def ruleBasedMapping(type_semantic_seg_rule, type_OCR_rule, type_scene_rule,
list_semantic_segmentation, list_OCR, list_scene,
needed_elements):
polys_to_obfuscate = []
if len(list_semantic_segmentation) > 0:
if type_semantic_seg_rule == "simple_list":
print("Dealing with the polygons from semantic segmentation.")
list_private_deeplab_labels = ["person, individual, someone, somebody, mortal, soul", \
"car, auto, automobile, machine, motorcar", \
"bus, autobus, coach, charabanc, double-decker, jitney, motorbus, ", \
"motorcoach, omnibus, passenger vehicle", "truck, motortruck", "van",
"conveyer belt, conveyor belt, conveyer, conveyor, transporter", "minibike, motorbike", \
"bicycle, bike, wheel, cycle", "poster, posting, placard, notice, bill, card", \
"signboard sign", "bulletin board, notice board", \
"screen door, screen", "screen, silver screen, projection screen", \
"crt screen", "plate", "monitor, monitoring device", \
"bookcase", "blind, screen", "book", "computer, computing machine, computing device, data processor ", \
"electronic computer, information processing system", \
"television receiver, television, television set, tv, tv set, idiot ", \
"trade name, brand name, brand, marque", "flag"]
for poly in list_semantic_segmentation:
#print("TODO: add filter per confidence score")
if poly[1] in list_private_deeplab_labels:
for poly_elem in poly[0]:
if poly_elem[
0].area > 4.0: # Check that the size of the polygons is large enough to actually see anything on the images.
#print(poly[1])
polys_to_obfuscate.append(poly_elem[0])
#print("TODO: check a surface size to filter out polygons.")
if len(list_OCR) > 0:
if type_OCR_rule == "simple_rule":
print("Dealing with the polygons from OCR.")
for text_recognized in list_OCR:
poly_text = text_recognized[0]
#print(poly_text)
possible_values = text_recognized[1]
for potential_value in possible_values:
# Check whether the string is actually not just one letter or a space.
string_without_space = potential_value.translate(
{ord(c): None
for c in string.whitespace})
if (len(string_without_space) > 1):
#print(potential_value)
### Obfuscate any number
# count number of digits in the string:
nb_digit = sum(
list(
map(lambda x: 1 if x.isdigit() else 0,
set(potential_value))))
if nb_digit > 3: # This is a parameter to tune. for now, 4 corresponds to a year, we will put 6 digits minimum because it corresponds to a birth date and phone numbers have even more numbers.
#print(potential_value)
polys_to_obfuscate.append(
Polygon([(poly_text[0], poly_text[1]),
(poly_text[2], poly_text[1]),
(poly_text[2], poly_text[3]),
(poly_text[0], poly_text[3])]))
break
# Obfuscate any element recognized as a location or organization or person.
continuous_chunk_1 = OCR_u.NERWithOldStanford(
potential_value)
continuous_chunk_2 = OCR_u.NERNewVersion(
potential_value)
list_recognized_entities_1 = [
chunk[1] for chunk in continuous_chunk_1
]
list_recognized_entities_2 = [
chunk[1] for chunk in continuous_chunk_2
]
list_recognized_entities = list_recognized_entities_1 + list_recognized_entities_2
if ("LOCATION" in list_recognized_entities) or \
("PERSON" in list_recognized_entities) or \
("ORGANIZATION" in list_recognized_entities) or \
("GPE" in list_recognized_entities) :
#print(potential_value, list_recognized_entities)
polys_to_obfuscate.append(
Polygon([(poly_text[0], poly_text[1]),
(poly_text[2], poly_text[1]),
(poly_text[2], poly_text[3]),
(poly_text[0], poly_text[3])]))
break
# Obfuscate elements in a list of names or locations.
words = potential_value.split()
list_words = []
for value in words:
list_words += [
value,
value.upper(),
value.lower(),
value.title()
]
for word in list_words:
# Get each word from the extracted strings and check for similarity
similar_words = difflib.get_close_matches(
word,
needed_elements["lines"],
n=3,
cutoff=0.9)
if len(similar_words) > 0:
#print(potential_value, similar_words)
polys_to_obfuscate.append(
Polygon([(poly_text[0], poly_text[1]),
(poly_text[2], poly_text[1]),
(poly_text[2], poly_text[3]),
(poly_text[0], poly_text[3])]))
break
if len(similar_words) > 0:
break
# Obfuscate elements that are next to "name" or "date". # Let's thnk about that later...
#print("TO IMPLEMENT")
elif type_OCR_rule == "simplest_rule":
print("Dealing with the polygons from OCR.")
# Obfuscate all text that is diffeernt from ""
for text_recognized in list_OCR:
poly_text = text_recognized[0]
possible_values = text_recognized[1]
for potential_value in possible_values:
if potential_value.strip():
polys_to_obfuscate.append(
Polygon([(poly_text[0], poly_text[1]),
(poly_text[2], poly_text[1]),
(poly_text[2], poly_text[3]),
(poly_text[0], poly_text[3])]))
break
return polys_to_obfuscate
def postProcessOCROutputs(OCR_outputs, needed_elements):
OCR_processed_output = []
for text_recognized in OCR_outputs:
poly_text = text_recognized[0]
#print(poly_text)
possible_values = list(set(text_recognized[1]))
#print(possible_values)
for potential_value in possible_values:
# Check whether the string is actually not just one letter or a space.
string_without_space = potential_value.translate(
{ord(c): None
for c in string.whitespace})
if (len(string_without_space) > 1):
#print(potential_value)
### Obfuscate any number
# count number of digits in the string:
nb_digit = sum(
list(
map(lambda x: 1 if x.isdigit() else 0,
set(potential_value))))
if nb_digit > 3: # This is a parameter to tune. for now, 4 corresponds to a year, we will put 6 digits minimum because it corresponds to a birth date and phone numbers have even more numbers.
#print(potential_value)
OCR_processed_output.append((Polygon([
(poly_text[0], poly_text[1]),
(poly_text[2], poly_text[1]),
(poly_text[2], poly_text[3]),
(poly_text[0], poly_text[3])
]), potential_value, "hasNumbers"))
break
# Obfuscate any element recognized as a location or organization or person.
continuous_chunk_1 = OCR_u.NERWithOldStanford(potential_value)
continuous_chunk_2 = OCR_u.NERNewVersion(potential_value)
list_recognized_entities_1 = [
chunk[1] for chunk in continuous_chunk_1
]
list_recognized_entities_2 = [
chunk[1] for chunk in continuous_chunk_2
]
list_recognized_entities = list_recognized_entities_1 + list_recognized_entities_2
if ("LOCATION" in list_recognized_entities) or \
("PERSON" in list_recognized_entities) or \
("ORGANIZATION" in list_recognized_entities) or \
("GPE" in list_recognized_entities) :
#print(potential_value, list_recognized_entities)
if ("LOCATION" in list_recognized_entities):
OCR_processed_output.append((Polygon([
(poly_text[0], poly_text[1]),
(poly_text[2], poly_text[1]),
(poly_text[2], poly_text[3]),
(poly_text[0], poly_text[3])
]), potential_value, "LOCATION"))
break
elif ("PERSON" in list_recognized_entities):
OCR_processed_output.append((Polygon([
(poly_text[0], poly_text[1]),
(poly_text[2], poly_text[1]),
(poly_text[2], poly_text[3]),
(poly_text[0], poly_text[3])
]), potential_value, "PERSON"))
break
elif ("ORGANIZATION" in list_recognized_entities):
OCR_processed_output.append((Polygon([
(poly_text[0], poly_text[1]),
(poly_text[2], poly_text[1]),
(poly_text[2], poly_text[3]),
(poly_text[0], poly_text[3])
]), potential_value, "ORGANIZATION"))
break
elif ("GPE" in list_recognized_entities):
OCR_processed_output.append((Polygon([
(poly_text[0], poly_text[1]),
(poly_text[2], poly_text[1]),
(poly_text[2], poly_text[3]),
(poly_text[0], poly_text[3])
]), potential_value, "GPE"))
break
# Obfuscate elements in a list of names or locations.
words = potential_value.split()
list_words = []
for value in words:
list_words += [
value,
value.upper(),
value.lower(),
value.title()
]
for word in list_words:
similar_words = ""
if len(
word
) > 3: # This is a design choice to avoid small words...
# Get each word from the extracted strings and check for similarity
similar_words = difflib.get_close_matches(
word,
needed_elements["lines_names"],
n=3,
cutoff=0.9)
if len(similar_words) > 0:
#print(potential_value, similar_words)
OCR_processed_output.append((Polygon([
(poly_text[0], poly_text[1]),
(poly_text[2], poly_text[1]),
(poly_text[2], poly_text[3]),
(poly_text[0], poly_text[3])
]), potential_value, "PERSON"))
break
similar_words = difflib.get_close_matches(
word,
needed_elements["lines_location"],
n=3,
cutoff=0.9)
if len(similar_words) > 0:
#print(potential_value, similar_words)
OCR_processed_output.append((Polygon([
(poly_text[0], poly_text[1]),
(poly_text[2], poly_text[1]),
(poly_text[2], poly_text[3]),
(poly_text[0], poly_text[3])
]), potential_value, "LOCATION"))
break
if len(similar_words) > 0:
break
return OCR_processed_output