Representing Noisy Image Without Denoising

TL;DR

This paper introduces a novel non-learning approach using Fractional-order Moments in Radon space (FMR) to robustly recognize noisy images without denoising, improving stability and efficiency over traditional methods.

Contribution

It proposes a new fractional-order moment method in Radon space that enhances noise robustness, rotation invariance, and time-frequency analysis capabilities, extending classical integer-order techniques.

Findings

FMR demonstrates superior noise robustness in experiments.

The method achieves rotation invariance and discriminability.

Applications include image security with improved stability.

Abstract

A long-standing topic in artificial intelligence is the effective recognition of patterns from noisy images. In this regard, the recent data-driven paradigm considers 1) improving the representation robustness by adding noisy samples in training phase (i.e., data augmentation) or 2) pre-processing the noisy image by learning to solve the inverse problem (i.e., image denoising). However, such methods generally exhibit inefficient process and unstable result, limiting their practical applications. In this paper, we explore a non-learning paradigm that aims to derive robust representation directly from noisy images, without the denoising as pre-processing. Here, the noise-robust representation is designed as Fractional-order Moments in Radon space (FMR), with also beneficial properties of orthogonality and rotation invariance. Unlike earlier integer-order methods, our work is a more generic design taking such classical methods as special cases, and the introduced fractional-order parameter offers time-frequency analysis capability that is not available in classical methods. Formally, both implicit and explicit paths for constructing the FMR are discussed in detail. Extensive simulation experiments and an image security application are provided to demonstrate the uniqueness and usefulness of our FMR, especially for noise robustness, rotation invariance, and time-frequency discriminability.