Non-parametric and region-based image fusion with Bootstrap sampling

Zribi, Mourad

doi:10.1016/j.inffus.2008.08.004

Cited by 39 publications

(16 citation statements)

References 43 publications

(60 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…During the past two decades, many image fusion methods are developed [1][2][3][4][5][6][7][8][9][10][11][12]. According to the stage at which image information is integrated, image fusion algorithms can be categorized into pixel, feature, and decision levels [1].…”

Section: Introductionmentioning

confidence: 99%

Performance comparison of different multi-resolution transforms for image fusion

2011

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Performance comparison of different multi-resolution transforms for image fusion

2011

View full text Add to dashboard Cite

“…In the other regions, the low-frequency subband coefficients of the panchromatic image should be selected as that of the fused image.That is: T and 3 T are the RRM threshold. 2 T is the RIE threshold.…”

Section: A Despeckle and Segmentation Of The Sar Imagementioning

confidence: 99%

“…While the panchromatic image is more sensitive to the physical and chemical properties of the ground object, which can reflect the contour information of the different object and has high spatial resolution and abundant texture features. Therefore, the SAR and panchromatic image fusion can make full use of the complementary information to obtain multi-level characteristics of the ground object, and has become a research focus in the field of image analysis [1][2][3][4].…”

Section: Introductionmentioning

confidence: 99%

SAR and panchromatic image fusion based on region features in nonsubsampled contourlet transform domain

Zhang

2012

2012 IEEE International Conference on Automation and Logistics

View full text Add to dashboard Cite

Focusing on the fusion of Synthetic Aperture Radar (SAR) and panchromatic images, a novel fusion algorithm based on the imaging characteristic of the SAR image is presented. Two measurements named region information entropy and ratio of region mean are presented in the nonsubsampled contourlet transform (NSCT) domain so that the SAR image can be split into roughness regions, smoothness regions and highlight point target regions. The algorithm performs the different fusion rules for each particular region independently. Experimental results show that the fused image not only joins the target information in the SAR image that is difficult to identify in the panchromatic image but also preserves the spatial resolution of the panchromatic image. The algorithm performs significantly better than the wavelet transform and the pixel-based NSCT.Index Terms -image fusion; nonsubsampled contourlet transform; Region Information Entropy; Ratio of Region Mean.

show abstract

“…Many research efforts have been made to develop an effective multimodal image fusion method in the last decade [7][8][9][10][11]. Among them, multiscale transform-based image fusion techniques have been the most popular because of their simplicity in implementation.…”

Section: Introductionmentioning

confidence: 99%