threshold.imwd(wavethresh)
threshold.imwd()所属R语言包：wavethresh
Threshold two-dimensional wavelet decomposition object
阈值二维小波分解对象
译者：生物统计家园网 机器人LoveR
描述----------Description----------
This function provides various ways to threshold a imwd class object.
此功能提供了多种阈值一个imwd类对象。
用法----------Usage----------
## S3 method for class 'imwd':
threshold(imwd, levels = 3 nlevels(imwd) - 1), type = "hard", policy =
"universal", by.level = FALSE, value = 0, dev = var, verbose = FALSE,
return.threshold = FALSE, compression = TRUE, Q = 0.05, ...)
参数----------Arguments----------
参数：imwd
The two-dimensional wavelet decomposition object that you wish to threshold.
二维小波分解的对象，你想阈值。
参数：levels
a vector of integers which determines which scale levels are thresholded in the decomposition. Each integer in the vector must refer to a valid level in the imwd object supplied. This is usually any integer from 0 to nlevels(wd)-1 inclusive. Only the levels in this vector contribute to the computation of the threshold and its application. (except for the fdr policy).
决定哪些规模水平的阈值分解的向量整数。向量中的每个整数必须在imwd对象提供一个有效的水平。这通常是从0到nlevels（WD）-1包容性的任一整数。只有在此向量的水平作出贡献的阈值的计算及其应用。 （除了fdr政策）。
参数：type
determines the type of thresholding this can be "hard" or "soft".
确定阈值的类型，这可能是“hard”或“soft”。
参数：policy
selects the technique by which the threshold value is selected. Each policy corresponds to a method in the literature. At present the different policies are: "universal", "manual", "fdr", "probability". The policies are described in detail below.
选择被选择的阈值的技术，通过该技术。每个策略对应的方法在文献中。目前，不同的政策是：“universal”，“manual”，“fdr”，“probability”。在下面详细描述的政策。
参数：by.level
If FALSE then a global threshold is computed on and applied to all scale levels defined in levels. If TRUE a threshold is computed and applied separately to each scale level.
如果为FALSE，那么一个全球性的阈值计算，并适用于所有等级的定义的水平。如果真正的阈值计算，并分别应用到每一个规模水平。
参数：value
This argument conveys the user supplied threshold. If the policy="manual" then value is the actual threshold value; if policy="probability" then value conveys the the user supplied quantile level.
这个参数传递的用户提供的阈值。如果policy="manual"然后值是实际的阈值，如果policy="probability"然后value传达用户提供的位数水平。
参数：dev
this argument supplies the function to be used to compute the spread of the absolute values coefficients. The function supplied must return a value of spread on the variance scale (i.e. not standard deviation) such as the var() function. A popular, useful and robust alternative is the madmad function.
此参数提供的功能被用于计算的绝对值的系数的传播。提供的函数必须返回一个值传播的方差比例（即不标准差），如var()功能。一个流行的，有用的和强大的另一种方法是madmad功能。
参数：verbose
if TRUE then the function prints out informative messages as it progresses.
如果真，那么该函数打印出的信息性消息，因为它的进展。
参数：return.threshold
If this option is TRUE then the actual value of the threshold is returned. If this option is FALSE then a thresholded version of the input is returned.
如果该选项是TRUE，则该阈值的实际值被返回。如果此选项为FALSE，则返回一个版本的输入阈值。
参数：compression
If this option is TRUE then this function returns a comressed two-dimensional wavelet transform object of class imwdc. This can be useful as the resulting object will be smaller than if it was not compressed. The compression makes use of the fact that many coefficients in a thresholded object will be exactly zero. If this option is FALSE then a larger imwd object will be returned.
如果此选项为真，那么函数返回一个comressed的二维小波变换对象的类imwdc。这可能是有用的对象将是更小的比，如果它没有被压缩。所述压缩使得使用的事实，即许多在一个阈限对象的系数将是完全为零。如果此选项为FALSE，则一个更大的imwd对象将被退回。
参数：Q
Parameter for the false discovery rate "fdr" policy.
参数的虚假发现率"fdr"政策。
参数：...
any other arguments
任何其他参数
Details
详细信息----------Details----------
This function thresholds or shrinks wavelet coefficients stored in a imwd object and by default returns the coefficients in a modified imwdc object. See the seminal papers by Donoho and Johnstone for explanations about thresholding. For a gentle introduction to wavelet thresholding (or shrinkage as it is sometimes called) see Nason and Silverman, 1994. For more details on each technique see the descriptions of each method below
此功能的阈值或收缩的小波系数存储在一个imwd对象，默认情况下返回系数在修改后的imwdc对象的。 Donoho和Johnstone的开创性论文的说明，关于阈值。对于简单的介绍小波阈值（或收缩，因为它有时也被称为），见利晨和Silverman，1994年。对于每个技术的详细信息，请参阅下面的每个方法的描述
The basic idea of thresholding is very simple. In a signal plus noise model the wavelet transform of an image is very sparse, the wavelet transform of noise is not (in particular, if the noise is iid Gaussian then so if the noise contained in the wavelet coefficients). Thus, since the image gets concentrated in few wavelet coefficients and the noise remains "spread" out it is "easy" to separate the signal from noise by keeping large coefficients (which correspond to true image) and delete the small ones (which correspond to noise). However, one has to have some idea of the noise level (computed using the dev option in threshold functions). If the noise level is very large then it is possible, as usual, that no image coefficients "stick up" above the noise.
