def test_td3_checker(self):
# optional data hash == '0'
mrz1 = ("P<CANMARTIN<<SARAH<<<<<<<<<<<<<<<<<<<<<<<<<<\n"
"ZE000509<9CAN8501019F2301147<<<<<<<<<<<<<<08")
test1 = bool(TD3CodeChecker(mrz1))
# optional data hash == '<'
mrz2 = ("P<CANMARTIN<<SARAH<<<<<<<<<<<<<<<<<<<<<<<<<<\n"
"ZE000509<9CAN8501019F2301147<<<<<<<<<<<<<<08")
test2 = bool(TD3CodeChecker(mrz2))
self.assertEqual(test1, test2)
def validate_whole(text):
td3_check = TD3CodeChecker(text, check_expiry=True)
if td3_check:
fields = td3_check.fields()
if fields.document_type == 'P':
document_type = 'Passport'
if fields.sex == 'M':
sex = 'Male'
else:
sex = 'Female'
json_object = {
'Document Type': document_type,
'Issuing Country': fields.country,
'Surname': fields.surname,
'Name': fields.name,
'Passport Number': fields.document_number,
'Nationality': fields.nationality,
'Date Of Birth': convert_date(fields.birth_date),
'Sex': sex,
'Date Of Expiry': convert_date(fields.expiry_date),
'Personal Number': fields.optional_data,
}
return json_object
else:
return False
def autoChecker(text):
text = ''.join(text.split(' '))
data = None
t = None
try:
data = TD1CodeChecker(text)
t = 'td1'
except:
try:
data = TD2CodeChecker(text)
t = 'td2'
except:
try:
data = TD3CodeChecker(text)
t = 'td3'
except:
try:
data = MRVACodeChecker(text)
t = 'mrva'
except:
try:
data = MRVBCodeChecker(text)
t = 'mrvb'
except:
print(" Error : MRZ valide")
return data, t
def create_person():
document_type = 'P'
country_code = random_letters(3)
surname = random_letters(random.random() * 10)
given_names = random_letters(random.random() * 12)
document_number = random_letters(random.random() * 9)
nationality = random_letters(3)
birth_date = radnom_date()
sex = random_sex()
expiry_date = radnom_date()
code = TD3CodeGenerator(document_type, country_code, surname, given_names,
document_number, nationality, birth_date, sex,
expiry_date, "", {}, True)
return str(code), TD3CodeChecker(str(code), False, False).fields()
def test_td3_checker(self):
mrz_code = ("P<ASUMXHMWD<<EBDALRXHYM<<<<<<<<<<<<<<<<<<<<<\n"
"A2222222<0ASU7108215M04120411000146819<<<<44")
td3_check = TD3CodeChecker(mrz_code)
fields = td3_check.fields()
self.assertEqual("MXHMWD", fields.surname)
self.assertEqual("EBDALRXHYM", fields.name)
self.assertEqual("ASU", fields.country)
self.assertEqual("ASU", fields.nationality)
self.assertEqual("710821", fields.birth_date)
self.assertEqual("041204", fields.expiry_date)
self.assertEqual("M", fields.sex)
self.assertEqual("P", fields.document_type)
self.assertEqual("A2222222", fields.document_number)
self.assertEqual("1000146819", fields.optional_data)
self.assertEqual("5", fields.birth_date_hash)
self.assertEqual("1", fields.expiry_date_hash)
self.assertEqual("0", fields.document_number_hash)
self.assertEqual("4", fields.final_hash)
def test_td3_checker(self):
mrz_td3 = ("P<UKRTKACHENKO<<MARIANA<<<<<<<<<<<<<<<<<<<<<\n"
"XX000000<0UKR9108242F23092571234567890<<<<70")
self.assertTrue(bool(TD3CodeChecker(mrz_td3)))
#!/usr/bin/python3
# -*- coding: utf-8 -*-
from mrz.checker.td3 import TD3CodeChecker
td3_check = TD3CodeChecker("P<INPSPECIMEN<<SAMPLE<<<<<<<<<<<<<<<<<<<<<<<\n"
"XX000000<0FRA1901012F16073021234567890<<<<70")
print("\n".join(td3_check.report_errors))
def test_a_td3_checker(self):
self.assertTrue(bool(TD3CodeChecker(self.mrz_td3)))
def test_c_td3_checker(self):
self.assertFalse(
bool(
TD3CodeChecker(self.mrz_td3,
check_expiry=True,
compute_warnings=True)))
def test_b_td3_checker(self):
self.assertListEqual(
TD3CodeChecker(self.mrz_td3, check_expiry=True).report_warnings,
['document expired'])
#!/usr/bin/python3
# -*- coding: UTF-8 -*-
from mrz.checker.td3 import TD3CodeChecker
td3_check = TD3CodeChecker(
"P<CZESPECIMEN<<VZOR<<<<<<<<<<<<<<<<<<<<<<<<<\n"
