Title: Estimation of the structural similarity index for remote sensing data
Authors: Felipe Osorio - Universidad Tecnica Federico Santa Maria (Chile) [presenting]
Ronny Vallejos - Universidad Tecnica Federico Santa Maria (Chile)
Wilson Barraza - U-Planner (Chile)
Silvia Ojeda - Universidad Nacional de Cordoba (Argentina)
Marcos Landi - Universidad Nacional de Cordoba (Argentina)
Abstract: The structural similarity (SSIM) index has been studied from different perspectives in the last decade. Most of the developments consider its parameters fixed. Because each of these parameters corresponds to the weight of a factor in the final SSIM coefficient, the usual assumption that all parameters are equal to one is questionable. A new model-based estimation method is proposed and developed so that, the usual assumption that all parameters are equal to one can be handled via approximate hypothesis-testing techniques that are properly developed in the context of regression. The method considers nonlinear models with multiplicative noise to explain the root mean square error (RMSE) as a function of the SSIM index for two given images that are split into several subimages to generate the samples necessary for the regression models. The nonlinear model is estimated using a pseudo-likelihood approach for which a recursive estimation algorithm is provided. A numerical experiment based on a Monte Carlo simulation is provided to test whether the parameters are all equal to one and to gain more insight into the performance of the estimates in practice.