阈值的基本思想是非常简单的。在小波变换的图像的信号加噪声模型是很稀疏，小波变换等的噪声是不（特别是，如果噪声是独立同分布的高斯那么，如果包含的噪声在小波系数）。因此，由于图像被集中在少数小波系数和噪声仍然是“传播”了，它是“容易”的信号从噪声中分离，保持较大的系数（对应于真实的图像），并删除小（对应于噪声）。然而，有一些想法的噪声电平（使用dev选项的阈值函数计算）。如果噪声电平是非常大的，那么它是可能的，像往常一样，没有图像的系数“，坚持”以上的噪音。
There are many components to a successful thresholding procedure. Some components have a larger effect than others but the effect is not the same in all practical data situations. Here we give some rough practical guidance, although you must refer to the papers below when using a particular technique. You cannot expect to get excellent performance on all signals unless you fully understand the rationale and limitations of each method below. I am not in favour of the "black-box" approach. The thresholding functions of WaveThresh3 are not a black box: experience and judgement are required!
一个成功的阈值程序有许多组件。某些组件有一个比别人更大的效果，但效果是不一样的，在所有实际数据的情况下。在这里，我们给出了一些粗糙的实用指导，但你必须参考以下的文件时使用特定的技术。除非你完全理解下面的基本原理和每种方法的局限，你不能指望获得优异的性能对所有信号。我并不赞成“黑盒子”的方法。阈值函数的WaveThresh3是不是黑盒的经验和判断！
Some issues to watch for:
注意的一些问题：
levels The default of levels = 3wd$nlevels - 1) for the levels option most certainly does not work globally for all data problems and situations. The level at which thresholding begins (i.e. the given threshold and finer scale wavelets) is called the primary resolution and is unique to a particular problem. In some ways choice of the primary resolution is very similar to choosing the bandwidth in kernel regression albeit on a logarithmic scale. See Hall and Patil, (1995) and Hall and Nason (1997) for more information. For each data problem you need to work out which is the best primary resolution. This can be done by gaining experience at what works best, or using prior knowledge. It is possible to "automatically" choose a "best" primary resolution using cross-validation (but not in WaveThresh).
水平默认的levels = 3wd$nlevels - 1)levels选项当然没有在全球范围的所有数据的问题和情况。在哪一级的阈值开始（即在给定的阈值和更细的刻度小波）称为主分辨率和是唯一的一个特别的问题。在某些方面，主决议选择是非常类似的选择的带宽在内核回归尽管在对数刻度。见厅和Patil（1995）和霍尔和利晨（1997）更多信息。对于每一个数据的问题，你需要的工作，这是最好的小学分辨率。这是可以做到什么效果最好，获得经验或使用先验知识。这是可能的“自动”选择“最佳”的主要决议，采用交叉验证（而不是在WaveThresh）。
Secondly the levels argument computes and applies the threshold at the levels specified in the levels argument. It does this for all the levels specified. Sometimes, in wavelet shrinkage, the threshold is computed using only the finest scale coefficients (or more precisely the estimate of the overall noise level). If you want your threshold variance estimate only to use the finest scale coefficients (e.g. with universal thresholding) then you will have to apply the threshold.imwd function twice. Once (with levels set equal to nlevels(wd)-1) and with return.threshold=TRUE to return the threshold computed on the finest scale and then apply the threshold function with the manual option supplying the value of the previously computed threshold as the value options.
其次，各级参数的阈值水平levels参数中指定的计算和应用。为此，它规定的水平。有时，在小波阈值，该阈值计算只用最好的比例系数（或更精确的估计的整体噪声水平）。如果您希望您的阈值的方差估计只有使用最好的规模系数（即通用阈值），那么你将不得不申请threshold.imwd函数两次。一旦（级别设置等于nlevels（WD）-1）和return.threshold=TRUE返回上最优秀的规模计算的阈值，然后应用阈值manual选项提供的功能与值value选项先前计算的阈值。
Note that the fdr policy does its own thing.
