Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

A Video-Based Measurement Framework for Chewing-Event Detection Using 3D Facial Landmark Dynamics and sEMG-Based Reference Annotation.

Sensors (Basel, Switzerland)·2026
Same author

Measurement of Fracture Networks in Rock Sample by X-Ray Tomography, Convolutional Filtering and Deep Learning.

Sensors (Basel, Switzerland)·2025
Same author

Virtualized Microphone Array for Moving Sources Mapping.

Sensors (Basel, Switzerland)·2025
Same author

Design and Uncertainty Evaluation of a Calibration Setup for Turbine Blades Vibration Measurement.

Sensors (Basel, Switzerland)·2025
Same author

Vision Measurement System for Gender-Based Counting of <i>Acheta domesticus</i>.

Sensors (Basel, Switzerland)·2024
Same author

Facial Expression Recognition for Measuring Jurors' Attention in Acoustic Jury Tests.

Sensors (Basel, Switzerland)·2024

Related Experiment Video

Updated: Aug 25, 2025

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals
07:34

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

Published on: August 22, 2019

8.1K

Correction of Substrate Spectral Distortion in Hyper-Spectral Imaging by Neural Network for Blood Stain

Nicola Giulietti1, Silvia Discepolo2, Paolo Castellini2

  • 1Department of Mechanical Engineering, Politecnico di Milano, 20156 Milano, Italy.

Sensors (Basel, Switzerland)
|October 14, 2022
PubMed
Summary

This study introduces a neural network method to correct bloodstain spectral data distorted by various surfaces. This advances forensic science by enabling accurate blood trace analysis on any material.

Keywords:
blood stainsforensicshyper-spectral imagingneural network

More Related Videos

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters
07:05

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

Published on: June 18, 2021

2.5K
Simultaneous Evaluation of Cerebral Hemodynamics and Light Scattering Properties of the In Vivo Rat Brain Using Multispectral Diffuse Reflectance Imaging
07:06

Simultaneous Evaluation of Cerebral Hemodynamics and Light Scattering Properties of the In Vivo Rat Brain Using Multispectral Diffuse Reflectance Imaging

Published on: May 7, 2017

7.8K

Related Experiment Videos

Last Updated: Aug 25, 2025

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals
07:34

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

Published on: August 22, 2019

8.1K
Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters
07:05

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

Published on: June 18, 2021

2.5K
Simultaneous Evaluation of Cerebral Hemodynamics and Light Scattering Properties of the In Vivo Rat Brain Using Multispectral Diffuse Reflectance Imaging
07:06

Simultaneous Evaluation of Cerebral Hemodynamics and Light Scattering Properties of the In Vivo Rat Brain Using Multispectral Diffuse Reflectance Imaging

Published on: May 7, 2017

7.8K

Area of Science:

  • Forensic Science
  • Biomedical Imaging
  • Spectroscopy

Background:

  • Hyper-spectral imaging is crucial in forensic science for analyzing biological traces.
  • Current bloodstain analysis methods are limited to specific surfaces, hindering real-world applications.
  • Substrate material and color significantly impact spectral analysis of bloodstains.

Purpose of the Study:

  • To develop a novel neural network-based method for correcting blood spectra contaminated by substrate influences.
  • To enable accurate bloodstain analysis across diverse and challenging surfaces in forensic investigations.

Main Methods:

  • Acquisition of hyper-spectral images of bloodstains on 12 different substrates over 12 days.
  • Development and training of a neural network model using the collected spectral data.
  • Implementation of an algorithm to identify blood and correct spectral data against a reference white substrate.

Main Results:

  • The neural network model achieved a mean absolute percentage error of 1.11% in predicting corrected blood spectra.
  • The algorithm successfully identified blood and corrected spectra, compensating for substrate effects.
  • Uncertainty analysis confirmed the accuracy of the predicted reflectance spectra compared to ground truth.

Conclusions:

  • The proposed neural network approach effectively corrects for substrate interference in bloodstain hyper-spectral imaging.
  • This method overcomes limitations of previous techniques, offering a robust solution for forensic bloodstain analysis.
  • The validated technique enhances the reliability and applicability of hyper-spectral imaging in forensic science.