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

Homocysteine and thyroid diseases.

Frontiers in endocrinology·2025

Same author

Association of creatinine level with neurodegenerative disorders: a prospective cohort study and Mendelian randomization analysis.

Neurological sciences : official journal of the Italian Neurological Society and of the Italian Society of Clinical Neurophysiology·2025

Same author

Valorization of tea (Camellia sinensis) waste: Extraction of bioactive compounds using ionic liquids and evaluation of their stability, efficiency, and volatile profiles during the process.

Food chemistry·2025

Same author

Metagenomic analysis reveals Bacillus cereus OTU8977 as a potential probiotic in promoting walnut growth.

BMC plant biology·2025

Same author

GBA1 Haplotypes and Age at Onset of Parkinson's Disease in the Asian Population.

Movement disorders : official journal of the Movement Disorder Society·2025

Same author

Validation of Genome-Wide Association Study (GWAS)-Identified Risk Loci for Parkinson's Disease in the Chinese Population.

Movement disorders : official journal of the Movement Disorder Society·2025

Search research articles

Related Experiment Video

Updated: Oct 17, 2025

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

Classification modeling method for hyperspectral stamp-pad ink data based on one-dimensional convolutional neural

Shuyue Wang¹, Hongyuan He¹, Rulin Lv¹

¹School of Criminal Investigation, People's Public Security, University of China, Beijing, China.

Journal of Forensic Sciences

|October 7, 2021

Summary

This study introduces a novel method for identifying stamp-pad inks using hyperspectral imaging (HSI) and deep learning. The one-dimensional convolutional neural network (1D-CNN) achieved high accuracy, offering a rapid, non-destructive forensic tool.

Keywords:

1D-CNN BPNN HIS NMF PCA back propagation neural network classification hyperspectral imaging non-negative matrix factorization one-dimensional convolutional neural network principal component analysis stamp-pad ink

More Related Videos

Classification of Neural Stem Cell Activation State In Vitro using Autofluorescence

Classification of Neural Stem Cell Activation State In Vitro using Autofluorescence

Published on: April 12, 2024

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

Related Experiment Videos

Last Updated: Oct 17, 2025

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

Classification of Neural Stem Cell Activation State In Vitro using Autofluorescence

Classification of Neural Stem Cell Activation State In Vitro using Autofluorescence

Published on: April 12, 2024

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

Area of Science:

Forensic Science
Analytical Chemistry
Computer Vision

Background:

Document examination relies heavily on analyzing stamp-pad inks to distinguish genuine from forged items.
Traditional methods for ink analysis can be time-consuming and may involve destructive techniques.

Purpose of the Study:

To develop a rapid, non-destructive method for identifying and classifying stamp-pad inks.
To evaluate the effectiveness of hyperspectral imaging (HSI) combined with deep learning algorithms for ink analysis.

Main Methods:

Collected and tested twenty different stamp-pad inks on A4 paper.
Acquired hyperspectral images and processed spectral data.
Compared back propagation neural network (BPNN) and one-dimensional convolutional neural network (1D-CNN) for classification.

Main Results:

The 1D-CNN model demonstrated superior performance over BPNN.
1D-CNN achieved high classification accuracy (98.30% training, 97.94% validation) with low loss.
HSI combined with 1D-CNN proved effective for stamp-pad ink detection.

Conclusions:

Hyperspectral imaging technology coupled with 1D-CNN offers a simple, rapid, and non-destructive approach for stamp-pad ink analysis.
This method has significant potential for forensic document examination.
The developed technique enhances the ability to authenticate documents based on ink characteristics.