An image-processing methodology for extracting bloodstain pattern features

Highlights • An image-processing methodology for analysing bloodstain patterns is proposed. • Local and global features based on traditional spatter properties were extracted. • Quantitative pattern data will enhance current bloodstain pattern taxonomies. • Pattern data will enable analysts to reach...

Full description

Saved in:
Bibliographic Details
Published inForensic science international Vol. 277; pp. 122 - 132
Main Authors Arthur, Ravishka M, Humburg, Philomena J, Hoogenboom, Jerry, Baiker, Martin, Taylor, Michael C, Bruin, Karla G.de
Format Journal Article
LanguageEnglish
Published Ireland Elsevier B.V 01.08.2017
Elsevier Limited
Subjects
Animals
Blood
Blood Stains
Bloodstain Pattern Analysis
Classification
Data processing
Feature extraction
Forensic engineering
Forensic science
Forensic sciences
Forensic Sciences - methods
Global features
Humans
Identification methods
Image processing
Image Processing, Computer-Assisted - methods
Local features
Methods
Neural networks
Numerical methods
Pathology
Pattern recognition
Stains & staining
Statistics as Topic
Taxonomy
Vocabularies & taxonomies
Bloodstain Pattern Analysis
Local Features
Forensic Science
Image-processing
Classification
Global Features
Global features
Local features
Forensic science
Online AccessGet full text

Cover

More Information
Summary:Highlights • An image-processing methodology for analysing bloodstain patterns is proposed. • Local and global features based on traditional spatter properties were extracted. • Quantitative pattern data will enhance current bloodstain pattern taxonomies. • Pattern data will enable analysts to reach objective pattern conclusions. • This study lays the groundwork for an automated pattern classification system.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0379-0738
1872-6283
DOI:10.1016/j.forsciint.2017.05.022