def test_duplication2(self):
expected = 0
img1 = SuspiciousImage(os.path.join(DIR, 'test/image/yrc_16.png'))
img2 = SuspiciousImage(os.path.join(DIR, 'test/image/yrc_5_po.png'))
detector = Duplication()
actual = detector.detect(img1, img2)
self.assertEqual(expected, actual)
def test_photopick(self):
expected = [1, 0]
img1 = SuspiciousImage(os.path.join(DIR, 'test/image/yrc_16.png'))
img2 = SuspiciousImage(os.path.join(DIR, 'test/image/graph.png'))
detector = PhotoPick()
actual = detector.detect([img1, img2])
self.assertEqual(expected[0], actual[0])
self.assertEqual(expected[1], actual[1])
def test_duplication(self):
expected = 1
img1 = SuspiciousImage(os.path.join(DIR, 'test/image/yrc_16.png'))
img2 = SuspiciousImage(
os.path.join(DIR, 'test/image/yrc_16_60degree.png'))
detector = Duplication()
actual = detector.detect(img1, img2)
detector.save_image(
os.path.join(DIR, 'test/image/duplication_result.jpg'))
self.assertEqual(expected, actual)
def test_cutpaste(self):
# TODO: re-traing a model
expected = [0, 1]
img1 = SuspiciousImage(
os.path.join(DIR, 'test/image/yrc_1000_505_cp.png'))
img2 = SuspiciousImage(os.path.join(DIR, 'test/image/yrc_16.png'))
detector = CutPaste()
actual = detector.detect([img1, img2])
print(actual)
self.assertEqual(expected[0], actual[0])
self.assertEqual(expected[1], actual[1])
def extraction(PMC_DIRs, from_where='from_pdf'):
detector = PhotoPick()
for PMC_DIR in PMC_DIRs:
print(PMC_DIR)
# from PDF files
files = glob.glob(os.path.join(PMC_DIR, '*.pdf'))
if len(files) > 0:
pdf_file = files[0]
SAVE_DIR = mkdir(os.path.join(PMC_DIR, from_where))
extract_img_from_pdf(pdf_file, SAVE_DIR)
# # from JPEG images #
# image_files = glob.glob(os.path.join(PMC_DIR, '*.jpg'))
# if len(image_files) > 0:
# SAVE_DIR = mkdir(PMC_DIR, 'from_jpg')
# Dismantler().dismantle(image_files, SAVE_DIR)
subimgs_path = glob.glob(
os.path.join(PMC_DIR, from_where, 'subimg_cut', '*.png'))
photo_DIR = mkdir(os.path.join(PMC_DIR, 'photo'))
other_DIR = mkdir(os.path.join(PMC_DIR, from_where, 'other'))
suspicious_imgs = [
SuspiciousImage(img_path) for img_path in subimgs_path
]
if len(suspicious_imgs) is 0:
print("No images")
continue
pred = detector.detect(suspicious_imgs)
for i, p in enumerate(pred):
if p == 1:
shutil.copy(subimgs_path[i], photo_DIR)
elif p == 0:
shutil.copy(subimgs_path[i], other_DIR)
def test_paintout1(self):
expected = 1
img1 = SuspiciousImage(os.path.join(DIR, 'test/image/yrc_5_po.png'))
detector = Clipping()
actual = detector.detect(img1)
detector.save_image(os.path.join(DIR,
'test/image/paintout_result.jpg'))
self.assertEqual(expected, actual)
def test_copymove(self):
expected = 1
img1 = SuspiciousImage(os.path.join(DIR, 'test/image/yrc_7_cm.png'))
detector = CopyMove()
actual = detector.detect(img1)
detector.save_image(os.path.join(DIR,
'test/image/copymove_result.jpg'))
self.assertEqual(expected, actual)
def test_paintout0(self):
expected = 0
img1 = SuspiciousImage(os.path.join(DIR, 'test/image/yrc_16.png'))
detector = Clipping()
actual = detector.detect(img1)
self.assertEqual(expected, actual)
def test_copymove2(self):
expected = 0
img1 = SuspiciousImage(os.path.join(DIR, 'test/image/yrc_16.png'))
detector = CopyMove()
actual = detector.detect(img1)
self.assertEqual(expected, actual)
def detection(post_id):
""" zipファイル展開 """
file = File.objects.get(pk=post_id)
p_id = post_id % 10
