Image Frame Fusion using 3D Anisotropic Diffusion

被引：0

作者：

Kahraman, Fatih ^{[1
]}

Mendi, C. Deniz ^{[1
]}

Gokmen, Muhittin ^{[2
]}

机构：

[1] TUBITAK Marmara Res Ctr, Inst Informat, Kocaeli, Turkey

[2] ITU Comp Engn Dept, TR-34469 Istanbul, Turkey

来源：

23RD INTERNATIONAL SYMPOSIUM ON COMPUTER AND INFORMATION SCIENCES | 2008年

关键词：

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper, a modified 3D anisotropic diffusion method is proposed to improve the multi-frame image fusion performance. Multi frame image sequence is considered to be composed of aligned and warped images. The goal of this approach is to obtain a restored image from the aligned and warped image sequence, where alignment error and Gaussian noise are reduced. The proposed method consists of medium band stack filter and tree-structured 3D diffusion filter.

引用

页码：605 / +

页数：2

共 10 条

[1]

[Anonymous], IEEE C COMP VIS PATT

[2] NOISE-REDUCTION IN IMAGE SEQUENCES USING MOTION-COMPENSATED TEMPORAL FILTERING [J].

DUBOIS, E ;

SABRI, S .

IEEE TRANSACTIONS ON COMMUNICATIONS, 1984, 32 (07) :826-831

[3] A review of image-warping methods [J].

Glasbey, CA ;

Mardia, KV .

JOURNAL OF APPLIED STATISTICS, 1998, 25 (02) :155-171

[4]

GUNTURK BK, 2003, P IEEE INT C IM PROC, V2, P319

[5]

*INTEL, 2007, INTEL WHIT PAP

[6] Multiframe selective information fusion from robust error estimation theory [J].

John, S ;

Vorontsov, MA .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2005, 14 (05) :577-584

[7] Efficient multiframe Wiener restoration of blurred and noisy image sequences [J].

Oezkan, Mehmet K. ;

Erdem, A. Tanju ;

Sezan, M. Ibrahim ;

Tekalp, A. Murat .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 1992, 1 (04) :453-476

[8] FAME - A flexible appearance modeling environment [J].

Stegmann, MB ;

Ersboll, BK ;

Larsen, R .

IEEE TRANSACTIONS ON MEDICAL IMAGING, 2003, 22 (10) :1319-1331

[9]

THOMAS D, 2007, P IEEE WORKSH MOT VI, P19

[10]

Wheeler F., 2007, P IEEE C BIOM THEOR, P27

← 1 →