大津（Ostu）阈值分割方法在matlab中的实现

 

在matlab的image processing工具箱中，大津（Ostu）阈值分割方法有现成的函数实现 graythreshold

 GRAYTHRESH Global image threshold using Otsu's method.

    LEVEL = GRAYTHRESH(I) computes a global threshold (LEVEL) that can be
    used to convert an intensity image to a binary image with IM2BW. LEVEL
    is a normalized intensity value that lies in the range [0, 1].
    GRAYTHRESH uses Otsu's method, which chooses the threshold to minimize
    the intraclass variance of the thresholded black and white pixels.
 
    [LEVEL EM] = GRAYTHRESH(I) returns effectiveness metric, EM, as the
    second output argument. It indicates the effectiveness of thresholding
    of the input image and it is in the range [0, 1]. The lower bound is
    attainable only by images having a single gray level, and the upper
    bound is attainable only by two-valued images.
 
    Class Support
    -------------
    The input image I can be uint8, uint16, int16, single, or double, and it
    must be nonsparse.  LEVEL and EM are double scalars.
 
    Example
    -------
        I = imread('coins.png');
        level = graythresh(I);
        BW = im2bw(I,level);
        figure, imshow(BW)