版本35和36间的区别
于2008-05-22 17:40:19修订的的版本35
大小: 1830
编辑: chenzhongke
备注:
于2008-05-22 17:55:20修订的的版本36
大小: 1211
编辑: chenzhongke
备注:
删除的内容标记成这样。 加入的内容标记成这样。
行号 30: 行号 30:
行号 33: 行号 32:
{{attachment:figure917.png}}

一个像素p的上下左右四个像素称为4邻接像素,上下左右再加上四个对角线像素称为8邻接像素。如果两个像素p1和pn之间存在一条路径p1,p2,...pn,其中每相邻两个之间都是4邻接的,则称p1和pn是4连通的;如果每相邻两个像素之间都是8邻接的,则称p1和pn是8连通的;如果不存在这样的路径,则称为p1和pn是不连通的。与p连通的所有像素的集合称为包含p的连通分量。

在matlab中,可以由bwlabel函数来找出连通分量,为不同的连通分量标上不同的标记。{{{
[L num] = bwlabel(f, conn)
}}}conn是4或者8,表示选择4连通或者8连通。

{{attachment:figure918.png}}

{{attachment:figure919.png}}

{{attachment:figure920.png}}
<<Include(^图像的数学形态学处理/110 标记连通分量)>>
行号 49: 行号 36:
{{attachment:figure921.png}} <<Include(^图像的数学形态学处理/120 形态学重构)>>
行号 51: 行号 38:
=== 由重构做开运算 === <<Include(^图像的数学形态学处理/130 由重构做开运算)>>
行号 53: 行号 40:
{{attachment:figure922.png}} <<Include(^图像的数学形态学处理/140 填充空洞)>>
行号 55: 行号 42:
=== 填充空洞 ===



=== 清除边界对象 ===
<<Include(^图像的数学形态学处理/150 清除边界对象)>>

<<Navigation: 执行失败 ['AllContext' object has no attribute 'values'] (see also the log)>>

预备知识

<<Include: 执行失败 [Missing parentheses in call to 'print'. Did you mean print(...)?] (see also the log)>>

<<Include: 执行失败 [Missing parentheses in call to 'print'. Did you mean print(...)?] (see also the log)>>

<<Include: 执行失败 [Missing parentheses in call to 'print'. Did you mean print(...)?] (see also the log)>>

膨胀和腐蚀

<<Include: 执行失败 [Missing parentheses in call to 'print'. Did you mean print(...)?] (see also the log)>>

<<Include: 执行失败 [Missing parentheses in call to 'print'. Did you mean print(...)?] (see also the log)>>

<<Navigation: 执行失败 ['AllContext' object has no attribute 'values'] (see also the log)>>

1. 常用的结构元素

在matlab中,可以用strel函数,生成一些常用的结构元素。

../table92.png

strel返回的不是矩阵,而是一个strel对象,它可以直接传给imdilate作为参数。也可以通过getnhood得到对应的矩阵。例如:

se = strel('diamond', 3)
B = getnhood(se)

<<Navigation: 执行失败 ['AllContext' object has no attribute 'values'] (see also the log)>>

<<Include: 执行失败 [Missing parentheses in call to 'print'. Did you mean print(...)?] (see also the log)>>

组合运算

<<Include: 执行失败 [Missing parentheses in call to 'print'. Did you mean print(...)?] (see also the log)>>

<<Include: 执行失败 [Missing parentheses in call to 'print'. Did you mean print(...)?] (see also the log)>>

<<Navigation: 执行失败 ['AllContext' object has no attribute 'values'] (see also the log)>>

1. 其他复合操作

在matlab中,使用bwmorph可以实现多种形态学运算

../table93.png

用法:

g = bwmorph(f, operation, n);

其中,operation是一个指定操作的字符串,n指定操作的重复次数,缺省是1。

例子:

g1 = bwmorph(f, 'thin', 1);
g2 = bwmorph(f, 'thin', 2);
ginf = bwmorph(f, 'thin', Inf);

../figure915.png

骨骼化(也称为提取骨架):

fs = bwmorph(f, 'skel', Inf);

../figure916.png

骨骼化的结果中会有一些毛刺,我们可以对起进行修剪,使用endpoints函数实现:

fs = fs&~endpoints(fs)

<<Navigation: 执行失败 ['AllContext' object has no attribute 'values'] (see also the log)>>

标记连通分量

<<Navigation: 执行失败 ['AllContext' object has no attribute 'values'] (see also the log)>>

1. 标记连通分量

../figure917.png

一个像素p的上下左右四个像素称为4邻接像素,上下左右再加上四个对角线像素称为8邻接像素。

如果两个像素p1和pn之间存在一系列像素p1,p2,...pn,其中每相邻两个之间都是4邻接的,则称p1和pn是4连通的;如果每相邻两个像素之间都是8邻接的,则称p1和pn是8连通的;如果不存在这样的路径,则称为p1和pn是不连通的。p1,p2,...pn称为p1到pn的一条路径。与p连通的所有像素的集合称为包含p的连通分量

在matlab中,可以由bwlabel函数来找出连通分量,为不同的连通分量标上不同的标记。

[L num] = bwlabel(f, conn)

conn是4或者8,表示选择4连通或者8连通。

../figure918.png

../figure919.png

../figure920.png

<<Navigation: 执行失败 ['AllContext' object has no attribute 'values'] (see also the log)>>

形态学重构

<<Include: 执行失败 [Missing parentheses in call to 'print'. Did you mean print(...)?] (see also the log)>>

<<Navigation: 执行失败 ['AllContext' object has no attribute 'values'] (see also the log)>>

1. 由重构做开运算

普通的开运算可以去掉较小的对象,操作是先腐蚀,再膨胀。但是开运算在膨胀中会使形状变形。

可以用重构代替膨胀来做开运算,这个运算定义为<<latex: execution failed [Missing parentheses in call to 'print'. Did you mean print(...)?] (see also the log)>>

例子:

../figure922.png

<<Navigation: 执行失败 ['AllContext' object has no attribute 'values'] (see also the log)>>

<<Include: 执行失败 [Missing parentheses in call to 'print'. Did you mean print(...)?] (see also the log)>>

<<Include: 执行失败 [Missing parentheses in call to 'print'. Did you mean print(...)?] (see also the log)>>

图像的数学形态学处理 (2008-05-22 17:55:20由chenzhongke编辑)

ch3n2k.com | Copyright (c) 2004-2020 czk.