请注意，FDR的政策做自己的事情。
by.levelfor a wd object which has come from data with noise that is correlated then you should have a threshold computed for each resolution level. See the paper by Johnstone and Silverman, 1997.
by.levelfor一个wd对象来自相关的噪音，那么你应该有一个阈值，计算出每个分辨率级别的数据。约翰斯通和Silverman，1997年的文件。
值----------Value----------
An object of class imwdc if the compression option above is TRUE, otherwise a imwd object is returned. In either case the returned object contains the thresholded coefficients. Note that if the return.threshold option is set to TRUE then the threshold values will be returned rather than the thresholded object.
类的一个对象imwdc如果compression上面的选项是TRUE，否则一个imwd对象被返回。在这两种情况下，返回的对象包含阈值的系数。请注意，如果return.threshold选项被设置为TRUE，则阈值将被返回，而比阈值对象。
RELEASE----------RELEASE----------
Version 3.6 Copyright Guy Nason and others 1997
3.6版版权盖利晨和其他1997
注意----------Note----------
This section gives a brief description of the different thresholding policies available. For further details see the associated papers. If there is no paper available then a small description is provided here. More than one policy may be good for problem, so experiment! They are arranged here in alphabetical order:
本节给出了不同的阈值策略的简要说明。有关进一步详情，请参阅相关的文件。如果没有纸张可用，则一个小的描述在此提供。超过一个策略可能是很好的问题，所以实验！他们被安排在这里按字母顺序排列：
fdrSee Abramovich and Benjamini, 1996. Contributed by Felix Abramovich.
fdrSee阿布拉莫维奇和Benjamini的，1996年。提供者费利克斯·阿布拉莫维奇。
manualspecify a user supplied threshold using value to pass the value of the threshold. The value argument should be a vector. If it is of length 1 then it is replicated to be the same length as the levels vector, otherwise it is repeated as many times as is necessary to be the levels vector's length. In this way, different thresholds can be supplied for different levels. Note that the by.level option has no effect with this policy.
manualspecify用户提供的阈值，使用value通过的阈值。 value参数应该是一个向量。如果它的长度为1，则它被复制到作为levels矢量是相同的长度，否则它被重复多次，levels向量的长度是必要的。以这种方式，可以提供不同的阈值的不同级别。需要注意的是by.level选项没有这个政策的影响。
probabilityThe probability policy works as follows. All coefficients that are smaller than the valueth quantile of the coefficients are set to zero. If by.level is false, then the quantile is computed for all coefficients in the levels specified by the "levels" vector; if by.level is true, then each level's quantile is estimated separately. The probability policy is pretty stupid - do not use it.
probabilityThe probability政策的工作原理如下。小于系数valueth位数的所有系数被设置为零。 by.level如果是假的，然后分位数计算的所有系数在规定的水平的“水平”矢量by.level如果是真的，那么每个级别的分位数估计分别。的概率政策是非常愚蠢的 - 不要使用它。
universalSee Donoho and Johnstone, 1995.
universalSee Donoho和Johnstone，1995年。
（作者）----------Author(s)----------
G P Nason
参考文献----------References----------
<h3>See Also</h3> <code>imwd</code>, <code>imwd.object</code>, <code>imwdc.object</code>. <code>threshold</code>.
实例----------Examples----------
#[]
# Let's use the lennon test image[让我们的的列侬测试图像使用]
#[]
data(lennon)
## Not run: image(lennon)[＃非执行：图像（列侬）]
#[]
# Now let's do the 2D discrete wavelet transform[现在，让我们做二维离散小波变换]
#[]
lwd <- imwd(lennon)
#[]
# Let's look at the coefficients[让我们来看看系数]
#[]
## Not run: plot(lwd)[＃未运行图（LWD）]
#[]
# Now let's threshold the coefficients[现在，让我们阈值的系数]
#[]
lwdT <- threshold(lwd)
#[]
# And let's plot those the thresholded coefficients[，让我们绘制这些阈值系数]
#[]
## Not run: plot(lwdT)[＃不运行：图（lwdT）]
#[]
# Note that the only remaining coefficients are down in the bottom[需要注意的是仅存的系数是在底部]
# left hand corner of the plot. All the others (black) have been set[左上角的图。其他所有的（黑色）已设置]
# to zero (i.e. thresholded).[到零（即，阈值）。]
转载请注明:出自 生物统计家园网(http://www.biostatistic.net)。
注：
注1：为了方便大家学习，本文档为生物统计家园网机器人LoveR翻译而成，仅供个人R语言学习参考使用，生物统计家园保留版权。
注2：由于是机器人自动翻译，难免有不准确之处，使用时仔细对照中、英文内容进行反复理解，可以帮助R语言的学习。
注3：如遇到不准确之处，请在本贴的后面进行回帖，我们会逐渐进行修订。
|
发表于 2012-10-1 20:12:03
