wdencmp

去噪或压缩

所有的页面崩溃

Syntax

[XC，CXC，LXC，PERF0，PERCL2] = WDENCMP（'GBL'，X，WNAME，N，THR，SORH，LEGEAPP）

[___] = wdencmp（'gbl'，c，l，wname，n，thr，sorh，legpapp）

[___] = wdencmp（'lvl'，x，wname，n，thr，sorh）

[___] = wdencmp（'lvl'，c，l，wname，n，thr，sorh）

描述

example

[XC.,CXC,LXC,Perf0.,PERFL2] = wdencmp('gbl',X,瓦姆姆,N,THR,硕士,keepapp.)返回去噪或压缩版本XC.输入数据Xobtained by wavelet coefficients thresholding using the global positive thresholdTHR。Xis a real-valued vector or matrix. [CXC,LXC] is theN-level wavelet decomposition structure ofXC.（看波东或者Wavedec2.了解更多信息）。PERFL2和Perf0.是L²- 分别恢复和压缩分数分别为百分比。如果keepapp.= 1, the approximation coefficients are kept. Ifkeepapp.= 0，近似系数可以阈值。

[___] = wdencmp('gbl',C,L,瓦姆姆,N,THR,硕士,keepapp.)使用小波分解结构[C,L] of the data to be denoised or compressed.

[___] = wdencmp（'lvl'，X,瓦姆姆,N,THR,硕士)用途the level-dependent thresholdsTHR。The approximation coefficients are kept.

[___] = wdencmp（'lvl'，C,L,瓦姆姆,N,THR,硕士)使用小波分解结构[C,L]。

例子

全部收缩

使用默认的全局阈值去噪1-D信号

打开直播脚本

使用Donoho-Johnstone全局阈值去噪1-D电消耗数据。

加载信号并选择用于去噪的段。

loadLeleccum.; indx = 2600:3100; x = leleccum(indx);

采用ddencmp.确定默认的全局阈值并拒绝信号。绘制原始和去噪的信号。

[thr,sorh,keepapp] = ddencmp('den','wv'，X）;xd = wdencmp（'GBL'，X，'db3'，2，thr，sorh，keepapp）;子图（211）绘图（x）;标题（'原始信号'）;子图（212）绘图（XD）;标题（'去噪'）;

Figure contains 2 axes objects. Axes object 1 with title Original Signal contains an object of type line. Axes object 2 with title Denoised Signal contains an object of type line.

Denoise Image Using Default Global Threshold

打开直播脚本

使用Donoho-Johnstone通用阈值去代表添加性白色高斯噪声的图像。

Load an image and add white Gaussian noise.

loadSinsin.y = x + 18 * randn（size（x））;

采用ddencmp.to obtain the threshold.

[thr,sorh,keepapp] = ddencmp('den','wv'，y）;

去那个图像。使用订单4个syplet和双级小波分解。绘制原始图像，嘈杂的图像和去噪结果。

xd = wdencmp（'GBL',Y,'sym4'，2，thr，sorh，keepapp）;subplot(2,2,1) imagesc(X) title('原始图像') subplot(2,2,2) imagesc(Y) title('Noisy Image'）子图（2,2,3）ImageC（XD）标题（'去噪图像')

Figure contains 3 axes objects. Axes object 1 with title Original Image contains an object of type image. Axes object 2 with title Noisy Image contains an object of type image. Axes object 3 with title Denoised Image contains an object of type image.

输入参数

全部收缩

`X`—输入数据
真实值的矢量|实验矩阵

输入数据以由实际值矢量或矩阵指定的代位或压缩。

数据类型：双倍的

`C`—Wavelet expansion coefficients
真实值的矢量

Wavelet expansion coefficients of the data to be compressed or denoised, specified as a real-valued vector. If the data is one-dimensional,C是输出波东。如果数据是二维，C是输出Wavedec2.。

例子：[c，l]= wavedec(randn(1,1024),3,'db4')

数据类型：双倍的

`L`—小波膨胀系数的大小
vector of positive integers|正整数的矩阵

小波膨胀系数的大小of the signal or image to be compressed or denoised, specified as a vector or matrix of positive integers.

