On the roles of PCA and ICA in data fusion

Chen, C.H.; Zhang, Xiaohui

doi:10.1109/igarss.2000.859660

Cited by 6 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our previous preliminary results on SAR and hyperspectral images were reported at several conferences [15,16,17]. Harold Szu used ICA to reduce boundary error with multiple-label-remote-sensing (MLRS) [18].…”

Section: Introductionmentioning

confidence: 98%

<title>New independent component analysis (ICA) method and its application to remote sensing images</title>

Zhang

Chen

2002

SPIE Proceedings

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 98%

<title>New independent component analysis (ICA) method and its application to remote sensing images</title>

Zhang

Chen

2002

SPIE Proceedings

View full text Add to dashboard Cite

show abstract

“…The fusion consists then in selecting the main coefficient of the sensor images, with certain criteria, and constructing a fused image in the transform domain, and finally make the inverse transform to obtain the resulting fused image. • Image fusion after principal or independent component analysis: When the number of images to fusion becomes more important ͑hyper spectral images͒ it may be necessary to extract the principal ͓principal component analysis ͑PCA͒ 11 ͔ or independent ͓inde-pendent component analysis ͑ICA͒ 12,13 ͔ components first and then use image fusion techniques on these components. • Probabilistic model-based approach: This type of approach consists of introducing a model that represents a relationship between the observed images and the source images or some particular features of them.…”

Section: Introductionmentioning

confidence: 99%

Image fusion and unsupervised joint segmentation using a HMM and MCMC algorithms

Féron

Mohammad-Djafari

2005

J. Electron. Imaging

View full text Add to dashboard Cite

In this paper we propose a Bayesian framework for unsupervised image fusion and joint segmentation. More specifically we consider the case where we have observed images of the same object through different imaging processes or through different spectral bands (multi-or hyperspectral images). The objective of this work is then to propose a coherent approach to combine these images and obtain a joint segmentation which can be considered as the fusion result of these observations. The proposed approach is based on a hidden Markov modeling of the images where the hidden variables represent the common classification or segmentation labels. These label variables are modeled by the Potts Markov random field. We propose two particular models for the pixels in each segment (iid. or Markovian) and develop appropriate Markov chain Monte Carlo algorithms for their implementations. Finally we present some simulation results to show the relative performances of these models and mention the potential applications of the proposed methods in medical imaging and survey and security imaging systems.

show abstract