Representing Noisy Image Without Denoising
arXiv:2301.07409 · doi:10.1109/TPAMI.2024.3386985
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.
Accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024
References in corpus (12)
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
- FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising
- Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning
- PCANet: A Simple Deep Learning Baseline for Image Classification?
- Domain Generalization: A Survey
- Media Forensics and DeepFakes: an overview
- Solving Inverse Problems With Deep Neural Networks -- Robustness Included?
- A Survey of Orthogonal Moments for Image Representation: Theory, Implementation, and Evaluation
- Bridging the Gap Between Computational Photography and Visual Recognition
- Enhance Visual Recognition under Adverse Conditions via Deep Networks
- A Principled Design of Image Representation: Towards Forensic Tasks
- Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives