The algorithm of zero-order Gaussian filtering for an open profile (GFO) was used to correct the edge of the filtered image.
并且利用零阶开环高斯滤波算法，对低通滤波图像的边缘进行了修正。
The experiment shows that the new method is more efficient and easier to realize than the conventional Gaussian filtering methods.
实验表明，与传统的高斯滤波方法相比，新方法算法简单，计算效率高，且易于实现。
Robust statistics is introduced to enhance the robustness of Gaussian filtering. Several selected robust weight functions are adopted and compared.
引入稳健统计学的思想，对高斯滤波进行了稳健处理，并比较了几种稳健估计权函数对高斯滤波性能的改进。
In Chapter 2, we present nonlinear filtration theory, and find out the nonlinear conditional Gaussian filtering estimation under one dim and multi dims.
第二章引入非线性滤波理论，给出一类关于条件高斯过程的一维和多维非线性滤波估计。
Taking the surface profile signal as an example, it analyzes the influence of outliers on the performance of Gaussian filtering with the help of the illustrations and evaluation parameters.
以表面轮廓信号为例，结合图形和参数评估，研究了异常信号对高斯滤波性能的影响。
Experiments show that his method overcomes the defect of blocky effect in mean shift filtering, and is superior to mean shift filtering, Gaussian scale space filtering and median filter.
该方法克服了均值漂移滤波存在块状效应的缺点。实验结果表明，该方法的整体性能优于均值漂移滤波、高斯滤波和中值滤波。
Another applied in filtering signal containing Gaussian white noise is computed directly by utilizing time-frequency spectrum of GST, which can enhance non-stationary signal and suppress noise.
后者直接应用广义s变换的时频谱实现，用于含高斯白噪声信号的滤波，达到了突出有效信号和压制噪声的效果。
We give the basic theory of frequency filtering. In the frequency domain, the work focuses on the adaptive Gaussian frequency filter.
给出了频域滤波的基本原理，重点研究了自适应高斯频域滤波器这一频域滤波算法。
Following that the Gaussian noises are filtered out by symmetrical-neighbor mean filtering.
其次滤除受高斯噪声污染的像素点，采用对称近邻均值滤波算法。
The particle filtering is a nonlinear filtering technology, which is suitable for the nonlinear system and non-Gaussian noise model.
粒子滤波技术是近几年出现的一种非线性滤波技术，它适用于非线性系统以及非高斯噪声模型。
In HF channel modeling, doppler spread effects are usually simulated by filtering white Gaussian noise. The signal correlation in time domain deviates far from the theoretical value.
在短波信道建模中，通常采用对高斯白噪声滤波来仿真多普勒扩展效应，这些模型的时域相关值与理论值相差较大。
This paper used Gaussian function as point spread function, applying in inverse filtering algorithm and Wiener filtering algorithm and improving them.
对模糊的成像结果进行图像复原，采用高斯函数作为点扩展函数，应用于三维逆滤波和维纳滤波算法中，改进了这两种算法。
The main tasks are as follows:(1) According to experiment and analyzing of several common filtering methods, median filter method and Gaussian filter method were improved in this paper.
主要工作如下：（1）通过几种常见滤波方法的实验与分析，改进了中值滤波法和高斯滤波法。
It could be directly applied to the nonlinear model of the initial system, and could get good filtering result whether the system noise or measured noise was Gaussian or not.
该算法可以直接应用于原系统的非线性模型当中，并且不需考虑系统噪声和量测噪声是否为高斯白噪声，都能得到很好的滤波效果。
In moving base transfer alignment under nonlinear and non-Gaussian situation, using Kalman Filtering could cause large error or even divergence.
在非线性、非高斯条件下进行动基座传递对准，如果采用卡尔曼滤波会出现误差较大甚至发散的问题。
In moving base transfer alignment under nonlinear and non-Gaussian situation, using Kalman Filtering could cause large error or even divergence.
在非线性、非高斯条件下进行动基座传递对准，如果采用卡尔曼滤波会出现误差较大甚至发散的问题。
应用推荐