Bootstrap approach and Stochastic EM algorithm combination applied for the improvement of the multisourceand multi-sensor image fusion process; was presented in this research. Improvement concerned not only image quality andreducing processing execution time as mentioned in our previous Bootstrap EM algorithm (BEM), but also regarding initializationdependence as well as fixed classes’ number. Such interesting fusion algorithm for multisource and multisensorimage using one stochastic phase, i.e. SEM algorithm, preceded by Bootstrap procedure was successfully implementedand tested for several prototype images. Targeted images were firstly split by an unsupervised Bayesian segmentationapproach in order to determine a joint region map for the fused image. The Bootstrap approach was then applied tothe targeted multisource image in conjunction with the SEM algorithm, forming hence one Bootstrap SEM algorithmcalled BSEM. The procedure of such algorithm involved both statistical parameters’ estimation from one representativeBootstrap sample of each source or sensor images.
展开▼