大概的轮廓……

你可能想要使用连接组件算法来隔离每个爪子区域。wiki对此有一个很好的描述(有一些代码):http://en.wikipedia.org/wiki/Connected_Component_Labeling

你必须决定是使用4连通性还是8连通性。就我个人而言，对于大多数问题，我更喜欢6连通性。无论如何，一旦你将每个“爪印”分离为一个连通区域，就很容易遍历该区域并找到最大值。一旦你找到了最大值，你就可以迭代地扩大区域，直到达到预定的阈值，以确定它是给定的“脚趾”。

这里有一个微妙的问题是，一旦你开始使用计算机视觉技术来识别某个东西是右/左/前/后爪，你开始观察单个脚趾，你就必须开始考虑旋转、倾斜和平移。这是通过分析所谓的“矩”来完成的。在视觉应用中有几个不同的时刻需要考虑:

中心矩:平移不变量 归一化矩:缩放和平移不变量 胡矩:平移、尺度和旋转不变量

更多关于moments的信息可以在wiki上搜索“image moments”。

只是想告诉你们，有一个很好的选项可以用python在图像中找到局部最大值:

from skimage.feature import peak_local_max

或者对于skimage 0.8.0:

from skimage.feature.peak import peak_local_max

http://scikit-image.org/docs/0.8.0/api/skimage.feature.peak.html

物理学家的解决办法: 定义5个爪标记，用它们的位置X_i来标识，并用随机的位置初始化它们。 定义一个能量函数，结合标记物在爪子位置的定位奖励和标记物重叠惩罚;比方说:

E(X_i;S)=-Sum_i(S(X_i))+alfa*Sum_ij (|X_i-Xj|<=2*sqrt(2)?1:0)

(S(X_i)是围绕X_i的2x2平方的平均力，阿尔法是一个实验峰值参数)

Now time to do some Metropolis-Hastings magic: 1. Select random marker and move it by one pixel in random direction. 2. Calculate dE, the difference of energy this move caused. 3. Get an uniform random number from 0-1 and call it r. 4. If dE<0 or exp(-beta*dE)>r, accept the move and go to 1; if not, undo the move and go to 1. This should be repeated until the markers will converge to paws. Beta controls the scanning to optimizing tradeoff, so it should be also optimized experimentally; it can be also constantly increased with the time of simulation (simulated annealing).

好吧，这里有一些简单而不是非常有效的代码，但对于这样大的数据集来说，这是很好的。

import numpy as np
grid = np.array([[0,0,0,0,0,0,0,0,0,0,0,0,0,0],
              [0,0,0,0,0,0,0,0,0.4,0.4,0.4,0,0,0],
              [0,0,0,0,0.4,1.4,1.4,1.8,0.7,0,0,0,0,0],
              [0,0,0,0,0.4,1.4,4,5.4,2.2,0.4,0,0,0,0],
              [0,0,0.7,1.1,0.4,1.1,3.2,3.6,1.1,0,0,0,0,0],
              [0,0.4,2.9,3.6,1.1,0.4,0.7,0.7,0.4,0.4,0,0,0,0],
              [0,0.4,2.5,3.2,1.8,0.7,0.4,0.4,0.4,1.4,0.7,0,0,0],
              [0,0,0.7,3.6,5.8,2.9,1.4,2.2,1.4,1.8,1.1,0,0,0],
              [0,0,1.1,5,6.8,3.2,4,6.1,1.8,0.4,0.4,0,0,0],
              [0,0,0.4,1.1,1.8,1.8,4.3,3.2,0.7,0,0,0,0,0],
              [0,0,0,0,0,0.4,0.7,0.4,0,0,0,0,0,0]])

arr = []
for i in xrange(grid.shape[0] - 1):
    for j in xrange(grid.shape[1] - 1):
        tot = grid[i][j] + grid[i+1][j] + grid[i][j+1] + grid[i+1][j+1]
        arr.append([(i,j),tot])

best = []

arr.sort(key = lambda x: x[1])

for i in xrange(5):
    best.append(arr.pop())
    badpos = set([(best[-1][0][0]+x,best[-1][0][1]+y)
                  for x in [-1,0,1] for y in [-1,0,1] if x != 0 or y != 0])
    for j in xrange(len(arr)-1,-1,-1):
        if arr[j][0] in badpos:
            arr.pop(j)


for item in best:
    print grid[item[0][0]:item[0][0]+2,item[0][1]:item[0][1]+2]

我基本上只是用左上角的位置和每个2x2平方的和来做一个数组，然后根据和来排序。然后我把和最高的2x2平方从竞争中取出，把它放在最好的数组中，然后删除所有其他使用了这个2x2平方的部分的2x2平方。

It seems to work fine except with the last paw (the one with the smallest sum on the far right in your first picture), it turns out that there are two other eligible 2x2 squares with a larger sum (and they have an equal sum to each other). One of them is still selects one square from your 2x2 square, but the other is off to the left. Fortunately, by luck we see to be choosing more of the one that you would want, but this may require some other ideas to be used to get what you actually want all of the time.

我脑子里有几个想法:

取扫描的梯度(导数)，看看是否消除了错误的调用 取局部极大值的最大值

你可能还想看看OpenCV，它有一个相当不错的Python API，可能有一些你会发现有用的函数。

如果你能够创建一些训练数据，那么使用神经网络可能是值得尝试的……但这需要手工标注许多样本。