Document source identification in printer forensics involves determining the origin of a printed document based on characteristics such as the printer model, serial number, defects, or unique printing artifacts. This process is crucial in forensic investigations, particularly in cases involving counterfeit documents or unauthorized printing. However, consistent pattern identification across various printer types remains challenging, especially when efforts are made to alter printer-generated artifacts. Machine learning models are often used in these tasks, but selecting discriminative features while minimizing noise is essential. Traditional KNN classifiers require a careful selection of distance metrics to capture relevant printing characteristics effectively. This study proposes leveraging quantum-inspired computing to improve KNN classifiers for printer source identification, offering better accuracy even with noisy or variable printing conditions. The proposed approach uses the Gray Level Co-occurrence Matrix (GLCM) for feature extraction, which is resilient to changes in rotation and scale, making it well-suited for texture analysis. Experimental results show that the quantum-inspired KNN classifier captures subtle printing artifacts, leading to improved classification accuracy despite noise and variability.
