each pen.