对于信号，L是输出波东。对于图像，L是输出Wavedec2.。

例子：[c，l]= wavedec(randn(1,1024),3,'db4')

数据类型：双倍的

`瓦姆姆`—Name of wavelet
字符向量|string scalar

Name of wavelet, specified as a character vector or string scalar, to use for denoising or compression. Seewavemngr了解更多信息。wdencmp用途瓦姆姆生成N-level wavelet decomposition ofX。

`N`—Level of wavelet decomposition
positive integer

小波分解级别，指定为正整数。

`THR`—临界点
scalar|真实值的矢量|实验矩阵

阈值适用于小波系数，指定为标量，实值矢量或实值矩阵。

对于案件'GBL',THRis a scalar.
对于一维案例和'lvd'选项，THR是一个长度N实值向量包含the level-dependent thresholds.
对于二维案例和'lvd'选项，THR是一个3-by-Nmatrix containing the level-dependent thresholds in the three orientations: horizontal, diagonal, and vertical.

数据类型：双倍的

`硕士`—Type of thresholding
`'s'`|`'H'`

要执行的阈值类型的类型：

's'- 软阈值
'H'- 硬阈值

Seewithresh.了解更多信息。

`keepapp.`—临界点approximation setting
`0`|`1`

阈值近似设置，指定为0或者1。如果keepapp.= 1，近似系数不能阈值。如果keepapp.= 0, the approximation coefficients can be thresholded.

数据类型：双倍的

Output Arguments

全部收缩

`XC.`— Denoised or compressed data
真实值的矢量| real-valued matrix

去噪或压缩数据，作为实值矢量或矩阵返回。XC.和X具有相同的尺寸。

`CXC`— Wavelet expansion coefficients
真实值的矢量

Wavelet expansion coefficients of the denoised or compressed dataXC.，作为一个真实值的向量返回。LXCcontains the number of coefficients by level.

`LXC`— Size of wavelet expansion coefficients
vector of positive integers | matrix of positive integers

小波膨胀系数的大小of the denoised or compressed dataXC., specified as a vector or matrix of positive integers. If the data is one-dimensional,LXC是正整数的矢量（见波东了解更多信息）。如果数据是二维，LXCis a matrix of positive integers (seeWavedec2.了解更多信息）。

`Perf0.`- 压缩得分
scalar

压缩评分，作为实数返回。Perf0.是等于0的阈值系数的百分比。

`PERFL2`—L²能量恢复
scalar

PERFL2= 100 *（矢量 - 规范CXC/ vector-norm ofC)²如果[c，l]表示小波分解结构X。

如果X是一维信号和'wname'正交小波，PERFL2is reduced to

$\frac{100. {‖ X C ‖}^{2}}{{‖ X ‖}^{2}}$

算法

去噪和压缩程序包含三个步骤：

Decomposition.
阈值化。
Reconstruction.

The two procedures differ in Step 2. In compression, for each level in the wavelet decomposition, a threshold is selected and hard thresholding is applied to the detail coefficients.

参考

[1] DeVore, R. A., B. Jawerth, and B. J. Lucier. “Image Compression Through Wavelet Transform Coding.”一世EEE Transactions on Information Theory。卷。38，第2992号，第719-746页。

[2] Dohoho，D. L。“小波分析和WVD的进展：十分钟之旅。”Progress in Wavelet Analysis and Applications(Y. Meyer, and S. Roques, eds.). Gif-sur-Yvette: Editions Frontières, 1993.

[3] Donoho，D. L.和I. M. Johnstone。“小波收缩的理想空间适应。”Biometrika。卷。81, pp. 425–455, 1994.

