Masks

gistfile1.txt

from __future__ import division
import matplotlib.pyplot as plt
import numpy as np
from skimage import io,color, img_as_float

def averaging_mask(A, mask_size):
    rows = np.shape(A)[0]
    columns = np.shape(A)[1]
    half_length = int((mask_size-1)/2)

    pad_A = np.concatenate([np.zeros((rows, half_length)), A, np.zeros((rows, half_length))], axis=1)
    pad_A = np.concatenate([np.zeros((half_length, columns+2*half_length)), pad_A, np.zeros((half_length, columns+2*half_length))], axis=0)
    mask = np.ones((mask_size, mask_size))/(mask_size**2)    

    B = np.zeros_like(A)
    for i in xrange(0, rows):
        for j in xrange(0, columns):
            B[i, j] = (np.multiply(mask, pad_A[i:mask_size + i, j:mask_size + j]))[half_length, half_length]
            print B[i, j]

    return B


def high_boost_filtering(A, k):
    smoothed = averaging_mask(A, mask_size)
    mask = A - smoothed 
    sharpened = A + k*mask

    return sharpened


def high_boost_filtering_single_mask(A, mask_size, k):
    rows = np.shape(A)[0]
    columns = np.shape(A)[1]
    half_length = int((mask_size-1)/2)

    pad_A = np.concatenate([np.zeros((rows, half_length)), A, np.zeros((rows, half_length))], axis=1)
    pad_A = np.concatenate([np.zeros((half_length, columns+2*half_length)), pad_A, np.zeros((half_length, columns+2*half_length))], axis=0)

    I = np.zeros((mask_size, mask_size))
    I[half_length, half_length] = 1
    average = np.ones((mask_size, mask_size))/(mask_size**2)
    mask = I + k*(I - average)

    sharpened = np.zeros_like(A)
    for i in xrange(0, rows):
        for j in xrange(0, columns):
            sharpened[i, j] = np.multiply(mask, pad_A[i:mask_size + i, j:mask_size + j])[half_length, half_length]

    return sharpened

A = io.imread('manwithspecs.jpg', plugin='pil')
B = color.rgb2gray(io.imread('moon.jpg', plugin='pil'))

mask_size = 17
out = averaging_mask(A, mask_size)

k = 2
out1 = high_boost_filtering(A, k)

out2 = high_boost_filtering_single_mask(A, mask_size, k)

print out1==out2

f, (ax0, ax1) = plt.subplots(1, 2)
f.tight_layout()

ax0.imshow(A, cmap=plt.cm.gray)
ax0.set_title('Input image')

ax1.imshow(out, cmap=plt.cm.gray)
ax1.set_title('Image smoothed using a averaging mask, mask size = ')

f1, (ax0, ax1) = plt.subplots(1, 2)
f1.tight_layout()

ax0.imshow(A, cmap=plt.cm.gray)
ax0.set_title('Input image')

ax1.imshow(out1, cmap=plt.cm.gray)
ax1.set_title('Image smoothed using high boost filtering, mask size = , k = ')

f2, (ax0, ax1) = plt.subplots(1, 2)
f2.tight_layout()

ax0.imshow(A, cmap=plt.cm.gray)
ax0.set_title('Input image')

ax1.imshow(out2, cmap=plt.cm.gray)
ax1.set_title('Image smoothed by a single mask convolution, mask size = , k = ')

plt.show()