Classification of Inkjet Printers based on Droplet Statistics

TL;DR

This paper presents a method for classifying inkjet printer models by analyzing droplet pattern features from high-resolution scans, enabling identification of both manufacturer and specific models using neural networks.

Contribution

It introduces a novel dataset and demonstrates that droplet frequency domain features can effectively classify printer models with neural networks.

Findings

Neural networks can distinguish printer models based on droplet features.

High-resolution scans and frequency domain features are effective for printer classification.

The dataset supports further research in printer identification techniques.

Abstract

Knowing the printer model used to print a given document may provide a crucial lead towards identifying counterfeits or conversely verifying the validity of a real document. Inkjet printers produce probabilistic droplet patterns that appear to be distinct for each printer model and as such we investigate the utilization of droplet characteristics including frequency domain features extracted from printed document scans for the classification of the underlying printer model. We collect and publish a dataset of high resolution document scans and show that our extracted features are informative enough to enable a neural network to distinguish not only the printer manufacturer, but also individual printer models.