Source Identification for Printed Documents

Min Jen Tsai; Mam Yuadi; Yu Han Tao; Jin Sheng Yin

doi:10.1109/CIC.2017.00019

Source Identification for Printed Documents

Min Jen Tsai, Mam Yuadi, Yu Han Tao, Jin Sheng Yin

Information Science and Library

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

7 Citations (Scopus)

Abstract

Technological advances in digitization with a variety of image manipulation techniques enable the creation of printed documents illegally. Correspondingly, many researchers conduct studies in determining whether the document printed counterfeit or original. This study examines the several statistical feature sets from Gray Level Co-occurrence Matrix (GLCM), Discrete Wavelet Transform (DWT), Spatial filters, Wiener filter, Gabor filter, Haralick and fractal filters to identify text and image document by using support vector machine (SVM) and decision fusion of feature selection. The average experimental results achieves that the image document is higher identification rate than text document. In summary, the proposed method outperforms the previous researches and it is a promising technique that can be implemented in real forensics for printed documents.

Original language	English
Title of host publication	Proceedings - 2017 IEEE 3rd International Conference on Collaboration and Internet Computing, CIC 2017
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	54-58
Number of pages	5
ISBN (Electronic)	9781538625651
DOIs	https://doi.org/10.1109/CIC.2017.00019
Publication status	Published - 9 Dec 2017
Event	3rd IEEE International Conference on Collaboration and Internet Computing, CIC 2017 - San Jose, United States Duration: 15 Oct 2017 → 17 Oct 2017

Publication series

Name	Proceedings - 2017 IEEE 3rd International Conference on Collaboration and Internet Computing, CIC 2017
Volume	2017-January

Conference

Conference	3rd IEEE International Conference on Collaboration and Internet Computing, CIC 2017
Country/Territory	United States
City	San Jose
Period	15/10/17 → 17/10/17

Keywords

Discrete Wavelet Transform (DWT)
Forensics
Fractal Filter
Gabor Filter
GLCM
Haralick Filter
Spatial Filter
Support Vector Machines (SVM)
Wiener Filter

Access to Document

10.1109/CIC.2017.00019

Cite this

Tsai, M. J., Yuadi, M., Tao, Y. H., & Yin, J. S. (2017). Source Identification for Printed Documents. In Proceedings - 2017 IEEE 3rd International Conference on Collaboration and Internet Computing, CIC 2017 (pp. 54-58). (Proceedings - 2017 IEEE 3rd International Conference on Collaboration and Internet Computing, CIC 2017; Vol. 2017-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CIC.2017.00019

Tsai, Min Jen ; Yuadi, Mam ; Tao, Yu Han et al. / Source Identification for Printed Documents. Proceedings - 2017 IEEE 3rd International Conference on Collaboration and Internet Computing, CIC 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 54-58 (Proceedings - 2017 IEEE 3rd International Conference on Collaboration and Internet Computing, CIC 2017).

@inproceedings{00ccd2098e1245418b7abc8b52399e46,

title = "Source Identification for Printed Documents",

abstract = "Technological advances in digitization with a variety of image manipulation techniques enable the creation of printed documents illegally. Correspondingly, many researchers conduct studies in determining whether the document printed counterfeit or original. This study examines the several statistical feature sets from Gray Level Co-occurrence Matrix (GLCM), Discrete Wavelet Transform (DWT), Spatial filters, Wiener filter, Gabor filter, Haralick and fractal filters to identify text and image document by using support vector machine (SVM) and decision fusion of feature selection. The average experimental results achieves that the image document is higher identification rate than text document. In summary, the proposed method outperforms the previous researches and it is a promising technique that can be implemented in real forensics for printed documents.",

keywords = "Discrete Wavelet Transform (DWT), Forensics, Fractal Filter, Gabor Filter, GLCM, Haralick Filter, Spatial Filter, Support Vector Machines (SVM), Wiener Filter",

author = "Tsai, {Min Jen} and Mam Yuadi and Tao, {Yu Han} and Yin, {Jin Sheng}",

note = "Funding Information: * This work was partially supported by the National Science Council in Taiwan, Republic of China, under Grant MOST 104-2410-H-009 -020 -MY2 and MOST 106-2410-H-009 -022. Publisher Copyright: {\textcopyright} 2017 IEEE.; 3rd IEEE International Conference on Collaboration and Internet Computing, CIC 2017 ; Conference date: 15-10-2017 Through 17-10-2017",

