Divide an image into 5x5 blocks in python and compute histogram for each block
If your images are large, you can improve performance by manipulating the array's strides to produce the windows you need. The following will use a generalized sliding window function found at Efficient Overlapping Windows with Numpy - I will include it at the end.
import numpy as np
image1 = np.arange(100).reshape(10,10)
image2 = np.arange(100).reshape(10,10)
from itertools import izip
window_size = (5,5)
windows1 = sliding_window(image1, window_size)
windows2 = sliding_window(image2, window_size)
histograms = [(np.histogram(window1,bins=256),np.histogram(window2,bins=256))
for window1, window2 in izip(windows1, windows2)]
for h1, h2 in histograms:
print np.all(h1[0] == h2[0])
sliding window function(s):
from numpy.lib.stride_tricks import as_strided as ast
from itertools import product
def norm_shape(shape):
'''
Normalize numpy array shapes so they're always expressed as a tuple,
even for one-dimensional shapes.
Parameters
shape - an int, or a tuple of ints
Returns
a shape tuple
'''
try:
i = int(shape)
return (i,)
except TypeError:
# shape was not a number
pass
try:
t = tuple(shape)
return t
except TypeError:
# shape was not iterable
pass
raise TypeError('shape must be an int, or a tuple of ints')
def sliding_window(a,ws,ss = None,flatten = True):
'''
Return a sliding window over a in any number of dimensions
Parameters:
a - an n-dimensional numpy array
ws - an int (a is 1D) or tuple (a is 2D or greater) representing the size
of each dimension of the window
ss - an int (a is 1D) or tuple (a is 2D or greater) representing the
amount to slide the window in each dimension. If not specified, it
defaults to ws.
flatten - if True, all slices are flattened, otherwise, there is an
extra dimension for each dimension of the input.
Returns
an array containing each n-dimensional window from a
from http://www.johnvinyard.com/blog/?p=268
'''
if None is ss:
# ss was not provided. the windows will not overlap in any direction.
ss = ws
ws = norm_shape(ws)
ss = norm_shape(ss)
# convert ws, ss, and a.shape to numpy arrays so that we can do math in every
# dimension at once.
ws = np.array(ws)
ss = np.array(ss)
shape = np.array(a.shape)
# ensure that ws, ss, and a.shape all have the same number of dimensions
ls = [len(shape),len(ws),len(ss)]
if 1 != len(set(ls)):
raise ValueError(\
'a.shape, ws and ss must all have the same length. They were %s' % str(ls))
# ensure that ws is smaller than a in every dimension
if np.any(ws > shape):
raise ValueError('ws cannot be larger than a in any dimension. a.shape was %s and ws was %s' % (str(a.shape),str(ws)))
# how many slices will there be in each dimension?
newshape = norm_shape(((shape - ws) // ss) + 1)
# the shape of the strided array will be the number of slices in each dimension
# plus the shape of the window (tuple addition)
newshape += norm_shape(ws)
# the strides tuple will be the array's strides multiplied by step size, plus
# the array's strides (tuple addition)
newstrides = norm_shape(np.array(a.strides) * ss) + a.strides
strided = ast(a,shape = newshape,strides = newstrides)
if not flatten:
