局部阈值 local_threshold

Currently the operator offers only the Method 'adapted_std_deviation'. This algorithm is a text binarization technique and provides good results for document images.

目前这个算子只提供'adapted_std_deviation'方法，这个算子是一个文本二值化技术，对文档图像的处理效果好。

'adapted_std_deviation'

By selecting Method = 'adapted_std_deviation', a locally adaptive thresholding based on local mean and standard deviation according to Sauvola (see the paper in Reference) is invoked. 

通过选择Method = 'adapted_std_deviation',调用根据Sauvola（参见参考文献中的论文）基于局部均值和标准差的局部自适应阈值。

The algorithm is able to segment document images even if they are degraded,e.g.,due to inhomogeneous illumination or noise.

该算法能够分割文档图像，即使它们是退化的，例如，由于不均匀的照明或噪音。

It enables text binarization on an inhomogeneous background by taking into account the local contrast.

它通过考虑局部对比度来实现非均匀背景上的文本二值化。

For a segmentation of the dark foreground (see parameter LightDark),for a pixel at position(r,c),a local threshold T(r,c) is calculated within a window of size  mask_size x mask_size(see the generic parameter 'mask_size')as follows:

对于暗的前景的分割（参见参数 LightDark），对于位置（r,c)的像素，在大小为  mask_size x mask_size 的窗口内计算局部阈值T(r,c)（参见通用参数'mask_size'),如下所示：

where  is the local mean value within the window and  demotes the corresponding standard deviation.

是窗口内的局部均值，是相应的标准差。

The parameter R(see 'range')is the assumed maximum value of the standard deviation(R=128 for byte images) and k(see 'scale') a parameter that controls how much the threshold value T(r,c) differs from the mean value .

参数R(参见'range')是标准偏差的假设最大值（对于字节图像R=128），k（参见'Scale'）是控制阈值与平均值相差多少的参数。

 If there is high contrast in the neighborhood of a point (r,c) the standard deviation  has a value close to R which yields a threshold value T(r,c) close to the local mean .

如果在点(R,c)附近有高对比度，则标准差的值接近R，从而产生接近局部平均值的阈值T(R,c)。

If the contrast is low, the local threshold is below the local mean value. For dark text on light background containing also darker regions, this lower threshold enables the segmentation of the text even in darker areas.

如果对比度低，局部阈值低于局部均值，对于包含暗区域的亮背景上的暗文字，这个低阈值能够分割低阈值能够分割即使在暗区域的文本。