Laser printer attribution: Exploring new features and beyond

Highlights • A multidirectional GLCM technique is proposed for printer attribution. • A multidirectional/multiscale GLCM extension is proposed. • A convolutional gradient texture filter is introduced. • Realistic dataset, comprising 1000+ Wikipedia documents is proposed for evaluation. • Comparison...

Full description

Saved in:
Bibliographic Details
Published inForensic science international Vol. 247; pp. 105 - 125
Main Authors Ferreira, Anselmo, Navarro, Luiz C, Pinheiro, Giuliano, Santos, Jefersson A. dos, Rocha, Anderson
Format Journal Article
LanguageEnglish
Published Ireland Elsevier Ireland Ltd 01.02.2015
Elsevier Limited
Subjects
Banding
Classification
Entropy
Forensic science
Forensic sciences
Laser printers
Lasers
Letters
Methods
Pathology
Printer forensics
Printers
Reproduction
Scanning
Segments
Signatures
Surface layer
Texture
Texture patterns
Printer forensics
Banding
Texture patterns
Online AccessGet full text

Cover

More Information
Summary:Highlights • A multidirectional GLCM technique is proposed for printer attribution. • A multidirectional/multiscale GLCM extension is proposed. • A convolutional gradient texture filter is introduced. • Realistic dataset, comprising 1000+ Wikipedia documents is proposed for evaluation. • Comparison to other techniques and other general-purpose descriptors is performed.
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.2014.11.030