def cropFromOneHoughLineConversion(A, color):
h, w = firstHough.shape
red = color
pixels = []
allText = ""
h, w = firstHough.shape
for i in range(1, h - 1):
for j in range(1, w - 1):
if A[i][j] != red and A[i - 1][j] == red and A[i - 1][
j - 1] == red and A[i][j - 1] == red:
pixels.append((i, j))
if A[i][j] != red and A[i - 1][j] == red and A[i - 1][
j + 1] == red and A[i][j + 1] == red:
pixels.append((i, j))
if A[i][j] != red and A[i + 1][j - 1] == red and A[
i + 1][j] == red and A[i][j - 1] == red:
pixels.append((i, j))
if A[i][j] != red and A[i + 1][j] == red and A[i + 1][
j + 1] == red and A[i][j + 1] == red:
pixels.append((i, j))
for i in range(len(pixels) - 3):
if levi.canBeARectangle(pixels[i], pixels[i + 1], pixels[i + 4],
pixels[i + 3]) == True:
singleRectangelImage = helper.cut_image(image, pixels[i][1],
pixels[i + 1][1],
pixels[i][0],
pixels[i + 3][0])
text = get_text.get_text_from_image(singleRectangelImage)
allText += text
allText += '\n'
return allText
def getName(image):
final_image = helper.cut_image(image, 100, 385, 166, 184)
text = get_text.get_text_from_image(final_image)
return text
def getAllMarks(image):
img = helper.cut_image(image, 330, 480, 335, 460)
cv2.imwrite('C:\\Users\\Istrati Lucian\\Admitere-OCR\\bac.jpg', img)
good = ""
for i in range(335, 436, 25):
singleMark = helper.cut_image(image, 330, 480, i, i + 25)
cv2.imwrite(
'C:\\Users\\Istrati Lucian\\Admitere-OCR\\bac' + str(
(460 - i) / 25) + '.jpg', singleMark)
text = get_text.get_text_from_image(singleMark)
t = extractMarkUsingLetters(text)
good += str(t) + " "
return good
def getCNP(image):
# get gender
#img = helper.cut_image(image, 80, 245, 277, 295) good
img = helper.cut_image(image, 89, 245, 277, 295)
#160 pixels, 13*12
text = ""
pytesseract.pytesseract.tesseract_cmd = 'C:\\Program Files\\Tesseract-OCR\\tesseract.exe'
for i in range(89,234,12):
digit = helper.cut_image(image,i,i+9,277,293)
path = "C:\\Users\\Istrati Lucian\\Admitere-OCR\\DIGIT"+str(i)+".jpg"
cv2.imwrite(path,digit)
t = get_text.get_text_from_image(digit)
#t = pytesseract.image_to_string(Image.open(path))
print(t,end=" ")
text+=t
"""
vertical = img
vertical = cv.bitwise_not(vertical)
show_wait_destroy("vertical_bit", vertical)
Extract edges and smooth image according to the logic
1. extract edges
2. dilate(edges)
3. src.copyTo(smooth)
4. blur smooth img
5. smooth.copyTo(src, edges)
'''
# Step 1
edges = cv.adaptiveThreshold(vertical, 255, cv.ADAPTIVE_THRESH_MEAN_C, \
cv.THRESH_BINARY, 3, -2)
show_wait_destroy("edges", edges)
# Step 2
kernel = np.ones((2, 2), np.uint8)
edges = cv.dilate(edges, kernel)
show_wait_destroy("dilate", edges)
# Step 3
smooth = np.copy(vertical)
# Step 4
smooth = cv.blur(smooth, (2, 2))
# Step 5
(rows, cols) = np.where(edges != 0)
vertical[rows, cols] = smooth[rows, cols]
# Show final result
show_wait_destroy("smooth - final", vertical)
"""
#text = get_text.get_text_from_image(img)
return text
def getSubject(image):
"""
This function extracts the name of the subject for which the student had his 2nd exam in Baccalaureate
The second exam may be either History or Mathematics, we need to extract the mark at maths, if he has one
"""
img = helper.cut_image(image, 35, 200, 338, 358)
cv2.imwrite('C:\\Users\\Istrati Lucian\\Admitere-OCR\\subject.jpg', img)
text = get_text.get_text_from_image(img)
"""
if text!=None and levi.iterative_levenshtein("Limba si literatura romana - scris",text)>=10:
img = helper.cut_image(image, 35, 200, 370, 390)
cv2.imwrite('C:\\Users\\Istrati Lucian\\Admitere-OCR\\subject.jpg', img)
text = get_text.get_text_from_image(img)
if text!=None and levi.iterative_levenshtein("Matematica",text)<=6 or levi.iterative_levenshtein("Istorie",text)<=6:
"""
return text
def getMathMark(image):
"""
To be revised - coordonations
"""
img = helper.cut_image(image, 300, 475, 338, 358)
cv2.imwrite('C:\\Users\\Istrati Lucian\\Admitere-OCR\\math.jpg', img)
text = get_text.get_text_from_image(img)
good = extractMarkUsingLetters(text)
######
"""
img = helper.cut_image(image, 35, 200, 338, 358)
cv2.imwrite('C:\\Users\\Istrati Lucian\\Admitere-OCR\\subject.jpg', img)
text = get_text.get_text_from_image(img)
if levi.iterative_levenshtein("Limba si literatura romana - scris",text)>=10:
img = helper.cut_image(image, 35, 200, 350, 370)
cv2.imwrite('C:\\Users\\Istrati Lucian\\Admitere-OCR\\subject.jpg', img)
text = get_text.get_text_from_image(img)
"""
########
return good
def getBacMarkInCaseSubjectRomanianLanguage(image):
img = helper.cut_image(image, 300, 475, 434, 454)
cv2.imwrite('C:\\Users\\Istrati Lucian\\Admitere-OCR\\bac.jpg', img)
text = get_text.get_text_from_image(img)
good = extractMarkUsingLetters(text)
return good
def getBacMark(image):
img = helper.cut_image(image, 300, 475, 390, 411)
cv2.imwrite('C:\\Users\\Istrati Lucian\\Admitere-OCR\\bac.jpg', img)
text = get_text.get_text_from_image(img)
good = extractMarkUsingLetters(text)
return good
def getAll(image):
return get_text.get_text_from_image(image)
def getSubjectInCaseSubjectRomanianLanguage(image):
img = helper.cut_image(image, 35, 200, 385, 407)
cv2.imwrite('C:\\Users\\Istrati Lucian\\Admitere-OCR\\subject.jpg', img)
text = get_text.get_text_from_image(img)
return text