def GetDigits(img):
img = PreProcessing.Binarization(img)
cv2.imshow('', img)
rows,cols = img.shape[:]
cols_coordinates = []
number=''
flag = True
for j in range(0,cols):
temp_sum = 0
for i in range(0,rows):
temp_sum += img[i][j]
if temp_sum == 255*rows and flag:
cols_coordinates.append(j+5)
flag = False
if temp_sum<255*rows:
flag = True
print(cols_coordinates)
if len(cols_coordinates)>0:
x = cols_coordinates[0]
for i in range(1,len(cols_coordinates)):
w = cols_coordinates[i]
crop_img = img[:,x:w]
x = w
crop_img = FindBoundary(crop_img)
crop_img = cv2.resize(crop_img, (20,20))
temp_crop_img = []
for i in range(28):
temp = []
for j in range(28):
temp.append(0)
temp_crop_img.append(temp)
for i in range(20):
for j in range(20):
if crop_img[i][j]>127:
crop_img[i][j] = 255
else:
crop_img[i][j] = 0
if crop_img[i][j]==0:
temp_crop_img[4+i][4+j] = 255
cv2.imshow('Boundary', np.float32(temp_crop_img))
cv2.waitKey(0)
pred_digit=get_Prediction(temp_crop_img)
count=0
digit=str(pred_digit[0])
for i in range(20):
for j in range(20):
if temp_crop_img[4+i][4+j] == 255 :
count=count+1
if count>=(200):
digit="1"
print(digit,count)
#Appending each digit to form a number
number=number + digit
return number
def remove(img):
rows, cols = img.shape[:2]
BinarizedImage = PreProcessing.Binarization(img)
upper_height = 0
for i in range(rows):
temp_sum = 0
for j in range(cols):
temp_sum += BinarizedImage[i, j]
if temp_sum < int(0.15 * 255 * cols):
upper_height = i + 5
else:
break
lower_height = 0
for i in range(rows):
temp_sum = 0
for j in range(cols):
temp_sum += BinarizedImage[rows - 1 - i, j]
if temp_sum < int(0.15 * 255 * cols):
lower_height = i + 5
else:
break
left_width = 0
for j in range(cols):
temp_sum = 0
for i in range(rows):
temp_sum += BinarizedImage[i, j]
if temp_sum < int(0.03 * 255 * rows):
left_width = j + 5
else:
break
right_width = 0
for j in range(cols):
temp_sum = 0
for i in range(rows):
temp_sum += BinarizedImage[i, cols - 1 - j]
if temp_sum < int(0.03 * 255 * rows):
right_width = j + 5
else:
break
x = left_width
y = upper_height
h = rows - 1 - lower_height
w = cols - 1 - right_width
return img[y:h, x:w]
def OCR_DICT():
image_indices = GlobalVariables.image_indices
no_of_rows = GlobalVariables.no_of_rows
no_of_cols = GlobalVariables.no_of_cols
count = 0
for row in range(no_of_rows):
for col in range(len(no_of_cols[row])):
count = count + 1
if count in image_indices:
image_name = 'Cropped_Images/row' + '_' + str(
row + 1) + '_' + 'col' + '_' + str(col + 1) + str('.png')
image = cv2.imread(image_name)
BinarizedImage = PreProcessing.Binarization(image)
if count == 15:
text = pytesseract.image_to_string(BinarizedImage)
temp_text = text.split('-')
form_dict[temp_text[0]] = temp_text[1]
else:
key, value = get_form_text(BinarizedImage)
form_dict[key] = value
return form_dict
if temp_image_name[1] == 'jpg' or temp_image_name[1] == 'JPG':
img = im.open(imageName)
img.save(temp_image_name[0] + '.png')
imageName = temp_image_name[0] + '.png'
#loading Image
image = cv2.imread(imageName)
#Rotating Image
RotatedImage = Skew_Correction.Correct_skew(imageName)
#smoothening Image
SmoothImage = PreProcessing.smoothening(RotatedImage)
#Binarizing Image
BinarizedImage = PreProcessing.Binarization(SmoothImage)
#Creating Chunks of images so that information can be extracted
FINAL_CROP_IMAGES_COORDINATES = Profiling.H_Profiling(BinarizedImage)
#Saving All Chunks into a Folder(Name = 'Cropped_Images')
Save_Images(FINAL_CROP_IMAGES_COORDINATES)
OCR_information = OCR.OCR_DICT()
Handwritten_info = handwrittenOCR.get_handwritten_dict()
#Merging Dictionaries
OCR_information.update(Handwritten_info)
#Saving Data as json in File
with open('data_5.txt', 'w') as outfile:
