User Trust in Assisted Decision-Making Using Miniaturized Near-Infrared Spectroscopy

Jiang, Weiwei; Sarsenbayeva, Zhanna; Berkel, Niels van; Wang, Chaofan; Yu, Difeng; Wei, Jing; Gonçalves, Jorge; Kostakos, Vassilis

doi:10.1145/3411764.3445710

Cited by 7 publications

(3 citation statements)

References 86 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Conventionally, NIRS is used for non-destructive analysis in a range of disciplines [Jiang et al 2021;Klakegg et al 2016;Siesler et al 2008]. Its typical applications include food quality control in agriculture [Goel et al 2015], physiological diagnosis in healthcare [Klakegg et al 2018;Scheeren et al 2012], medicine control in pharmaceutics [Roggo et al 2007], and brain-computer interfaces in computer science [Solovey et al 2009].…”

Section: Ccs Concepts: • Computing Methodologies → Computer Graphics;mentioning

confidence: 99%

Near-infrared Imaging for Information Embedding and Extraction with Layered Structures

Jiang¹,

Yu²,

Wang³

et al. 2022

ACM Trans. Graph.

Self Cite

View full text Add to dashboard Cite

Non-invasive inspection and imaging techniques are used to acquire non-visible information embedded in samples. Typical applications include medical imaging, defect evaluation, and electronics testing. However, existing methods have specific limitations, including safety risks ( e.g. , X-ray), equipment costs ( e.g. , optical tomography), personnel training ( e.g. , ultrasonography) and material constraints ( e.g. , terahertz spectroscopy). Such constraints make these approaches impractical for everyday scenarios. In this paper, we present a method that is low-cost and practical for non-invasive inspection in everyday settings. Our prototype incorporates a miniaturized near-infrared spectroscopy scanner driven by a computer-controlled 2D-plotter. Our work presents a method to optimize content embedding, as well as a wavelength selection algorithm to extract content without human supervision. We show that our method can successfully extract occluded text through a paper stack of up to 16 pages. In addition, we present a deep-learning based image enhancement model that can further improve the image quality and simultaneously decompose overlapping content. Finally, we demonstrate how our method can be generalized to different inks and other layered materials beyond paper. Our approach enables a wide range of content embedding applications, including chipless information embedding, physical secret sharing, 3D print evaluations, and steganography.

show abstract

Section: Ccs Concepts: • Computing Methodologies → Computer Graphics;mentioning

confidence: 99%

Near-infrared Imaging for Information Embedding and Extraction with Layered Structures

Jiang¹,

Yu²,

Wang³

et al. 2022

ACM Trans. Graph.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The scanning resolution is 24 × 24, resulting 576 near-infrared spectra for each image. The scanner's settings are identical to literature [29][30][31] (900 𝑛𝑚 -1700 𝑛𝑚 wavelength range, 228 wavelength resolution, 7.03 𝑛𝑚 light pattern width, and 0.635 𝑚𝑠 exposure time). As a result, the raw dimension for a near-infrared image is 24 × 24 × 228.…”

Section: Reading Processmentioning

confidence: 99%

InfoPrint: Embedding Information into 3D Printed Objects

Jiang¹,

Wang²,

Sarsenbayeva³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We present a technique to embed information invisible to the eye inside 3D printed objects. The information is integrated in the object model, and then fabricated using off-the-shelf dual-head FDM (Fused Deposition Modeling) 3D printers. Our process does not require human intervention during or after printing with the integrated model. The information can be arbitrary symbols, such as icons, text, binary, or handwriting. To retrieve the information, we evaluate two different infrared-based imaging devices that are readily available -thermal cameras and near-infrared scanners. Based on our results, we propose design guidelines for a range of use cases to embed and extract hidden information. We demonstrate how our method can be used for different applications, such as interactive thermal displays, hidden board game tokens, tagging functional printed objects, and autographing non-fungible fabrication work.

show abstract

“…Only a limited amount of prior work focused on using multi-or hyperspectral imaging in HCI. In comparison, the use of a limited amount of bands of the electromagnetic spectrum -for example using near-infrared for spectroscopy of sucrose contents drinks [15] -is much more common in HCI and UbiComp as such devices are cheaper, smaller and easier to integrate into end-user devices [15,16,13,22]. An example of using multi-spectral imaging is SpeCam presented by Yeo at al.…”

Section: Introductionmentioning

confidence: 99%

Museum Visitor Experiences Based on Hyperspectral Image Data

Löchtefeld,

Papachristos,

Deborah

2023

Human-Computer Interaction – INTERACT 2023

View full text Add to dashboard Cite

Hyper-and multispectral imaging allows to collect data from specific wavelength ranges or across the electromagnetic spectrum, including frequencies that are imperceivable for humans. As non-invasive imaging techniques, it has been used in the field of art conservation and art history extensively in the past. In these areas application of hyperspectral imaging include for example conservation monitoring or pigment identification. In the context of museum exhibits, hyperspectral data of artworks offers a unique opportunity to enhance visitor experiences by providing new ways of engaging with artefacts, artworks, and cultural heritage. This paper presents design concepts for creating immersive and meaningful experiences using hyperspectral data. We used an expert led design workshop to explore the possibilities of museum experiences with such data, including considerations such as suited technologies, visitor types and visitor experience.

show abstract

User Trust in Assisted Decision-Making Using Miniaturized Near-Infrared Spectroscopy

Cited by 7 publications

References 86 publications

Near-infrared Imaging for Information Embedding and Extraction with Layered Structures

Near-infrared Imaging for Information Embedding and Extraction with Layered Structures

InfoPrint: Embedding Information into 3D Printed Objects

Museum Visitor Experiences Based on Hyperspectral Image Data

Contact Info

Product

Resources

About