OUT_DIR = os.path.join(BASE_DIR, 'media', 'images', str(p_id))
if os.path.exists(OUT_DIR):
shutil.rmtree(OUT_DIR)
os.makedirs(OUT_DIR)
if file.zip.path.split('.')[-1] == 'zip':
with zipfile.ZipFile(os.path.join(BASE_DIR,
file.zip.path)) as existing_zip:
existing_zip.extractall(OUT_DIR)
# TODO: fix
images_path = glob.glob(os.path.join(OUT_DIR, '*', '*'))
images_path = [
p for p in images_path
if p.split('.')[-1] in ['jpg', 'png', 'tif', 'JPG', 'JPEG', 'TIF']
]
images_url = list(map(lambda x: x.split('media/')[-1], images_path))
# images_name = list(map(lambda x: x.split(
# '/')[-1].split('.')[0], images_url))
print(images_url)
elif file.zip.path.split('.')[-1] in [
'jpg', 'png', 'tif', 'JPG', 'JPEG', 'TIF'
]:
images_path = [file.zip.path]
else:
return 0
print('loaded')
RESULT_DIR = os.path.join(BASE_DIR, 'media', 'results', str(p_id))
if os.path.exists(RESULT_DIR):
shutil.rmtree(RESULT_DIR)
os.makedirs(RESULT_DIR)
# # pdfファイル展開
# if file.zip.path.split('.')[-1] == 'pdf' or file.zip.path.split('.')[-1] == 'PDF':
# images = imgminer(file.zip.path, OUT_DIR)
# """ 図の分割 """
# if len(images_path) > 0:
# Dismantler().dismantle(images_path, EXTRACT_DIR)
# subimgs_path = glob.glob(os.path.join(EXTRACT_DIR, 'subimg_cut', '*.png'))
# suspicious_images = [
# SuspiciousImage(img_path) for img_path in subimgs_path]
# if len(suspicious_images) is 0:
# print("No images")
# return 0
# detector = PhotoPick(
# model_name=os.path.join(
# MODEL_DIR, 'photopicker_rf_lee_2700.sav'),
# param_name=os.path.join(
# MODEL_DIR, 'photopicker_rf_lee_2700.sav-param.npz'))
# pred = detector.detect(suspicious_images)
# suspicious_images = [img for i, img in enumerate(
# suspicious_images) if pred[i] == 1]
suspicious_images = [
SuspiciousImage(path, nfeatures=5000) for path in images_path
]
print(suspicious_images)
len_sus = len(suspicious_images)
# """ 画像の切り出し """
# images = splitting(images)
""" Detection """
# Detectors #
# detector_no = Noise(
# model_name=os.path.join(
# MODEL_DIR,
# 'noise_oneclass_42.sav'))
detector_cl = Clipping(min_area=100)
detector_cm = CopyMove(min_kp=20,
min_match=20,
min_key_ratio=0.75,
flags=0)
detector_du = Duplication(min_kp=20,
min_match=20,
min_key_ratio=0.75,
flags=0)
# detector_cp = CutPaste(
# model_name=os.path.join(
# MODEL_DIR, 'cutpaste_svm_uci_200.sav'), param_name=os.path.join(
# MODEL_DIR, 'cutpaste_svm_uci_200.sav-param.npz'), )
for img in suspicious_images:
dsize = (img.w, img.h)
# Clipping check #
pred = detector_cl.detect(img)
img.clipping = pred
if pred is 1:
ratio = detector_cl.ratio_
img.area_ratio = ratio
img.cl_img = cv.resize(detector_cl.image_, dsize=dsize)
# Copy-move check #
pred = detector_cm.detect(img)
img.copymove = pred
if pred is 1:
ratio = detector_cm.mask_ratio_
img.mask_ratio = ratio
img.cm_img = cv.resize(detector_cm.image_, dsize=dsize)
print('detected')
for img in suspicious_images:
nameroot = img.name
dsize = (img.w, img.h)
suspicious = Suspicious()
suspicious.post_id = p_id
suspicious.w, suspicious.h = dsize
suspicious.name = img.name
suspicious.size = img.size
file_name = os.path.join(RESULT_DIR, '{}.jpg'.format(nameroot))
cv.imwrite(file_name, cv.resize(img.mat, dsize=dsize))
suspicious.original = file_name.split('media/')[-1]
# suspicious.noise = img.noise
file_name = os.path.join(RESULT_DIR, '{}_no.jpg'.format(nameroot))
cv.imwrite(file_name, img.no_img)
suspicious.no_img = file_name.split('media/')[-1]
