suffix = "frames/x40/"
save_path = "/home/fred/Projects/srt-cancer-img/pair-data/output/"
# normalizers
normalizer_rd = stainNorm_Reinhard.Normalizer()
normalizer_mk = stainNorm_Macenko.Normalizer()
normalizer_vd = vahadane.vahadane()
for dirname in listdir(source_path):
if 'A06' in dirname:
print("Processing directory ", dirname)
imgs = [f for f in listdir(join(source_path, dirname, suffix))]
for img in imgs[1:]:
source = stain_utils.read_image(
join(source_path, dirname, suffix, img))
target = stain_utils.read_image(
join(source_path, dirname.replace('A', 'H', 1), suffix,
img.replace('A', 'H', 1)))
print("Processing image: ", img)
# load and fit target img
normalizer_rd.fit(target)
normalizer_mk.fit(target)
Wt, Ht = normalizer_vd.stain_separate(target)
# reinhard
out = normalizer_rd.transform(source)
out = cv.cvtColor(out, cv.COLOR_RGB2BGR)
cv.imwrite(join(save_path, "reinhard", img), out)
import numpy as np
import matplotlib.pyplot as plt
norm = stainNorm_Macenko.normalizer(
) # normalizer() is the algorithm function for Macenko
print("BENIGN")
for i in range(0, 69): # since we have 69 images in benign class
path = "Benign" + "/" #input path for images
path_norm = "Benign_m_norm" + "/" #output path to keep the normalised output
n = "t" + str(i) + ".tif" # image name
fullpath = path + n # path to the input image
fullpath_norm = path_norm + n # output path to the normalised image
print(fullpath)
print(fullpath_norm)
i1 = utils.read_image(fullpath) # for reading images as arrays
if (i == 0):
#print(i1)
norm.fit(
i1
) # for the first image we read, we need to fit the Mackenko normaliser() function in accordance with the first image so that we can normalise other images on this basis...norm.fit() actually
# comes up with the values of mean and sd so that we can normalise the images.
io.imsave((fullpath_norm), i1) #save the first image
else:
i2 = norm.transform(
i1) # apply the Mackenko transformation algorithm for the image
io.imsave((fullpath_norm), i2) # save the image
print("IN SITU")
