smooth_imagesmooth_imageSmoothImageSmoothImagesmooth_image (算子)

名称

smooth_imagesmooth_imageSmoothImageSmoothImagesmooth_image — 使用各种滤波器平滑图像。

签名

描述

smooth_imagesmooth_imageSmoothImageSmoothImageSmoothImagesmooth_image smooths gray images using recursive filters originally developed by Deriche and Shen and using the non-recursive Gaussian filter. The following filters can be chosen via the parameter FilterFilterFilterFilterfilterfilter: 'deriche1', 'deriche2', 'shen' and 'gauss'. The “filter width” (i.e., the range of the filter and thereby result of the filter) can be of any size. In the case that the Deriche or Shen is chosen it decreases by increasing the filter parameter AlphaAlphaAlphaAlphaalphaalpha and increases in the case of the Gauss filter (and AlphaAlphaAlphaAlphaalphaalpha corresponds to the standard deviation of the Gaussian function). An approximation of the appropriate size of the filter width AlphaAlphaAlphaAlphaalphaalpha is performed by the operator info_smoothinfo_smoothInfoSmoothInfoSmoothInfoSmoothinfo_smooth。

Non-recursive filters like the Gaussian filter are often implemented using filter-masks. In this case the runtime of the operator increases with increasing size of the filter mask. The runtime of the recursive filters remains constant; except the border treatment becomes a little bit more time consuming. The Gaussian filter becomes slow in comparison to the recursive ones but is in contrast to them isotropic (the filter 'deriche2' is only weakly direction sensitive). A comparable result of the smoothing is achieved by choosing the following values for the parameter: Alpha(deriche2) = Alpha(deriche1) / 2, Alpha(shen) = Alpha(deriche1) / 2, Alpha(gauss) = 1.77 / Alpha(deriche1).

有关平滑滤波器概念的说明，请参阅 滤波器 / 平滑 一章的引言。

注意

请注意，若使用域缩减后的图像作为输入，滤波器算子可能会返回意外结果。请参阅 滤波器 一章

执行信息

• 多线程类型：可重入（与非独占算子并行运行）。
• 多线程作用域：全局（可从任何线程调用）。
• 在元组级别上自动并行化。
• 在通道级别上自动并行化。
• 在内部数据级别上自动并行化。

参数

info_smooth('deriche2',0.5,Size,Coeffs)
smooth_image(Input,Smooth,'deriche2',7)

info_smooth('deriche2',0.5,Size,Coeffs);
smooth_image(Input,&Smooth,'deriche2',7);

info_smooth('deriche2',0.5,Size,Coeffs)
smooth_image(Input,Smooth,'deriche2',7)

info_smooth('deriche2',0.5,Size,Coeffs)
smooth_image(Input,Smooth,'deriche2',7)

info_smooth('deriche2',0.5,Size,Coeffs)
smooth_image(Input,Smooth,'deriche2',7)

结果

如果参数值正确，算子 smooth_imagesmooth_imageSmoothImageSmoothImageSmoothImagesmooth_image 返回值 2 ( H_MSG_TRUE )。当输入为空（无可用输入图像）时可设置行为通过算子 set_system('no_object_result',<Result>)set_system("no_object_result",<Result>)SetSystem("no_object_result",<Result>)SetSystem("no_object_result",<Result>)SetSystem("no_object_result",<Result>)set_system("no_object_result",<Result>)。如有必要，则抛出异常。

可能的前趋

read_imageread_imageReadImageReadImageReadImageread_image

可能的后继

thresholdthresholdThresholdThresholdThresholdthreshold, dyn_thresholddyn_thresholdDynThresholdDynThresholdDynThresholddyn_threshold, regiongrowingregiongrowingRegiongrowingRegiongrowingRegiongrowingregiongrowing

替代

binomial_filterbinomial_filterBinomialFilterBinomialFilterBinomialFilterbinomial_filter, gauss_filtergauss_filterGaussFilterGaussFilterGaussFiltergauss_filter, mean_imagemean_imageMeanImageMeanImageMeanImagemean_image, derivate_gaussderivate_gaussDerivateGaussDerivateGaussDerivateGaussderivate_gauss, isotropic_diffusionisotropic_diffusionIsotropicDiffusionIsotropicDiffusionIsotropicDiffusionisotropic_diffusion

另见

info_smoothinfo_smoothInfoSmoothInfoSmoothInfoSmoothinfo_smooth, median_imagemedian_imageMedianImageMedianImageMedianImagemedian_image, sigma_imagesigma_imageSigmaImageSigmaImageSigmaImagesigma_image, anisotropic_diffusionanisotropic_diffusionAnisotropicDiffusionAnisotropicDiffusionAnisotropicDiffusionanisotropic_diffusion

参考文献

R.Deriche: “Fast Algorithms for Low-Level Vision”; IEEE Transactions on Pattern Analysis and Machine Intelligence; PAMI-12, no. 1; S. 78-87; 1990.

模块

基础