# suspicious.no_img = img.no_img
suspicious.clipping = img.clipping
if img.clipping:
file_name = os.path.join(RESULT_DIR, '{}_cl.jpg'.format(nameroot))
cv.imwrite(file_name, img.cl_img)
suspicious.cl_img = file_name.split('media/')[-1]
else:
suspicious.cl_img = suspicious.original
suspicious.area_ratio = int(img.area_ratio * 100)
suspicious.copymove = img.copymove
if suspicious.copymove:
file_name = os.path.join(RESULT_DIR, '{}_cm.jpg'.format(nameroot))
cv.imwrite(file_name, img.cm_img)
suspicious.cm_img = file_name.split('media/')[-1]
else:
suspicious.cm_img = suspicious.original
suspicious.mask_ratio = int(img.mask_ratio * 100)
# suspicious.cutpaste = img.cutpaste
file_name = os.path.join(RESULT_DIR, '{}_cp.jpg'.format(nameroot))
cv.imwrite(
file_name,
cv.resize(img.keyimg[img.gap:-img.gap, img.gap:-img.gap],
dsize=dsize))
suspicious.cp_img = file_name.split('media/')[-1]
suspicious.save()
print('saved')
### Duplication check ###
n_dp = 0
for i in range(len_sus):
img = suspicious_images[i]
imgname = img.name
for j in range(i + 1, len_sus):
pred = detector_du.detect(suspicious_images[j], img)
if pred is 1:
file_name = os.path.join(
RESULT_DIR,
'{}_{}_duplication.jpg'.format(suspicious_images[j].name,
imgname))
detector_du.save_image(file_name)
suspicious = SuspiciousDuplication()
suspicious.post_id = p_id
suspicious.name1 = suspicious_images[j].name
suspicious.name2 = imgname
suspicious.du_img = file_name.split('media/')[-1]
suspicious.mask_ratio = int(detector_du.mask_ratio_ * 100)
suspicious.save()
n_dp = n_dp + 1
# for i in range(len(images)):
# imgname = images[i].name.split('/')[-1]
# img = images[i]
#
#
# ### Painting-out check ###
# isPaintingOut, img_detect = paintout(images[i])
# if isPaintingOut:
# result_path = os.path.join(RESULT_DIR, imgname.split('.')[0] + '_po.jpg')
# result_url = result_path.split('media/')[-1]
# cv.imwrite(result_path, img_detect)
# photo = Photo()
# photo.name = imgname
# photo.result = result_url
# photo.title = 'Over-adjustment of contrast/brightness or painting-out'
# photo.ratio = 50
# photo.save()
# continue
# print('paintingout')
#
# ### Copy-move check ###
# isCopyMove, img_detect = copymove(img)
# if isCopyMove:
# result_path = os.path.join(Duplication.RESULT_DIR, imgname.split('.')[0] + '_cm.jpg')
# result_url = result_path.split('media/')[-1]
# cv.imwrite(result_path, img_detect)
# photo = Photo()
# photo.name = imgname
# photo.result = result_url
# photo.title = 'Reuse within a same image'
# photo.ratio = 50
# photo.save()
# print('copymove')
#
# print('DONE: ', imgname)
#
# print(Photo.objects.all())
return len_sus, n_dp
def detection(MODEL_DIR,
REPORT_DIR,
PMC_DIRs,
log_file_name,
wave_thres=488,
gap=32):
# Detectors #
detector_cl = Clipping()
detector_no = Noise(model_name=MODEL_DIR + 'noise_oneclass_42.sav')
detector_cm = CopyMove(min_kp=20, min_match=20, min_key_ratio=0.75)
detector_du = Duplication(min_kp=20, min_match=20, min_key_ratio=0.75)
detector_cp = CutPaste(
model_name=MODEL_DIR + 'cutpaste_svm_uci_200.sav',
param_name=MODEL_DIR + 'cutpaste_svm_uci_200.sav-param.npz',
)
log = []
for PMC_DIR in PMC_DIRs:
OUT_DIR = os.path.join(PMC_DIR, 'output')
if os.path.exists(OUT_DIR):
shutil.rmtree(OUT_DIR)
os.makedirs(OUT_DIR)
PMCID = os.path.basename(PMC_DIR)
# Load images #
images_path = glob.glob(os.path.join(PMC_DIR, 'photo', '*.png'))
if len(images_path) is 0:
print(PMC_DIR, "No images.")
