Premium
Rapid Localization of Bone Fragments on Surfaces using Back‐Projection and Hyperspectral Imaging
Author(s) -
Alsberg Bjørn K.,
Rosvold Jørgen
Publication year - 2014
Publication title -
journal of forensic sciences
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.715
H-Index - 96
eISSN - 1556-4029
pISSN - 0022-1198
DOI - 10.1111/1556-4029.12319
Subject(s) - hyperspectral imaging , artificial intelligence , partial least squares regression , projection (relational algebra) , linear discriminant analysis , pattern recognition (psychology) , computer vision , computer science , discriminant , geology , mathematics , machine learning , algorithm
Manual localization of bone fragments on the ground or on complex surfaces in relation to accidents or criminal activity may be time‐consuming and challenging. It is here investigated whether combining a near‐infrared hyperspectral camera and chemometric modeling with false color back‐projection can be used for rapid localization of bone fragments. The approach is noninvasive and highlights the spatial distribution of various compounds/properties to facilitate manual inspection of surfaces. Discriminant partial least squares regression is used to classify between bone and nonbone spectra from the hyperspectral camera. A predictive model (>95% prediction ability) is constructed from raw chicken bones mixed with stone, sand, leaves, moss, and wood. The model uses features in the near‐infrared spectrum which may be selective for bones in general and is able to identify a wide variety of bones from different animals and contexts, including aged and weathered bone.