def LeeFilter(image, kernelLength, show=False):
import numpy as np
import cv2
from ImageMedicalLib import changeFormat, info
if image.dtype == 'uint8':
image = changeFormat.uint2double(image)
rect = cv2.selectROI(image)
cv2.waitKey(0)
cv2.destroyAllWindows()
c1, c2 = rect[0], rect[0] + rect[2]
l1, l2 = rect[1], rect[0] + rect[3]
stdRect = np.std(image[l1:l2, c1:c2])
newImage = np.zeros(image.shape)
w = np.zeros((kernelLength, kernelLength), dtype=int)
w_center = int((w.shape[0]) / 2)
for indexrow, frow in enumerate(image[:-(w_center * 2)]):
for indexcolumn, fcolumn in enumerate(frow[:-(w_center * 2)]):
maskLocal = image[indexrow:1 + indexrow + w_center * 2,
indexcolumn:1 + indexcolumn + w_center * 2]
meanMask = np.mean(maskLocal + w)
k = np.clip(1 - (stdRect / (0.001 + maskLocal.std())), 0, 1)
newImage[indexrow + w_center,
indexcolumn + w_center] = meanMask + k * (
image[indexrow + w_center, indexcolumn + w_center] -
meanMask)
if show:
info.showImageStyle(
1, 2, {
'I1': changeFormat.im2uint8(image),
'Imean': changeFormat.im2uint8(newImage)
}, ['Original', 'Lee Filter'])
return newImage
def idealfilter(m, n, fc, filterType='LP', show=False):
"""
Filtro ideal para dominio da frequencia
INPUTS:
m: número de linhas
n: número de colunas
fc: frequencia de corte (0 a 1)
filterType: Passa baixa ou passa alta (padrão = LP passa baixa)
show: parametro para exibir filtro criado
OUTPUTS:
H: filtro ideal 2D
"""
import numpy as np
from ImageMedicalLib import changeFormat, info
H = np.zeros((m, n), dtype=int)
centerX, centerY = int(m / 2), int(n / 2)
Do = fc * (0.5 * (centerX * 0.5 + centerY * 0.5))
for i in range(H.shape[0]):
for j in range(H.shape[1]):
D_uv = ((centerX - i)**2 + (centerY - j)**2)**0.5
if D_uv <= Do and filterType == 'LP':
H[i, j] = 1
elif D_uv >= Do and filterType != 'LP':
H[i, j] = 1
if show:
images = {'H': changeFormat.im2uint8(H)}
info.showImageStyle(1, 1, images, ['Butter Mask'])
return H
def butterFilter2D(m, n, fc, nPoles, filterType='LP', show=False):
"""
Filtro butterworth para dominio da frequencia
INPUTS:
m: número de linhas
n: número de colunas
fc: frequencia de corte (0 a 1)
nPoles: número de polos para filtragem
filterType: Passa baixa ou passa alta (padrão = LP passa baixa)
show: parametro para exibir filtro criado
OUTPUTS:
H: filtro butterworth 2D
"""
import numpy as np
from ImageMedicalLib import changeFormat, info
if filterType == 'LP':
H = np.zeros((m, n))
else:
H = np.full((m, n), -1).astype(float)
centerX, centerY = int(m / 2), int(n / 2)
Do = fc * (0.5 * (centerX * 0.5 + centerY * 0.5))
for i in range(m):
for j in range(n):
D_uv = ((centerX - i)**2 + (centerY - j)**2)**0.5
H[i, j] = np.abs(H[i, j] + (1 / (1 + (D_uv / Do)**(2 * nPoles))))
if show:
images = {'H': changeFormat.im2uint8(H)}
info.showImageStyle(1, 1, images, ['Butter Mask'])
return H
#%% 2 - Pulso quadrado
squarePulse = imageio.imread(r'ImagensAulas\PulsoQuadrado1.pgm')
plt.figure()
plt.get_current_fig_manager().window.showMaximized()
fig = plt.gcf()
fig.canvas.set_window_title('Square Pulse')
plt.imshow(squarePulse,cmap='gray',vmin = 0, vmax=255)