log.append([PMCID, 0, 0, 0, 0, 0, 0, 0])
continue
suspicious_images = [
SuspiciousImage(path,
hist_eq=True,
algorithm='orb',
nfeatures=2000,
gap=gap) for path in images_path
]
len_sus = len(suspicious_images)
# Report #
report = pd.DataFrame(0,
index=[img.name for img in suspicious_images],
columns=[
'Clipping',
'area_ratio',
'CopyMove',
'mask_ratio',
'CutPaste',
'proba',
'Duplication',
])
for i in range(len_sus):
img = suspicious_images[i]
imgname = img.name
# Paint-out (blown-out highlights, clipping) check #
pred = detector_cl.detect(img)
report.loc[imgname, 'Clipping'] = pred
img.clipping = pred
if pred is 1:
ratio = detector_cl.ratio_
report.loc[imgname, 'area_ratio'] = ratio
img.area_ratio = ratio
file_name = os.path.join(OUT_DIR,
'{}_clipping.jpg'.format(imgname))
detector_cl.save_image(file_name)
img.cl_img = detector_cl.image_
# Copy-move check #
pred = detector_cm.detect(img)
report.loc[imgname, 'CopyMove'] = pred
img.copymove = pred
if pred is 1:
ratio = detector_cm.mask_ratio_
report.loc[imgname, 'mask_ratio'] = ratio
img.mask_ratio = ratio
file_name = os.path.join(OUT_DIR,
'{}_copymove.jpg'.format(imgname))
detector_cm.save_image(file_name)
img.cm_img = detector_cm.image_
# Noise check #
report['Noise'] = detector_no.detect(suspicious_images)
report['dist'] = detector_no.dist_
for i, img in enumerate(suspicious_images):
img.noise = report.Noise[i]
# Cut-paste check #
enough_size_images = [
img for img in suspicious_images if img.gray.shape[0] >= wave_thres
and img.gray.shape[1] >= wave_thres
]
if len(enough_size_images) > 0:
results = detector_cp.detect(enough_size_images)
probas = detector_cp.proba_
for i, img in enumerate(enough_size_images):
img.cutpaste = results[i]
img.prob = probas[i]
for i, img in enumerate(suspicious_images):
report.iloc[i, 4] = img.cutpaste
report.iloc[i, 5] = img.prob
# Duplication check #
# flip_images = [
# SuspiciousImage().make_flip(img.mat, img.name + '-flip')
# for img in suspicious_images]
result_imgnames = []
result_imgarrs = []
result_ratios = []
for i in range(len_sus):
img = suspicious_images[i]
imgname = img.name
for j in range(i + 1, len_sus):
pred = detector_du.detect(suspicious_images[j], img)
report.loc[imgname, 'Duplication'] += pred
if pred is 1:
file_name = os.path.join(
OUT_DIR, '{}_{}_duplication.jpg'.format(
suspicious_images[j].name, imgname))
detector_du.save_image(file_name)
result_imgnames.append(
[suspicious_images[j].name, imgname])
result_imgarrs.append(detector_du.image_)
result_ratios.append(detector_du.mask_ratio_)
# # flipped images
# pred = detector_du.detect(
# img, flip_images[j])
# report.loc[imgname, 'Duplication'] += pred
# if pred:
# file_name = os.path.join(
# OUT_DIR, '{}_{}_duplication.jpg'.format(
# imgname, flip_images[j].name))
# detector_du.save_image(file_name)
# result_imgnames.append([imgname, flip_images[j].name])
# result_imgarrs.append(detector_du.image_)
# result_ratios.append(detector_du.mask_ratio_)
# Output report #
print(PMC_DIR, len(glob.glob(os.path.join(OUT_DIR, '*.jpg'))))
report.to_csv(
os.path.join(PMC_DIR,
'report_{}.csv'.format(os.path.basename(PMC_DIR))))
report = report[report == 1].sum()
len_output = len(glob.glob(os.path.join(OUT_DIR, '*.jpg')))
log.append([
PMCID, len_sus, len_output, report['Clipping'], report['CopyMove'],
report['Duplication'], report['CutPaste'], report['Noise']
])
for i, img in enumerate(suspicious_images):
plot_report(img, len_sus, i, PMCID, REPORT_DIR)
if len(result_ratios) > 0:
plot_duplication_report(result_imgnames, result_imgarrs,
result_ratios, PMCID, REPORT_DIR)
log = pd.DataFrame(log)
log.columns = [
'PMCID', 'Extracted', 'Suspicious', 'Clipping', 'CopyMove',
'Duplication', 'CutPaste', 'Noise'
]
log.to_csv(os.path.join(DIR, log_file_name))