Begin My Journey of IMAGE

-


function of scipy.ndimage.measurements.label

# scipy.ndimage.measurements.label(input, structure=None, output=None)
>>> a = np.array([[0,0,1,1,0,0],
...               [0,0,0,1,0,0],
...               [1,1,0,0,1,0],
...               [0,0,0,1,0,0]])
>>> labeled_array, num_features = label(a)

>>> print(num_features)
4
>>> print(labeled_array)
array([[0, 0, 1, 1, 0, 0],
       [0, 0, 0, 1, 0, 0],
       [2, 2, 0, 0, 3, 0],
       [0, 0, 0, 4, 0, 0]])

the default structuring element is:

[[0,1,0],
 [1,1,1],
 [0,1,0]]

>>> s = generate_binary_structure(2,2)
>>> s = [[1,1,1],
         [1,1,1],
         [1,1,1]]
Label the image using the new structuring element:

>>> labeled_array, num_features = label(a, structure=s)
# Show the 2 labeled features 
(note that features 1, 3, and 4 from above 
are now considered a single feature):

>>> print(num_features)
2
>>> print(labeled_array)

array([[0, 0, 1, 1, 0, 0],
       [0, 0, 0, 1, 0, 0],
       [2, 2, 0, 0, 1, 0],
       [0, 0, 0, 1, 0, 0]])

留言

張貼留言

這個網誌中的熱門文章

AndrewNg's CNN notes(practical issues)

-
圖片
In this example, the author adapted the architecture obtained from training ILSVRC-2011 dataset which consists of 1000 classes with approximately 1.5 million images. And using the pre-trained VGG-16 network, the author fine-tuned the network on PASCAL VOC detection data (20 object classes, and 1 background class) and replaced the original 1000 way classification layer by a randomly initialized 21-way classification layer. Apart from that, the author keep the rest of the CNN architecture remains unchanged. After training of CNN parameters and filter the region proposals based on their IoU value, at the test stage, RCNN uses Selective Search to extract ~300 boxes that likely contain objects and evaluates the ConvNet on each one of them, followed by NMS(non-maximum suppression) within each class.
閱讀完整內容

New findings in Numpy

-
1, Ellipsis >>> a = np.arange(6).reshape(2,3) >>> a array([[0, 1, 2], [3, 4, 5]]) >>> for x in np.nditer(a, op_flags=['readwrite']):                                                       x[...] = 2 * x >>> a array([[ 0, 2, 4], [ 6, 8, 10]]) 2, array or matrix Operator  * ,  dot() , and  multiply() : For  array ,  ‘``*``’ means element-wise multiplication , and the  dot()  function is used for matrix multiplication. For  matrix ,  ‘``*``’ means matrix multiplication , and the  multiply()  function is used for element-wise multiplication. Handling of vectors (one-dimensional arrays) For  array , the  vector shapes 1xN, Nx1, and N are all different things . Operations like  A[:,1]  return a one-dimensional array of shape N, not...
閱讀完整內容