"99003853<1CZE1101018M1207046110101111<<<<<94",
check_expiry=True)
print(bool(td3_check))
print(td3_check.report_warnings)
def get_passport_data(path):
# initialize a rectangular and square structuring kernel
rectKernel = cv2.getStructuringElement(cv2.MORPH_RECT, (13, 5))
sqKernel = cv2.getStructuringElement(cv2.MORPH_RECT, (27, 27))
image = cv2.imread(path)
imgHeight = image.shape[0]
imgWidth = image.shape[1]
if imgWidth < imgHeight:
image = cv2.rotate(image, rotateCode=cv2.ROTATE_90_COUNTERCLOCKWISE)
image = imutils.resize(image, height=600)
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# gray = cv2.bitwise_not(gray)
# smooth the image using a 3x3 Gaussian, then apply the blackhat
# morphological operator to find dark regions on a light background
gray = cv2.GaussianBlur(gray, (3, 3), 0)
# cv2.imshow("Gray", gray)
# cv2.waitKey()
blackhat = cv2.morphologyEx(gray, cv2.MORPH_BLACKHAT, rectKernel)
# cv2.imshow("Blackhat", blackhat)
# cv2.waitKey()
# compute the Scharr gradient of the blackhat image and scale the
# result into the range [0, 255]
gradX = cv2.Sobel(blackhat, ddepth=cv2.CV_32F, dx=1, dy=0, ksize=-1)
gradX = np.absolute(gradX)
(minVal, maxVal) = (np.min(gradX), np.max(gradX))
gradX = (255 * ((gradX - minVal) / (maxVal - minVal))).astype("uint8")
# apply a closing operation using the rectangular kernel to close
# gaps in between letters -- then apply Otsu's thresholding method
gradX = cv2.morphologyEx(gradX, cv2.MORPH_CLOSE, rectKernel)
thresh = cv2.threshold(gradX, 0, 255,
cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
# perform another closing operation, this time using the square
# kernel to close gaps between lines of the MRZ, then perform a
# serieso of erosions to break apart connected components
thresh = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, sqKernel)
# cv2.imshow("tresh", thresh)
# cv2.waitKey()
thresh = cv2.erode(thresh, None, iterations=4)
# cv2.imshow("Erode", thresh)
# cv2.waitKey()
# during thresholding, it's possible that border pixels were
# included in the thresholding, so let's set 5% of the left and
# right borders to zero
p = int(image.shape[1] * 0.05)
thresh[:, 0:p] = 0
thresh[:, image.shape[1] - p:] = 0
# find contours in the thresholded image and sort them by their
# size
cnts = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)[-2]
cnts = sorted(cnts, key=cv2.contourArea, reverse=True)
# loop over the contours
for c in cnts:
# compute the bounding box of the contour and use the contour to
# compute the aspect ratio and coverage ratio of the bounding box
# width to the width of the image
(x, y, w, h) = cv2.boundingRect(c)
ar = w / float(h)
crWidth = w / float(gray.shape[1])
# cv2.imshow("Image", image[y:y + h, x:x + w].copy())
# check to see if the aspect ratio and coverage width are within
# acceptable criteria
# print(ar, crWidth)
if ar > 5 and crWidth > 0.6:
# pad the bounding box since we applied erosions and now need
# to re-grow it
pX = int((x + w) * 0.03)
pY = int((y + h) * 0.03)
(x, y) = (x - pX, y - pY)
(w, h) = (w + (pX * 2), h + (pY * 2))
# extract the ROI from the image and draw a bounding box
# surrounding the MRZ
roi = image[y:y + h, x:x + w].copy()
cv2.rectangle(image, (x, y), (x + w, y + h), (0, 255, 0), 2)
break
else:
roi = None
# show the output images
# cv2.imshow("Image", image)
if roi is not None:
config = (
"--oem 0 --psm 6 -c tessedit_char_whitelist=ABCDEFGHIJKLMNOPQRSTUVWXYZ<1234567890"
)
# config = ("--oem 3 --psm 6 --tessdata-dir ./Trained -l eng+ocrb")
# config = ("--oem 0")
# cv2.imshow("ROI", roi)
# cv2.waitKey()
roiGray = cv2.cvtColor(roi, cv2.COLOR_BGR2GRAY)
roiBlackhat = cv2.morphologyEx(roiGray, cv2.MORPH_BLACKHAT, rectKernel)
roiThresh = cv2.threshold(roiBlackhat, 0, 255,
cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
# coords = np.column_stack(np.where(roiThresh > 0))
# angle = cv2.minAreaRect(coords)[-1]
# # the `cv2.minAreaRect` function returns values in the
# # range [-90, 0); as the rectangle rotates clockwise the
# # returned angle trends to 0 -- in this special case we
# # need to add 90 degrees to the angle
# if angle < -45:
# angle = -(90 + angle)
# # otherwise, just take the inverse of the angle to make
# # it positive
# else:
# angle = -angle
# # rotate the image to deskew it
# (h, w) = roiBlackhat.shape[:2]
# center = (w // 2, h // 2)
# M = cv2.getRotationMatrix2D(center, angle, 1.0)
# rotated = cv2.warpAffine(
# roiBlackhat, M, (w, h), flags=cv2.INTER_CUBIC, borderMode=cv2.BORDER_REPLICATE)
# print(angle)
# roiBitwise = cv2.bitwise_not(roi)
# roiThresh = cv2.threshold(roi, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
# cv2.imshow("ROTATED", roiThresh)
# cv2.waitKey()
# pytesseract.image_to_string(Image.open("./imagesStackoverflow/xyz-small-gray.png"),lang="eng",boxes=False,config="--psm 4 --oem 3 -c tessedit_char_whitelist=-01234567890XYZ:"))
text = pytesseract.image_to_string(roiThresh, config=config)
# print(text)
# enhancing text from ocr engine
text = text.replace(" ", "")
textList = text.split("\n")
textEnhanced = []
for txt in textList:
l = len(txt) > 44
if l > 44:
textEnhanced.append(txt[0:44])
elif l < 44:
complement = txt + "<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<"
textEnhanced.append(complement[0:44])
else:
textEnhanced.append(txt)
# print(textEnhanced)
text = "\n".join(textEnhanced)
td3_check = TD3CodeChecker(text)
fields = td3_check.fields()
# print(fields)
# print(fields.surname.replace("0", "O"))
# if bd > current then minus 1 century (human age = 0-99)
now = datetime.datetime.now()
oneCentury = relativedelta(years=100)
bd = None
try:
bd = datetime.datetime.strptime(fields.birth_date, '%y%m%d')
if bd > now:
bd = bd - oneCentury
except Exception as identifier:
bd = None
exp = None
try:
exp = datetime.datetime.strptime(fields.expiry_date, '%y%m%d')
except Exception as identifier:
exp = None
# print(bd.strftime('%Y-%m-%d'))
try:
resp = {
'surname':
"" if fields.surname == "None" else fields.surname.replace(
"0", "O"),
'given_names':
"" if fields.name == "None" else fields.name.replace("0", "O"),
'country_code':
fields.country,
'passport_number':
passport_fixer(fields.document_number),
'nationality':
fields.nationality,
'sex':
'M' if fields.sex == 'H' else fields.sex,
'birth_date':
bd.strftime('%Y-%m-%d') if bd is not None else None,
'expiry_date':
exp.strftime('%Y-%m-%d') if exp is not None else None
}
return resp
except Exception as identifier:
return None
else:
return None
#!/usr/bin/python3
# -*- coding: UTF-8 -*-
from mrz.base.countries_ops import is_code
from mrz.checker.td3 import TD3CodeChecker
mrz_td3 = ("P<ASUMXHMWD<<EBDALRXHYM<<<<<<<<<<<<<<<<<<<<<\n"
"A2222222<0ASU7108215F04120411000146819<<<<44")
td3_check = TD3CodeChecker(mrz_td3, check_expiry=True)
print(td3_check.mrz_code)
if not td3_check:
print("Falses:", td3_check.report_falses)
print("Warnings:", td3_check.report_warnings)
print("'%s' is code: %s" % (td3_check._country, str(is_code("ASU"))))
def print_txt(title, value):
print(title.ljust(20), value)
fields = td3_check.fields()
print_txt("Document Type:", fields.document_type)
print_txt("Country:", fields.country)
print_txt("Surname:", fields.surname)
print_txt("Name:", fields.name)
print_txt("Doc. Number", fields.document_number)
#!/usr/bin/python3
# -*- coding: UTF-8 -*-
from mrz.checker.td3 import TD3CodeChecker
print(TD3CodeChecker("P<CANMARTIN<<SARAH<<<<<<<<<<<<<<<<<<<<<<<<<<\n"
"ZE000509<9CAN8501019F2301147<<<<<<<<<<<<<<08",
check_expiry=True,
compute_warnings=True))