In image-related applications, the recorded images are the blurry version of the original image that usually depicts any scene. Due to the optical aberrations, atmospheric distortions, and motion of objects in the scene, blur occurs in the images and degrades image quality. Various image deblurring methods are modeled in the existing works, but accurately recovering the exact true image from the single recorded image or the set of images still results in challenging medical imaging applications. Thus, an effective image deblurring method named Exponential-Ant Cuckoo Search Optimization (Exponential-ACSO) is developed in this research to find the spatial information from the blurred image. The proposed Exponential-ACSO is designed by integrating the Exponential Weighted Moving Average (EWMA) with Ant Lion Optimization (ALO) and Cuckoo Search (CS) algorithm. The computation of new pixel values for noisy pixels makes the image deblurring process more robust and accurate. The objective function is considered to find the optimal fitness value for the parameters of kernel estimation. However, the proposed Exponential-ACSO showed better performance for the metrics, like peak signal-to-noise ratio (PSNR), second derivative like the measure of enhancement (SDME), and structural similarity index (SSIM) with the values 29.756, 33.562, and 0.6988, respectively.

在与图像相关的应用中，记录的图像是原始图像的模糊版本，通常描绘任何场景。由于场景中的光学像差、大气失真和物体的运动，图像中会出现模糊并降低图像质量。现有工作中对各种图像去模糊方法进行了建模，但从单个记录图像或一组图像中准确恢复准确的真实图像仍然给医学成像应用带来挑战。因此，本研究开发了一种名为指数-蚂蚁布谷鸟搜索优化（Exponential-ACSO）的有效图像去模糊方法，以从模糊图像中找到空间信息。提议的指数-ACSO 是通过将指数加权移动平均 (EWMA) 与 Ant Lion 优化 (ALO) 和布谷鸟搜索 (CS) 算法集成而设计的。噪声像素的新像素值的计算使图像去模糊过程更加稳健和准确。目标函数被认为是寻找核估计参数的最佳适应度值。然而，提议的指数-ACSO 表现出更好的指标性能，如峰值信噪比 (PSNR)、二阶导数，如增强度量 (SDME) 和结构相似性指数 (SSIM)，其值为 29.756、33.562和 0.6988，分别。目标函数被认为是寻找核估计参数的最佳适应度值。然而，提议的指数-ACSO 在指标方面表现出更好的性能，如峰值信噪比 (PSNR)、二阶导数，如增强度量 (SDME) 和结构相似性指数 (SSIM)，其值为 29.756、33.562和 0.6988，分别。目标函数被认为是寻找核估计参数的最佳适应度值。然而，提议的指数-ACSO 在指标方面表现出更好的性能，如峰值信噪比 (PSNR)、二阶导数，如增强度量 (SDME) 和结构相似性指数 (SSIM)，其值为 29.756、33.562和 0.6988，分别。