Being able to determine the age of a bloodstain can be a key element in a crime scene investigation. Many techniques exploit reflectance spectroscopy because it is very versatile and can be used in the field with ease. However, there are no methods for estimating bloodstain age with adequate uncertainty, and the problem of substrate influence is not yet fully resolved. We develop a hyperspectral imaging based tech-nique for the substrate-independent age estimation of a bloodstain. Once the hyperspectral image is ac-quired, a neural network model recognizes the pixels belonging to the bloodstain. The reflectance spectra belonging to the bloodstain are then processed by an artificial intelligence model that removes the effect of the substrate on the bloodstain and then estimates its age. The method is trained on bloodstains deposited on 9 different substrates over a time period of 0-385 h obtaining an absolute mean error of 6.9 h over the period considered. Within two days of age, the method achieves a mean absolute error of 1.1 h. The method is finally tested on a new material (i.e., red cardboard) never used to test or validate the neural network models. Also in this case the bloodstain age is identified with the same accuracy.

Neural network based hyperspectral imaging for substrate independent bloodstain age estimation / Giulietti, Nicola; Discepolo, Silvia; Castellini, Paolo; Martarelli, Milena. - In: FORENSIC SCIENCE INTERNATIONAL. - ISSN 0379-0738. - 349:(2023). [10.1016/j.forsciint.2023.111742]

Neural network based hyperspectral imaging for substrate independent bloodstain age estimation

Discepolo, Silvia;Castellini, Paolo;Martarelli, Milena
2023-01-01

Abstract

Being able to determine the age of a bloodstain can be a key element in a crime scene investigation. Many techniques exploit reflectance spectroscopy because it is very versatile and can be used in the field with ease. However, there are no methods for estimating bloodstain age with adequate uncertainty, and the problem of substrate influence is not yet fully resolved. We develop a hyperspectral imaging based tech-nique for the substrate-independent age estimation of a bloodstain. Once the hyperspectral image is ac-quired, a neural network model recognizes the pixels belonging to the bloodstain. The reflectance spectra belonging to the bloodstain are then processed by an artificial intelligence model that removes the effect of the substrate on the bloodstain and then estimates its age. The method is trained on bloodstains deposited on 9 different substrates over a time period of 0-385 h obtaining an absolute mean error of 6.9 h over the period considered. Within two days of age, the method achieves a mean absolute error of 1.1 h. The method is finally tested on a new material (i.e., red cardboard) never used to test or validate the neural network models. Also in this case the bloodstain age is identified with the same accuracy.
2023
File in questo prodotto:
File Dimensione Formato  
Giulietti_Neural-network-based-hyperspectral-imaging_2023.pdf

Solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza d'uso: Tutti i diritti riservati
Dimensione 4.04 MB
Formato Adobe PDF
4.04 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Giulietti_Neural-network-based-hyperspectral-imaging_Post-print.pdf

Open Access dal 02/06/2024

Tipologia: Documento in post-print (versione successiva alla peer review e accettata per la pubblicazione)
Licenza d'uso: Creative commons
Dimensione 5.54 MB
Formato Adobe PDF
5.54 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11566/328299
Citazioni
  • ???jsp.display-item.citation.pmc??? 0
  • Scopus 5
  • ???jsp.display-item.citation.isi??? 5
social impact