return strided
# Collapse strided so that it has one more dimension than the window. I.e.,
# the new array is a flat list of slices.
meat = len(ws) if ws.shape else 0
firstdim = (np.product(newshape[:-meat]),) if ws.shape else ()
dim = firstdim + (newshape[-meat:])
# remove any dimensions with size 1
dim = filter(lambda i : i != 1,dim)
return strided.reshape(dim)
If you want to divide an image into four parts, you need to calculate the ws and ss paramaters. If both dimensions are divisible by two then ws and ss are the same value (ss defaults to ws when not specified). Numpy has the ability to treat array dimensions as (column, row) or (row, column) - I haven't changed any defaults and mine is (row, column). For an 18x26 picture, ws = (26/2, 18/2) - each window will be 13x9 and the adjacent windows are obtained by siliding the window by an equal amount, no overlap. If a dimension is not divisable by two, ss will also need to be determined and there will be some overlap in the windows. For an 18x33 image:
>>>
>>> rows = 33
>>> columns = 18
>>> divisor = 2
>>> col_size, col_overlap = divmod(columns, divisor)
>>> row_size, row_overlap = divmod(rows, divisor)
>>> ws = (row_size, col_size)
>>> ss = (row_size - row_overlap, col_size - col_overlap)
>>> ws, ss
((16, 9), (15, 9))
>>>
For 3d windows (data from images with a color dimension) ws and ss need to have three dimensions. A 15x15 image will have 9 5x5x3 windows
from PIL import Image
import numpy as np
img = Image.open('15by15.bmp')
a = np.asarray(img)
window_size = (5,5,3)
windows = sliding_window(a, window_size)
print windows.shape
>>> (9, 5, 5, 3)
for window in windows:
print window.shape
>>> (5, 5, 3) (5, 5, 3) (5, 5, 3) (5, 5, 3) (5, 5, 3) (5, 5, 3) (5, 5, 3) (5, 5, 3) (5, 5, 3)
Not sure if it is something like this you are looking for, This is the brute-force version.and it's probably quite slow.but it does the job You have to decide what to do with the boundaries though. This will not include the boundary unless the window fits exactly
import numpy as numpy
grey_levels = 256
# Generate a test image
test_image = numpy.random.randint(0,grey_levels, size=(11,11))
# Define the window size
windowsize_r = 5
windowsize_c = 5
# Crop out the window and calculate the histogram
for r in range(0,test_image.shape[0] - windowsize_r, windowsize_r):
for c in range(0,test_image.shape[1] - windowsize_c, windowsize_c):
window = test_image[r:r+windowsize_r,c:c+windowsize_c]
hist = numpy.histogram(window,bins=grey_levels)
Below is the result and the full image is at the end. r,c represents the topleft corner of the window
r=0,c=0
[[ 63 173 131 205 239]
[106 37 156 48 81]
[ 85 85 119 60 228]
[236 79 247 1 206]
[ 97 50 117 96 206]]
r=0,c=5
[[108 241 155 214 183]
[202 2 236 183 225]
[214 141 1 185 115]
[ 4 234 249 95 67]
[232 217 116 211 24]]
r=5,c=0
[[179 155 41 47 190]
[159 69 211 41 92]
[ 64 184 187 104 245]
[190 199 71 228 166]
[117 56 92 5 186]]
r=5,c=5
[[ 68 6 69 63 242]
[213 133 139 59 44]
[236 69 148 196 215]
[ 41 228 198 115 107]
[109 236 191 48 53]]
[[ 63 173 131 205 239 108 241 155 214 183 42]
[106 37 156 48 81 202 2 236 183 225 4]
[ 85 85 119 60 228 214 141 1 185 115 80]
[236 79 247 1 206 4 234 249 95 67 203]
[ 97 50 117 96 206 232 217 116 211 24 242]
[179 155 41 47 190 68 6 69 63 242 162]
[159 69 211 41 92 213 133 139 59 44 196]
[ 64 184 187 104 245 236 69 148 196 215 91]
[190 199 71 228 166 41 228 198 115 107 82]
[117 56 92 5 186 109 236 191 48 53 65]
[177 170 114 163 101 54 80 25 112 35 85]]
I have write this code two automatically split image into n rows and m columns. m and n are arguments and it is easily modifiable. After that it is easy compute histogram for each block which are also saving into the folder named patches.
# Image path, number of rows
# and number of columns
# should be provided as an arguments
import cv2
import sys
import os
if not os.path.exists('patches'):
os.makedirs('patches')
nRows = int(sys.argv[2])
# Number of columns
mCols = int(sys.argv[3])
# Reading image
img = cv2.imread(sys.argv[1])
#print img
#cv2.imshow('image',img)
# Dimensions of the image
sizeX = img.shape[1]
sizeY = img.shape[0]
print(img.shape)
for i in range(0,nRows):
for j in range(0, mCols):
roi = img[i*sizeY/nRows:i*sizeY/nRows + sizeY/nRows ,j*sizeX/mCols:j*sizeX/mCols + sizeX/mCols]
cv2.imshow('rois'+str(i)+str(j), roi)
cv2.imwrite('patches/patch_'+str(i)+str(j)+".jpg", roi)
cv2.waitKey()