year = "2017",

month = dec,

day = "9",

doi = "10.1109/CIC.2017.00019",

language = "English",

series = "Proceedings - 2017 IEEE 3rd International Conference on Collaboration and Internet Computing, CIC 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "54--58",

booktitle = "Proceedings - 2017 IEEE 3rd International Conference on Collaboration and Internet Computing, CIC 2017",

address = "United States",

}

Tsai, MJ, Yuadi, M, Tao, YH & Yin, JS 2017, Source Identification for Printed Documents. in Proceedings - 2017 IEEE 3rd International Conference on Collaboration and Internet Computing, CIC 2017. Proceedings - 2017 IEEE 3rd International Conference on Collaboration and Internet Computing, CIC 2017, vol. 2017-January, Institute of Electrical and Electronics Engineers Inc., pp. 54-58, 3rd IEEE International Conference on Collaboration and Internet Computing, CIC 2017, San Jose, United States, 15/10/17. https://doi.org/10.1109/CIC.2017.00019

Source Identification for Printed Documents. / Tsai, Min Jen; Yuadi, Mam; Tao, Yu Han et al.
Proceedings - 2017 IEEE 3rd International Conference on Collaboration and Internet Computing, CIC 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 54-58 (Proceedings - 2017 IEEE 3rd International Conference on Collaboration and Internet Computing, CIC 2017; Vol. 2017-January).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Source Identification for Printed Documents

AU - Tsai, Min Jen

AU - Yuadi, Mam

AU - Tao, Yu Han

AU - Yin, Jin Sheng

N1 - Funding Information: * This work was partially supported by the National Science Council in Taiwan, Republic of China, under Grant MOST 104-2410-H-009 -020 -MY2 and MOST 106-2410-H-009 -022. Publisher Copyright: © 2017 IEEE.

PY - 2017/12/9

Y1 - 2017/12/9

N2 - Technological advances in digitization with a variety of image manipulation techniques enable the creation of printed documents illegally. Correspondingly, many researchers conduct studies in determining whether the document printed counterfeit or original. This study examines the several statistical feature sets from Gray Level Co-occurrence Matrix (GLCM), Discrete Wavelet Transform (DWT), Spatial filters, Wiener filter, Gabor filter, Haralick and fractal filters to identify text and image document by using support vector machine (SVM) and decision fusion of feature selection. The average experimental results achieves that the image document is higher identification rate than text document. In summary, the proposed method outperforms the previous researches and it is a promising technique that can be implemented in real forensics for printed documents.

AB - Technological advances in digitization with a variety of image manipulation techniques enable the creation of printed documents illegally. Correspondingly, many researchers conduct studies in determining whether the document printed counterfeit or original. This study examines the several statistical feature sets from Gray Level Co-occurrence Matrix (GLCM), Discrete Wavelet Transform (DWT), Spatial filters, Wiener filter, Gabor filter, Haralick and fractal filters to identify text and image document by using support vector machine (SVM) and decision fusion of feature selection. The average experimental results achieves that the image document is higher identification rate than text document. In summary, the proposed method outperforms the previous researches and it is a promising technique that can be implemented in real forensics for printed documents.

KW - Discrete Wavelet Transform (DWT)

KW - Forensics

KW - Fractal Filter

KW - Gabor Filter

KW - GLCM

KW - Haralick Filter

KW - Spatial Filter

KW - Support Vector Machines (SVM)

KW - Wiener Filter

UR - http://www.scopus.com/inward/record.url?scp=85046690695&partnerID=8YFLogxK

U2 - 10.1109/CIC.2017.00019

DO - 10.1109/CIC.2017.00019

M3 - Conference contribution

AN - SCOPUS:85046690695

T3 - Proceedings - 2017 IEEE 3rd International Conference on Collaboration and Internet Computing, CIC 2017

SP - 54

EP - 58

BT - Proceedings - 2017 IEEE 3rd International Conference on Collaboration and Internet Computing, CIC 2017

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 3rd IEEE International Conference on Collaboration and Internet Computing, CIC 2017

Y2 - 15 October 2017 through 17 October 2017

ER -

Tsai MJ, Yuadi M, Tao YH, Yin JS. Source Identification for Printed Documents. In Proceedings - 2017 IEEE 3rd International Conference on Collaboration and Internet Computing, CIC 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 54-58. (Proceedings - 2017 IEEE 3rd International Conference on Collaboration and Internet Computing, CIC 2017). doi: 10.1109/CIC.2017.00019

Source Identification for Printed Documents

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this