Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Yoga as a cost-effective adjunct therapy for dry eye: clinical outcomes from a 12-week randomized controlled trial.

Frontiers in medicine·2026

Same author

Yoga for Eye Disorders-A Systematic Review.

Advances in mind-body medicine·2025

Same author

Correction: Quantum dot-to-dye-based fluorescent ratiometric immunoassay for GFAP: a biomarker for ischaemic stroke and glioblastoma multiforme.

The Analyst·2025

Same author

Turn-on fluorescence sensing of histidine in body fluids: unveiling its oncogenic potential as a cancer risk biomarker.

The Analyst·2025

Same author

Upconversion nanoparticle-FITC conjugate as a fluorescence switching probe for the sensitive detection of Tau: an Alzheimer's disease biomarker.

Mikrochimica acta·2025

Same author

Copper Nanocluster-Enabled Fluorescent Sensing of Serine: A Strategy for Noninvasive Cancer Biomarker Detection.

Journal of fluorescence·2025

Search research articles

Related Experiment Video

Updated: Dec 24, 2025

ExCYT: A Graphical User Interface for Streamlining Analysis of High-Dimensional Cytometry Data

ExCYT: A Graphical User Interface for Streamlining Analysis of High-Dimensional Cytometry Data

Published on: January 16, 2019

Dimensionality reduction and visualisation of hyperspectral ink data using t-SNE.

Binu Melit Devassy¹, Sony George¹

¹Department of Computer Science, Norwegian University of Science and Technology, Gjøvik, Norway.

Forensic Science International

|April 7, 2020

Summary

t-Distributed Stochastic Neighbor embedding (t-SNE) enhances forensic ink analysis by reducing hyperspectral imaging data. This advanced technique improves visualization and clustering for non-destructive document examination.

Keywords:

Dimensionality reduction Hyperspectral imaging Ink analysis Visualisation t-SNE

More Related Videos

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Published on: June 18, 2021

Multimodal Optical Imaging Platform for Studying Cellular Metabolism

Multimodal Optical Imaging Platform for Studying Cellular Metabolism

Published on: June 6, 2025

Related Experiment Videos

Last Updated: Dec 24, 2025

ExCYT: A Graphical User Interface for Streamlining Analysis of High-Dimensional Cytometry Data

ExCYT: A Graphical User Interface for Streamlining Analysis of High-Dimensional Cytometry Data

Published on: January 16, 2019

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Published on: June 18, 2021

Multimodal Optical Imaging Platform for Studying Cellular Metabolism

Multimodal Optical Imaging Platform for Studying Cellular Metabolism

Published on: June 6, 2025

Area of Science:

Forensic Science
Analytical Chemistry
Image Processing

Background:

Ink analysis is crucial in forensic science and document examination.
Hyperspectral imaging (HSI) offers non-invasive analysis of forensic evidence by capturing spectral data.
Processing high-dimensional HSI data presents computational challenges, necessitating dimensionality reduction.

Purpose of the Study:

To introduce and evaluate the t-Distributed Stochastic Neighbor embedding (t-SNE) algorithm for hyperspectral ink analysis.
To assess t-SNE's effectiveness in reducing dimensionality and improving data visualization for forensic document analysis.
To compare t-SNE with Principal Component Analysis (PCA) for ink spectral data processing.

Main Methods:

Application of the t-Distributed Stochastic Neighbor embedding (t-SNE) algorithm to hyperspectral ink data.
Extraction of non-linear similarity features from spectral data.
Dimensionality reduction of HSI data to two dimensions for visualization and analysis.
Quantitative and visual evaluation of t-SNE performance compared to Principal Component Analysis (PCA).

Main Results:

t-SNE effectively extracts non-linear similarity features from ink spectral data.
The two-dimensional data generated by t-SNE provides superior visualization compared to PCA.
t-SNE demonstrates a significant improvement in clustering quality for ink analysis.

Conclusions:

t-SNE is a valuable tool for dimensionality reduction and visualization in hyperspectral ink analysis.
The algorithm offers enhanced data interpretation for forensic document examination.
t-SNE presents a promising alternative to traditional methods like PCA for processing complex HSI data.