Translator Disclaimer
Presentation + Paper
20 September 2020 Comparison of learning-based and maximum-likelihood estimators of image noise variance for real-life and synthetic anisotropic textures
Author Affiliations +
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.
Conference Presentation
© (2020) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Mykhail Uss, Benoit Vozel, Vladimir Lukin, and Kacem Chehdi "Comparison of learning-based and maximum-likelihood estimators of image noise variance for real-life and synthetic anisotropic textures", Proc. SPIE 11533, Image and Signal Processing for Remote Sensing XXVI, 1153303 (20 September 2020);


SAR image analysis of the sea surface by local fractal...
Proceedings of SPIE (March 13 2003)
Optimal nonlinear fax restoration
Proceedings of SPIE (March 23 1994)
A new type of remote sensors which allow directly forming...
Proceedings of SPIE (October 22 2010)
Autonomous hyperspectral end-member determination methods
Proceedings of SPIE (December 28 1999)
Analysis of system noise in thermal imagers
Proceedings of SPIE (May 16 2003)

Back to Top