Comparison of learning-based and maximum-likelihood estimators of image noise variance for real-life and synthetic anisotropic textures - Université de Rennes Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Comparison of learning-based and maximum-likelihood estimators of image noise variance for real-life and synthetic anisotropic textures

Résumé

Processing of remote sensing data is often based on an assumption that noise parameters in component images are a priori known. If this assumption is not valid, it is desired to perform estimation of noise parameters directly from noisy image patches. In this paper, two estimators - model- and learning-based ones possessing the ability to evaluate noise standard deviation (SD) or variance and to predict estimation accuracy for each image patch are considered. The former approach is the representative of maximum likelihood estimator (MLE) of parameters for anisotropic fractional Brownian motion (afBm) field whilst the learning-based one is the representative of convolutional neural networks (CNN) that employs training on real-life images. Our goal is to compare the performance for two cases: for pure afBm data and for real-life images. It is shown that the learning-based approach occurs to be less effective for pure afBm data since it produces a certain bias whilst the model-based approach runs into problems for complex image patches in reallife images. Based on this analysis, we propose to use synthetic afBm data as additional source of training data for learning-based methods of noise parameters estimation. By mixing real and synthetic data for training of the NoiseNet CNN, we were able to improve its performance in both domains. For afBm data, NoiseNet bias was significantly reduced and ability to predict noise SD estimates confidence improved. On NED2012 database of real images, the modified NoiseNet reduces signal-independent noise SD component estimation error by about 40% as compared to the original CNN version. © SPIE. Downloading of the abstract is permitted for personal use only.
Fichier non déposé

Dates et versions

hal-03003494 , version 1 (13-11-2020)

Identifiants

Citer

M. Uss, B. Vozel, V. Lukin, K. Chehdi. Comparison of learning-based and maximum-likelihood estimators of image noise variance for real-life and synthetic anisotropic textures. Image and Signal Processing for Remote Sensing XXVI 2020, Sep 2020, Edinburgh, United Kingdom. pp.1153303, ⟨10.1117/12.2573934⟩. ⟨hal-03003494⟩
21 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More