Representing Noisy Image Without Denoising
This work addresses the challenge of inefficient and unstable methods for noisy image recognition, offering a more generic design that could benefit applications like image security, though it appears incremental as it builds on classical integer-order methods.
The paper tackles the problem of recognizing patterns from noisy images by proposing a non-learning paradigm that derives robust representations directly from noisy images without denoising, resulting in a method called Fractional-order Moments in Radon space (FMR) that demonstrates noise robustness, rotation invariance, and time-frequency discriminability in simulations and an image security application.
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.