该方法由特征估计和多尺度滤波两部分组成。
The method is composed of feature estimation and multi-scale smoothing.
基于人眼视觉机理启发，提出了一种新的多尺度滤波模板构造方法。
Secondly, a novel approach is proposed based on a mechanism of human vision model.
基于EMD时间尺度滤波特性，在引入相关度分析的基础上提出了EMD相关度去噪方法。
Based on the idea of the correlation degree and the EMD (Empirical Mode Decompositon) time scale filtering, the EMD de-noising method based on the correlation degree is proposed.
基于正交二进小波，设计了一个滤波器对图象进行多尺度滤波，得到不同尺度的小波变换。
A filter based on orthonormal wavelet bases is designed to do wavelet transform with images. Different scale image edges can be detected form different scale image wavelet transform.
首先根据原始图像直方图的尺度空间特性和多尺度滤波结果，选取最佳阈值将图像分为多个类。
Firstly, according to the properties of the histogram scale space of an original image and the result of the multiscale filtering, optimal thresholds were determined for classifying the cells image.
本文研究尺度滤波器的基本分解问题。基于所得结果，对于任意给定的尺度滤波器，给出了双正交小波矩阵的构造方案。
In this paper, the factorization of scaling vector filters into prime factors is considered. A construction of bi-orthogonal wavelet matrix with pre-asigned scaling filter is given.
为了满足局部放电在线监测的在线准实时要求，提出了改进的尺度空间滤波算法，并将其应用于局部放电脉冲的提取。
In order to satisfy the quasi real-time requirement of generator PD online monitoring, an improved scale space filtering technique is proposed and applied in PD pulse extraction.
提出了一种用于多尺度边缘检测的小波变换滤波器系数的计算方法，并且以具体例子进行了检验，表明了该方法的有效性。
A method of calculating wavelet transformation filter coefficients for multiscale edge detection is given in this paper, and the efficiency of the method is clarified.
信号的多分辨经验模分解方法可以解释为以信号极值特征尺度为度量的时空滤波过程。
The multiresolution empirical mode decomposition method of signal can be interpreted as spatial filtering based on the signal's extremum characteristic scale.
用M带小波变换来拟合状态在各尺度空间的投影关系，建立了满足标准卡尔曼滤波条件的系统模型。
M-band wavelet is used to approximate the projection relationship between the scale Spaces, and system model that satisfies Kalman filter condition is built.
小波变换局部极大值滤波方法利用信号与噪声不同的尺度变化特性来区分信号与噪声，将噪声从信号中分离出来。
A filtering method based on wavelet transform with local maximum value was discussed. The method could distinguish signal from the noise according to the different features of scale change.
同时对太阳毫秒级资料作带通滤波将不同时间尺度的快速起伏分离出来。
In this paper, a band-pass filter is used to separate the components of rapid fluctuations with various time scales from ms-resolution data of solar bursts.
由于周期性纹理的纹元是以周期为单位的纹理块，该文试图对周期性纹理图像进行方向滤波后找出纹理的周期，然后以周期尺度为采样块的大小和采样间距，进行纹理合成。
Because the texel of periodic texture is the patch with the textures period, here try to calculate the period by direction filter, and then synthesize the periodic texture by sampling with the period.
该算法对图像进行多结构多尺度自适应形态滤波处理，从而抑制图像的暗噪声和暗纹理细节。
The algorithm first executed the adaptive morphological filtering of fusion to restrain dark noise and texture details of the images.
论文提出一种基于高斯滤波器的尺度相乘边缘检测算法。
This paper presents an algorithm to edge detection by scale multiplication based on Gaussian filter.
分别研究了所有滤波长度为4和5的双正交多尺度分析（MRA）的构造。
The construction of biorthonormal MRAs with filter length 4 and 5 is studied respectively.
文中还给出了这三和滤波下的相关峰值与旋转角度及尺度因子的关系曲线。
Correlations against rotation Angle and scaling factor for all the three filters are also presented.
用CB形态滤波器对灰度图进行滤波，构成CB形态学尺度空间，以实现对拐角的多尺度检测。
Filtering the intensity image by CB morphological filters, the idea of CB morphological scale space is constructed, by which to realize multi scale corner detection.
针对这种相关性，并结合薄雾退化图像的特点，采用了一种多尺度的处理方法，对处理后的图像采用自适应中值滤波器滤除噪声。
According to this correlation and the features of the degradation images by fog the method of multi-scale process was used in this paper.
针对复杂情况下变尺度目标跟踪问题，提出一种基于粒子滤波的自适应尺度目标跟踪算法。
To track objects with scale changes in a complex scene, a particle filter based object tracking approach is proposed in this paper.
论文基于这一思想，从二维平滑函数出发，并根据尺度呈级数变化的特点，导出了一组多尺度小波滤波器。
According to the peculiarity that the scale exhibit progressional variety, this paper deduces a group of multiscale wavelet filter from two dimensions smooth function.
针对所处理图像的特点，对分割提取的真菌图像应用了多尺度cb形态滤波滤除噪声，并利用结构元素的串行分解原则提高了运算速度。
According to the characteristic of bacteria image processed using our system, we have improved the fast methods of multi-scaled CB morphology filter to remove noise.
当两种滤波器的尺度空间常数很大时，它们的时域与频域性能基本相近。
When the scale space constants of the two filters are large enough, the characteristics and performances are almost the same.
用这种滤波器实现了平移、旋转、尺度三重不变光学图像识别，且有较高的信噪比。
By this filter, the shift, scale and rotation invariant optical pattern recognition was realized with a high signal noise ratio of correlation output.
提出了一种贝叶斯估计和尺度空间滤波相结合的滤波方法。
This paper proposes a method of denoising by the use of jointing Bayes estimation and scale space filtering.
该算法以小波变换中的滤波器理论为基础，通过将图像序列在时间域的尺度分解和相应统计量计算，获得在红外焦平面校正中起影响的偏置和增益系数。
With the scale decomposition of image sequences on the time field and the corresponding statistics' calculation, the offset and gain coefficients in IRFPA NUC were obtained.
用滤波方法得到产生强风暴的中尺度天气系统。
The mesoscale systems generating severe storms are separated through filtering.
针对小波变换多分辨分析(mra)的特点，本文提出一种多尺度分级的自适应模糊权重中值滤波的去噪方法。
According to the feature of the MRA, this paper presents a noise filtering method of adaptive fuzzy threshold for wavelet classification base on multi resolution.
针对多尺度带乘性噪声系统，在多尺度最优滤波融合的基础上，进行状态最优固定域平滑算法的研究。
Based on multiscale optimal filtering fusion, an optimal state fixed-interval smoothing algorithm is developed for systems with multiplicative noise.
针对多尺度带乘性噪声系统，在多尺度最优滤波融合的基础上，进行状态最优固定域平滑算法的研究。
Based on multiscale optimal filtering fusion, an optimal state fixed-interval smoothing algorithm is developed for systems with multiplicative noise.
应用推荐