Abstract

A crucial aspect of contemporary image processing systems is image denoising. The anisotropic diffusion function is a feature of the partial differential equation employed for the purpose of noise reduction and the preservation of image characteristics such as edges. A new tangent sigmoid diffusion coefficient and a new adaptive threshold parameter have been proposed in this work, which leads to faster convergence. In comparison to traditional anisotropic diffusion model techniques, the proposed technique performs admirably. As evidenced by the results, which demonstrate that the new anisotropic diffusion technique is not only capable of efficiently removing noise, but also of maintaining content in the denoised image. The performance of the proposed method is evaluated using various metrics, including peak signal-to-noise ratio, convergence rate, structural similarity index, time complexity, and space complexity. When comparing the proposed approach to previous methods, it is evident that the proposed method outperforms in various aspects. These include a higher convergence rate (− 0.1278), a greater peak signal-to-noise ratio (37.9827 dB), a higher structural similarity index (0.97432), a lower time complexity (5.72 s), and a smaller space complexity (15.6 KB).

中文翻译：

---

一种基于新颖的正切 sigmoid 各向异性扩散函数的图像去噪快速计算技术

摘要

当代图像处理系统的一个重要方面是图像去噪。各向异性扩散函数是偏微分方程的一个特征，用于降低噪声和保留图像特征（例如边缘）。这项工作提出了一种新的切线 sigmoid 扩散系数和一种新的自适应阈值参数，可以加快收敛速度​​。与传统的各向异性扩散模型技术相比，所提出的技术表现出色。结果表明，新的各向异性扩散技术不仅能够有效去除噪声，而且能够保留去噪图像中的内容。使用各种指标评估所提出方法的性能，包括峰值信噪比、收敛速度、结构相似性指数、时间复杂度和空间复杂度。将所提出的方法与以前的方法进行比较时，很明显，所提出的方法在各个方面都表现出色。其中包括更高的收敛速度（− 0.1278）、更大的峰值信噪比（37.9827 dB）、更高的结构相似性指数（0.97432）、更低的时间复杂度（5.72 s）和更小的空间复杂度（15.6）知识库）。