Created
November 9, 2020 09:58
-
-
Save poojapi/7e2b0028933849566671e71a99143c80 to your computer and use it in GitHub Desktop.
Python detect paragraphs with opencv
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import cv2 | |
import numpy as np | |
def para_detect(file_name): | |
img = cv2.imread(file_name) | |
img_final = cv2.imread(file_name) | |
img2gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) | |
ret, mask = cv2.threshold(img2gray, 180, 255, cv2.THRESH_BINARY) | |
image_final = cv2.bitwise_and(img2gray, img2gray, mask=mask) | |
ret, new_img = cv2.threshold(image_final, 180, 255, cv2.THRESH_BINARY_INV) # for black text , cv.THRESH_BINARY_INV | |
''' | |
line 8 to 12 : Remove noisy portion | |
''' | |
kernel = cv2.getStructuringElement(cv2.MORPH_CROSS, (10, | |
3)) # to manipulate the orientation of dilution , large x means horizonatally dilating more, large y means vertically dilating more | |
dilated = cv2.dilate(new_img, kernel, iterations=5) # dilate , more the iteration more the dilation | |
output = cv2.bitwise_not(dilated, dilated) | |
ais = [] | |
for contour in contours: | |
# get rectangle bounding contour | |
[x, y, w, h] = cv2.boundingRect(contour) | |
a = w * h | |
ais.append(a) | |
ais.sort(reverse=True) | |
for contour in contours: | |
[x, y, w, h] = cv2.boundingRect(contour) | |
# Don't plot small false positives that aren't text | |
#if w < 2050 and h < 450: | |
# continue | |
if w*h not in ais[:2]: | |
continue | |
# cv2.imshow('w', img) | |
# cv2.waitKey() | |
# write original image with added contours to disk | |
cv2.imwrite('output4.png', img) | |
file_name = 'n.png' | |
para_detect(file_name) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
contours
is not defined.