论文标题
使用傅立叶变换和灰度级别的共发生矩阵对Hadamard矩阵重新排序，以进行压缩单金成像
Re-ordering of Hadamard matrix using Fourier transform and gray-level co-occurrence matrix for compressive single-pixel imaging
论文作者
论文摘要
单金成像中最活跃的研究领域之一是采样基础的影响及其在重建图像质量中的顺序。本文以低采样比（0.5至0.01）的形式提出了哈达玛的基础上的两个新订单，分别是哈达姆基础的上升量表（AS）和上升惯性（AI），并使用模拟和实验方法测试其性能。将这些订单与两个最先进的订单，蛋糕切割（CC）和总梯度（TG）进行了比较，使用TVAL3作为重建算法和三个噪声水平。这些新提出的订单在模拟数据集（110张图像）上具有更好的重建图像质量，并获得了高于CC顺序的结构相似性指数值。实验数据集（2张图像）表明，AS和AI订单的性能更好，采样比为0.5，而对于较低的采样比，AS，AI和CC的性能相似。在大多数情况下，TG订单表现最差。最后，模拟结果提供了明确的证据，表明峰值信噪比（PSNR）不是可靠的图像质量评估（IQA）度量标准，可以在单像素成像的背景下评估图像重建质量。
One of the most active research fields in single-pixel imaging is the influence of the sampling basis and its order in the quality of the reconstructed images. This paper presents two new orders, ascending scale (AS) and ascending inertia (AI), of the Hadamard basis and test their performance, using simulation and experimental methods, for low sampling ratios (0.5 to 0.01). These orders were compared with two state-of-the-art orders, cake-cutting (CC) and total gradient (TG), using TVAL3 as the reconstruction algorithm and three noise levels. These newly proposed orders have better reconstructed image quality on the simulation data set (110 images) and achieved structure similarity index values higher than CC order. The experimental data set (2 images) showed that the AS and AI orders performed better with a sampling ratio of 0.5, while for lower sampling ratio the performance of AS, AI and CC was similar. The TG order performed worst in the majority of the cases. Finally, the simulation results present clear evidence that peak signal-to-noise ratio (PSNR) is not a reliable image quality assessment (IQA) metric to assess image reconstruction quality in the context of single pixel imaging.