[4] Donoho, D. L., I. M. Johnstone, G. Kerkyacharian, and D. Picard. “Wavelet Shrinkage: Asymptopia?”皇家统计社会学报,B.，卷。57，2，PP。301-369,1995。

[5] Donoho, D. L., and I. M. Johnstone. “Ideal denoising in an orthonormal basis chosen from a library of bases.”C. R. Acad。SCI。巴黎,Ser。一世，卷。319，PP。1317-1322,1994。

[6] Donoho, D. L. “De-noising by Soft-Thresholding.”一世EEE Transactions on Information Theory。卷。42, Number 3, pp. 613–627, 1995.

Extended Capabilities

C / C ++代码生成
使用MATLAB®Coder™生成C和C ++代码。

使用说明和限制：

Variable-size data support must be enabled.

Version History

在R2006A之前介绍

wdencmp

Syntax

描述

例子

使用默认的全局阈值去噪1-D信号

Denoise Image Using Default Global Threshold

输入参数

`X`—输入数据
真实值的矢量|实验矩阵

`C`—Wavelet expansion coefficients
真实值的矢量

`L`—小波膨胀系数的大小
vector of positive integers|正整数的矩阵

`瓦姆姆`—Name of wavelet
字符向量|string scalar

`N`—Level of wavelet decomposition
positive integer

`THR`—临界点
scalar|真实值的矢量|实验矩阵

`硕士`—Type of thresholding
`'s'`|`'H'`

`keepapp.`—临界点approximation setting
`0`|`1`

Output Arguments

`XC.`— Denoised or compressed data
真实值的矢量| real-valued matrix

`CXC`— Wavelet expansion coefficients
真实值的矢量

`LXC`— Size of wavelet expansion coefficients
vector of positive integers | matrix of positive integers

`Perf0.`- 压缩得分
scalar

`PERFL2`—L²能量恢复
scalar

算法

参考

Extended Capabilities

C / C ++代码生成
使用MATLAB®Coder™生成C和C ++代码。

Version History

See Also

Functions

Apps

wdencmp

Syntax

描述

例子

使用默认的全局阈值去噪1-D信号

Denoise Image Using Default Global Threshold

输入参数

X—输入数据真实值的矢量|实验矩阵

C—Wavelet expansion coefficients真实值的矢量

L—小波膨胀系数的大小vector of positive integers|正整数的矩阵

瓦姆姆—Name of wavelet字符向量|string scalar

N—Level of wavelet decompositionpositive integer

THR—临界点scalar|真实值的矢量|实验矩阵

硕士—Type of thresholding's'|'H'

keepapp.—临界点approximation setting0|1

Output Arguments

XC.— Denoised or compressed data真实值的矢量| real-valued matrix

CXC— Wavelet expansion coefficients真实值的矢量

LXC— Size of wavelet expansion coefficientsvector of positive integers | matrix of positive integers

Perf0.- 压缩得分scalar

PERFL2—L2能量恢复scalar

算法

参考

Extended Capabilities

C / C ++代码生成使用MATLAB®Coder™生成C和C ++代码。

Version History

See Also

Functions

Apps

`X`—输入数据
真实值的矢量|实验矩阵

`C`—Wavelet expansion coefficients
真实值的矢量

`L`—小波膨胀系数的大小
vector of positive integers|正整数的矩阵

`瓦姆姆`—Name of wavelet
字符向量|string scalar

`N`—Level of wavelet decomposition
positive integer

`THR`—临界点
scalar|真实值的矢量|实验矩阵

`硕士`—Type of thresholding
`'s'`|`'H'`

`keepapp.`—临界点approximation setting
`0`|`1`

`XC.`— Denoised or compressed data
真实值的矢量| real-valued matrix

`CXC`— Wavelet expansion coefficients
真实值的矢量

`LXC`— Size of wavelet expansion coefficients
vector of positive integers | matrix of positive integers

`Perf0.`- 压缩得分
scalar

`PERFL2`—L²能量恢复
scalar

C / C ++代码生成
使用MATLAB®Coder™生成C和C ++代码。