plt.axis('off')
plt.show()
#%% 3 - FFT2 Pulso quadrado
fftsquarePulse,fftshiftsquarePulse,absfftsquarePulse = filters.imageFFT(squarePulse)
logFFT = np.log(1+fftshiftsquarePulse)
logFFTABS = np.abs(logFFT)
logFFTABS = changeFormat.im2uint8(changeFormat.imNormalize(logFFTABS))
info.showImageStyle(1,3,{'fftsquarePulse': changeFormat.im2uint8(changeFormat.imNormalize(np.abs(fftsquarePulse))),
'absfftsquarePulse':changeFormat.im2uint8(absfftsquarePulse),
'logFFTABS':logFFTABS},
['fftsquarePulse','absfftsquarePulse','LogfftsquarePulse'])
#%% 4 - Filtro passa baixas de 10%
H = np.zeros(squarePulse.shape, dtype = int)
centerX, centerY = int((squarePulse.shape[0])/2),int((squarePulse.shape[1])/2)
filter_length = centerX*0.5
for i in range (H.shape[0]):
for j in range (H.shape[1]):
if ((centerX - i)**2 + (centerY - j)**2)**0.5 <= filter_length:
H[i,j] = 1
Ffiltrado = changeFormat.im2uint8(absfftsquarePulse)*H
kernelLength = 7
newImage = np.zeros(image.shape)
w = np.zeros((kernelLength, kernelLength), dtype=int)
w_center = int((w.shape[0]) / 2)
for indexrow, frow in enumerate(image[:-(w_center * 2)]):
for indexcolumn, fcolumn in enumerate(frow[:-(w_center * 2)]):
maskLocal = image[indexrow:1 + indexrow + w_center * 2,
indexcolumn:1 + indexcolumn + w_center * 2]
meanMask = np.mean(maskLocal + w)
k = np.clip(1 - (stdRect / (0.001 + maskLocal.std())), 0,
1) # minimo é zero e maximo é 1
newImage[
indexrow + w_center, indexcolumn + w_center] = meanMask + k * (
image[indexrow + w_center, indexcolumn + w_center] - meanMask)
info.showImageStyle(1, 2, {
'I1': changeFormat.im2uint8(I1),
'newImage': changeFormat.im2uint8(newImage)
}, ['Original', 'Image Filtered'])
#%% Função zero bala Filtro de Lee (esse é mais rapido)
newImage = filters.LeeFilter(I1, 9, True)
#%% DESAFIO
sobel_Image = changeFormat.uint2double(filters.sobel(I1))
meanI1 = changeFormat.uint2double(filters.meanFilterFast(I1, 8))
challenge = meanI1 + sobel_Image * (I1 - meanI1)
info.showImageStyle(1, 2, {
'I1': changeFormat.im2uint8(I1),
'challenge': changeFormat.im2uint8(challenge)
}, ['Original', 'Challenge'])
plt.subplot(122)
plt.imshow(w_Gauss2D1)
plt.title('Gaussian Filter')
plt.show()
#%% 3 - Convolução mamo e kernel
mamo = imageio.imread(r'ImagensAulas\Mamography.pgm')
w_Gauss2Dnorm = w_Gauss2D / w_Gauss2D.sum()
mamoConv = ndimage.convolve(mamo, w_Gauss2Dnorm)
info.showImageStyle(1,
1, {'mamoConv': mamoConv}, ['Mamo Gaussian Filter'],
title='Mamo Gaussian Filter')
#%% Função mascara gaussiana
w_Gauss2D = filters.kernelGauss(10, 5, A=1)
info.showImageStyle(1, 1, {'w_Gauss2D': changeFormat.im2uint8(w_Gauss2D)},
['w_Gauss2D'])
#%% Convolucao com mascara gaussiana gerada no item acima
mamoConv = ndimage.convolve(mamo, w_Gauss2D)
info.showImageStyle(1, 1, {'mamoConv': mamoConv}, ['mamoConv'])
#%% 4 -Afiamento de bordas
imri = imageio.imread(r'ImagensAulas\TransversalMRI2.pgm')
imri = changeFormat.uint2double(
imri) # Conversão para double para não dar ruim
mask = filters.kernelGauss(8, 3, A=1)
f_blur = ndimage.convolve(imri, mask)
g = imri - f_blur
f_sharpened = (imri + g).clip(0, 1)
images = {