def divide_ver(img):
"""Divide paper by blank detection in vertical direction.
Args:
img: Image to be divided.
Returns:
A list of horizontal coordinates.
"""
verCoorX1 = []
verCoorX2 = []
temp = []
temp1 = []
temp2 = []
result = []
bw = imu.preprocess_bw_inv(img)
weight, profile = imu.vertical_proj(bw)
# print('weight = {}'.format(weight[:100]))
for i in range(0, len(weight)):
if weight[i] > 0:
if i == len(weight) - 1 or weight[i + 1] == 0:
verCoorX2.append(i)
if i == 0 or weight[i - 1] == 0:
verCoorX1.append(i)
# print(verCoorX1)
# print(verCoorX2)
temp = list(zip(verCoorX1, verCoorX2))
# print(temp)
for r in temp:
if r[1] - r[0] > 5:
temp1.append(r)
first = 1 if temp1[0][0] < 100 else 0
start = temp1[first][0]
end = temp1[first][1]
for r in range(first, len(temp1)):
if r == len(temp1) - 1:
end = temp1[r][1]
temp2.append((start, end))
elif temp1[r + 1][0] - temp1[r][1] < 45:
continue
else:
end = temp1[r][1]
temp2.append((start, end))
start = temp1[r + 1][0]
for i in temp2:
if i[1] - i[0] > 800:
result.append(i)
if len(result) > 2:
result = result[0:2]
# print(result)
# print(temp)
return result
def find_char(img, coor):
"""Divide line by blank detection in horizontal direction from left to right.
Args:
img: Image to be divided.
coor: A list of line coordinates.
Returns:
A list of first 2 or 3 characters coordinates of each lines.
"""
result = []
for i, c in enumerate(coor):
verCoorX1 = []
verCoorX2 = []
line = []
imgLine = img[c[1]:c[3], c[0]:c[2]]
bw = imu.preprocess_bw_inv(imgLine, smooth=False)
# cv2.imwrite('./res/lines/'+str(i)+'.png', bw)
weight, profile = imu.vertical_proj(bw)
if weight[0] > 1:
verCoorX1.append(0)
for i in range(1, len(weight) - 1):
if weight[i] > 1:
if weight[i + 1] <= 1:
verCoorX2.append(i)
if weight[i - 1] <= 1:
verCoorX1.append(i)
if weight[-1] > 1:
verCoorX2.append(len(weight) - 1)
# print(verCoorX1)
# print(verCoorX2)
ver = list(zip(verCoorX1, verCoorX2))
n = 3
for v in ver:
if n == 0:
break
elif v[1] - v[0] < 3:
continue
else:
line.append((v[0] + c[0], c[1], v[1] + c[0], c[3]))
n -= 1
result.append(line)
return result