Image based source camera identification using demosaicking

被引：92

作者：

Long, Yangjing ^{[1
]}

Huang, Yizhen ^{[2
]}

机构：

[1] Shanghai Jiao Tong Univ, Sch Sci, Dept Math, Shanghai 200240, Peoples R China

[2] Shanghai Jiao Tong Univ, Dept Comp Sci & Engn, Sch Elect Informat & Elect Eneg, Shanghai 200030, Peoples R China

来源：

2006 IEEE WORKSHOP ON MULTIMEDIA SIGNAL PROCESSING | 2006年

关键词：

back propagation networks; principal components analysis; source camera identification;

D O I：

10.1109/MMSP.2006.285343

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We represent the spatially periodic inter-pixel correlation due to color filter array interpolation in a quadratic form. Based on this, a coefficient matrix is obtained for each color channel, whose principal components are extracted and fed to feed-forward Back Propagation networks for source camera identification. Experiments demonstrate the efficacy, sensitivity and robustness of our method.

引用

页码：419 / +

页数：3

共 15 条

[1]

Bayer B.E., 1976, U.S. Patent, Patent No. 3971065

[2]

BOYKOV Y, P ICCV 2001, P105

[3]

CHANG E, 1999, SPIE, V3650, P36

[4]

CHUANG YY, P CVPR 2001, P264

[5]

COK DR, 1986, Patent No. 4642678

[6]

FREED LA, 1988, NATL GEOGR RES, V4, P395

[7]

Geradts ZJ, 2000, PROC SPIE, V4232, P505, DOI 10.1117/12.417569

[8] Demosaicking: Color filter array interpolation [J].

Gunturk, BK ;

Glotzbach, J ;

Altunbasak, Y ;

Schafer, RW ;

Mersereau, RM .

IEEE SIGNAL PROCESSING MAGAZINE, 2005, 22 (01) :44-54

[9] Color plane interpolation using alternating projections [J].

Gunturk, BK ;

Altunbasak, Y ;

Mersereau, RM .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2002, 11 (09) :997-1013

[10]

KHARRAZI M, P ICPC 2004, P709

← 1 2 →