Benjamin_Loison/Robust_image_source_identification_on_modern_smartphones
1
0
Fork 0
Code Issues 69 Pull Requests Packages Projects Releases 1 Wiki Activity

#63: WIP

Browse Source
This commit is contained in:
Benjamin Loison
2024-04-30 05:01:05 +02:00
parent 319ca8fb60
commit b6425b426e
1 changed files with 28 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

41
datasets/raise/attribute_source_camera.py
View File

@@ -25,32 +25,30 @@ imagesCamerasFileNames = {camera: os.listdir(imageCameraFolder) for camera, imag
random.seed(0)
# To not have a bias (chronological for instance) when split to make training and testing sets.
for camera in IMAGES_CAMERAS_FOLDER:
#print(imagesCamerasFileNames[camera][:3])
random.shuffle(imagesCamerasFileNames[camera])
#print(imagesCamerasFileNames[camera][:3])
#exit(1)
minimumNumberOfImagesCameras = 10#min([len(imagesCamerasFileNames[camera]) for camera in IMAGES_CAMERAS_FOLDER])
#print(minimumNumberOfImagesCameras)
#exit(1)
for camera in IMAGES_CAMERAS_FOLDER:
IMAGES_CAMERAS_FOLDER[camera] = IMAGES_CAMERAS_FOLDER[camera][:minimumNumberOfImagesCameras]
numberOfCameras = len(IMAGES_CAMERAS_FOLDER)
camerasIterativeMean = [iterativeMean() for _ in range(numberOfCameras)]
camerasIterativeMean = {camera: iterativeMean() for camera in IMAGES_CAMERAS_FOLDER}
minColor = None
maxColor = None
accuracy = []
numberOfTrainingImages = int(minimumNumberOfImagesCameras * TRAINING_PORTION)
numberOfTestingImages = minimumNumberOfImagesCameras - int(minimumNumberOfImagesCameras * TRAINING_PORTION)
cameraTestingImagesNoise = {}#{camera: [] for camera in IMAGES_CAMERAS_FOLDER}
returnSingleColorChannelImage = lambda singleColorChannelImage, _minColor, _maxColor: singleColorChannelImage
for computeExtremes in tqdm(([True] if minColor is None or maxColor is None else []) + [False], 'Compute extremes'):
rescaleIfNeeded = returnSingleColorChannelImage if computeExtremes else rescaleRawImageForDenoiser
for cameraImageIndex in tqdm(range(minimumNumberOfImagesCameras * TRAINING_PORTION), 'Camera image index'):
for cameraIndex, camera in enumerate(tqdm(IMAGES_CAMERAS_FOLDER, 'Camera')):
imageFileName = imagesCamerasFileNames[camera][cameraImageIndex]
for cameraTrainingImageIndex in tqdm(range(minimumNumberOfImagesCameras if computeExtremes else numberOfTrainingImages), 'Camera training image index'):
for camera in tqdm(IMAGES_CAMERAS_FOLDER, 'Camera'):
imageFileName = imagesCamerasFileNames[camera][cameraTrainingImageIndex]
imageFilePath = f'{IMAGES_CAMERAS_FOLDER[camera]}/{imageFileName}'
singleColorChannelImages = {color: rescaleIfNeeded(getColorChannel(imageFilePath, color), minColor, maxColor) for color in Color}
multipleColorsImage = mergeSingleColorChannelImagesAccordingToBayerFilter(singleColorChannelImages)
@@ -63,16 +61,33 @@ for computeExtremes in tqdm(([True] if minColor is None or maxColor is None else
multipleColorsDenoisedImage = mergeSingleColorChannelImagesAccordingToBayerFilter(singleColorChannelDenoisedImages)
imagePrnuEstimateNpArray = multipleColorsImage - multipleColorsDenoisedImage
cameraIterativeMean = subgroupsIterativeMean[cameraIndex]
cameraIterativeMean = camerasIterativeMean[camera]
cameraIterativeMean.add(imagePrnuEstimateNpArray)
if cameraIndex == numberOfCameras - 1:
rms = rmsDiffNumpy(subgroupIterativeMean.mean, subgroupsIterativeMean[1 - cameraIndex].mean)
rmss += [rms]
for cameraTestingImageIndex in tqdm(range(numberOfTrainingImages), 'Camera testing image index'):
singleColorChannelImages = {color: rescaleIfNeeded(getColorChannel(imageFilePath, color), minColor, maxColor) for color in Color}
multipleColorsImage = mergeSingleColorChannelImagesAccordingToBayerFilter(singleColorChannelImages)
singleColorChannelDenoisedImages = {color: denoise(singleColorChannelImages[color], DENOISER) for color in Color}
multipleColorsDenoisedImage = mergeSingleColorChannelImagesAccordingToBayerFilter(singleColorChannelDenoisedImages)
rms = rmsDiffNumpy(subgroupIterativeMean.mean, subgroupsIterativeMean[1 - cameraIndex].mean)
accuracy += [rms]
if computeExtremes:
print(f'{minColor=} {maxColor=}')
print('Extracting noise of testing images')
for camera in tqdm(IMAGES_CAMERAS_FOLDER, 'Camera'):
for cameraTestingImageIndex in tqdm(range(numberOfTestingImages), 'Camera testing image index'):
imageFilePath =
singleColorChannelImages = {color: rescaleIfNeeded(getColorChannel(imageFilePath, color), minColor, maxColor) for color in Color}
multipleColorsImage = mergeSingleColorChannelImagesAccordingToBayerFilter(singleColorChannelImages)
singleColorChannelDenoisedImages = {color: denoise(singleColorChannelImages[color], DENOISER) for color in Color}
multipleColorsDenoisedImage = mergeSingleColorChannelImagesAccordingToBayerFilter(singleColorChannelDenoisedImages)
imagePrnuEstimateNpArray = multipleColorsImage - multipleColorsDenoisedImage
cameraTestingImagesNoise[camera] = cameraTestingImagesNoise.get(camera, []) + [multipleColorsDenoisedImage]
for camera in range(IMAGES_CAMERAS_FOLDER):
plt.imsave(f'{setting}_estimated_prnu_subgroup_{escapeFilePath(camera)}.png', (subgroupsIterativeMean[cameraIndex].mean))
plt.imsave(f'{setting}_estimated_prnu_subgroup_{escapeFilePath(camera)}.png', (camerasIterativeMean[camera].mean))
plt.title(f'Accuracy of camera source attribution thanks to a given number of images to estimate PRNUs with {DENOISER} denoiser')
plt.xlabel('Number of images to estimate PRNU')