arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.07409cs.CVeess.IV
收藏

无需去噪的含噪图像表示方法

Representing Noisy Image Without Denoising

College of Information Technology, Jiangxi University of Finance and Economics(江西财经大学信息技术学院);College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics(南京航空航天大学计算机科学与技术学院);College of Computer Science, Chongqing University(重庆大学计算机学院);School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University(中山大学深圳校区网络空间科学与技术学院);Deakin University(迪肯大学)

Shuren Qi, Yushu Zhang, Chao Wang, Tao Xiang, Xiaochun Cao, Yong Xiang

AI总结:

针对现有含噪图像表示方法低效不稳定的问题,提出无需去噪预处理的非学习范式,构建兼具正交性、旋转不变性及时频分析能力的Radon空间分数阶矩FMR,经实验验证其在抗噪等方面的实用性。

摘要:

人工智能领域一个长期存在的课题是从含噪图像中有效识别模式。对此,当前的数据驱动范式主要采用两种思路:一是在训练阶段加入含噪样本以提升表示鲁棒性(即数据增强),二是通过学习求解逆问题对含噪图像进行预处理(即图像去噪)。但这类方法普遍存在过程低效、结果不稳定的问题,限制了其实际应用。本文探索了一种非学习范式,旨在直接从含噪图像中提取鲁棒表示,无需将去噪作为预处理步骤。本文设计的抗噪表示为Radon空间分数阶矩(Fractional-order Moments in Radon space, FMR),该表示还具备正交性和旋转不变性的优良特性。与早期的整数阶方法不同,本工作是更具通用性的设计,可将这类经典方法视为其特例;引入的分数阶参数提供了经典方法不具备的时频分析能力。本文形式化地详细讨论了构建FMR的隐式路径和显式路径。大量仿真实验及一项图像安全应用验证了FMR的独特性和实用性,尤其体现在抗噪性、旋转不变性及时频判别能力方面。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