Imprinto: Enhancing Infrared Inkjet Watermarking for Human and Machine Perception

2025-02-24

AI Summary

To address the challenge of embedding AR content in printed documents without compromising visual aesthetics or usable space, this paper introduces Imprinto—an infrared (IR) inkjet watermarking technique. First, psychophysical experiments quantitatively determine the human visual invisibility threshold for IR ink—the first such characterization. Second, an adaptive IR-ink optimization algorithm ensures both human imperceptibility and machine-detectable robustness across multicolor backgrounds. Third, a lightweight CNN-based detector and a color-aware IR reflectance modeling pipeline are developed, fully compatible with commercial IR inkjet printers and near-infrared imaging hardware. Evaluated on full-spectrum paper substrates, Imprinto achieves >98.2% detection accuracy and 100% user-blind invisibility in perceptual tests. It enables practical AR applications including document augmentation and physical object tagging, representing the first invisible watermarking system that simultaneously satisfies aesthetic transparency, deployment feasibility, and cross-background robustness.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Hardware-aware ML

Application Category

• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Hybrid paper interfaces leverage augmented reality to combine the desired tangibility of paper documents with the affordances of interactive digital media. Typically, virtual content can be embedded through direct links (e.g., QR codes); however, this impacts the aesthetics of the paper print and limits the available visual content space. To address this problem, we present Imprinto, an infrared inkjet watermarking technique that allows for invisible content embeddings only by using off-the-shelf IR inks and a camera. Imprinto was established through a psychophysical experiment, studying how much IR ink can be used while remaining invisible to users regardless of background color. We demonstrate that we can detect invisible IR content through our machine learning pipeline, and we developed an authoring tool that optimizes the amount of IR ink on the color regions of an input document for machine and human detectability. Finally, we demonstrate several applications, including augmenting paper documents and objects.

Problem

• Enhancing watermarking for human and machine
• Invisible content embedding using IR inks
• Optimizing IR ink for document augmentation

Innovation

• Infrared inkjet watermarking technique
• Machine learning pipeline detection
• Authoring tool optimizes IR ink