Benjamin_Loison/Robust_image_source_identification_on_modern_smartphones
1
0
Fork 0
Code Issues 68 Pull Requests Packages Projects Releases Wiki Activity

Compute automatically extreme values

Browse Source
This commit is contained in:
Benjamin Loison 2024-04-16 03:11:38 +02:00
parent a8fa053687
commit d4e13ed123
No known key found for this signature in database
1 changed files with 16 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
datasets/raise/extract_noise.py
View File

@ -33,10 +33,11 @@ if requiresRaiseFiltering:
imagesFileNames = [imageFileName for imageFileName in tqdm(imagesFileNames, 'Filtering images') if files[imageFileName]['Device'] == 'Nikon D7000' and Image.open(f'{imagesFolderPath}/{imageFileName}').size == (4946, 3278)]
minGreen = 308#None
minColor = None
maxColor = None
def treatImage(imageFileName):
global mean, numberOfImagesInMean, minGreen
def treatImage(imageFileName, computeExtremes = False):
global mean, numberOfImagesInMean, minColor, maxColor
imageFilePath = f'{imagesFolderPath}/{imageFileName}'
if imageFileName.endswith('.NEF'):
with rawpy.imread(imageFilePath) as raw:
@ -45,22 +46,22 @@ def treatImage(imageFileName):
assert np.array_equal(raw.raw_pattern, np.array([[0, 1], [3, 2]], dtype = np.uint8))
rawImageVisible = raw.raw_image_visible.copy()
greenRawImageVisible = rawImageVisible[1::2, ::2]
'''
greenRawImageVisibleMin = greenRawImageVisible.min()
if minGreen is None or greenRawImageVisibleMin < minGreen:
minGreen = greenRawImageVisibleMin
print(minGreen)
'''
imageNpArray = (greenRawImageVisible - minGreen) / (4908 - minGreen)
if computeExtremes:
greenRawImageVisibleMin = greenRawImageVisible.min()
greenRawImageVisibleMax = greenRawImageVisible.max()
if minColor is None or greenRawImageVisibleMin < minColor:
minColor = greenRawImageVisibleMin
if maxColor is None or greenRawImageVisibleMax > maxColor:
maxColor = greenRawImageVisibleMax
return
imageNpArray = (greenRawImageVisible - minGreen) / (maxGreen - minGreen)
# Pay attention to range of values expected by the denoiser.
# Indeed if provide the thousands valued raw image, then the denoiser only returns values between 0 and 1 and making the difference between both look pointless.
#exit(1)
else:
imagePil = Image.open(imageFilePath)
imageNpArray = img_as_float(np.array(imagePil))
# As the arguments differ from a denoiser to the other should use a match instead.
imageDenoisedNpArray = denoise(imageNpArray, rescale_sigma=True)
#print(imageNpArray, imageDenoisedNpArray)
imageNoiseNpArray = imageNpArray - imageDenoisedNpArray
if mean is None:
mean = imageNoiseNpArray
@ -68,6 +69,9 @@ def treatImage(imageFileName):
mean = ((mean * numberOfImagesInMean) + imageNoiseNpArray) / (numberOfImagesInMean + 1)
numberOfImagesInMean += 1
for imageFileName in tqdm(imagesFileNames, 'Computing extremes of images'):
treatImage(imageFileName, computeExtremes = True)
for imageFileName in tqdm(imagesFileNames, 'Denoising images'):
treatImage(imageFileName)