Author:
Lakhal Samy,Darmon Alexandre,Mastromatteo Iacopo,Marsili Matteo,Benzaquen Michael
Abstract
AbstractWe use an agnostic information-theoretic approach to investigate the statistical properties of natural images. We introduce the Multiscale Relevance (MSR) measure to assess the robustness of images to compression at all scales. Starting in a controlled environment, we characterize the MSR of synthetic random textures as function of image roughness $$\text{ H }$$
H
and other relevant parameters. We then extend the analysis to natural images and find striking similarities with critical ($$\text {H}\approx 0$$
H
≈
0
) random textures. We show that the MSR is more robust and informative of image content than classical methods such as power spectrum analysis. Finally, we confront the MSR to classical measures for the calibration of common procedures such as color mapping and denoising. Overall, the MSR approach appears to be a good candidate for advanced image analysis and image processing, while providing a good level of physical interpretability.
Publisher
Springer Science and Business Media LLC
Reference52 articles.
1. Krizhevsky, A., Sutskever, I. & Hinton, G. E. Imagenet classification with deep convolutional neural networks. Commun. ACM 60, 84 (2017).
2. LeCun, Y., Bottou, L., Bengio, Y. & Haffner, P. Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278 (1998).
3. Vaswani, A. et al. Attention is all you need Adv. Neural Inf. Process. Syst. 30 (2017).
4. Krizhevsky, A. Learning multiple layers of features from tiny images Department of Computer Science, University of Toronto (2009).
5. Deng, J. et al. Imagenet: A large-scale hierarchical image database IEEE Conf. Comput. Vis. Pattern Recognit. 248 (2009).