Detecting vertical lines using Hough transforms in opencv

Question

I'm trying to remove the square boxes(vertical and horizontal lines) using Hough transform in opencv (Python). The problem is none of the vertical lines are being detected. I've tried looking through contours and hierarchy but there are too many contours in this image and I'm confused how to use them.

After looking through related posts, I've played with the threshold and rho parameters but that didn't help. I've attached the code for more details. Why does Hough transform not find the vertical lines in the image?. Any suggestions in solving this task are welcome. Thanks.

Input Image :

Hough transformed Image:

Drawing contours:

import cv2
import numpy as np
import pdb


img = cv2.imread('/home/user/Downloads/cropped/robust_blaze_cpp-300-0000046A-02-HW.jpg')

gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(gray, 140, 255, 0)
im2, contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cv2.drawContours(img, contours, -1, (0,0,255), 2)

edges = cv2.Canny(gray,50,150,apertureSize = 3)
minLineLength = 5
maxLineGap = 100
lines = cv2.HoughLinesP(edges,rho=1,theta=np.pi/180,threshold=100,minLineLength=minLineLength,maxLineGap=maxLineGap)
for x1,y1,x2,y2 in lines[0]:
    cv2.line(img,(x1,y1),(x2,y2),(0,255,0),2)

cv2.imwrite('probHough.jpg',img)

Answer 1

To be honest, rather than looking for the lines, I'd instead look for the white boxes.

1. Preparation

   import cv2
   import numpy as np
   

2. Load the image

   img = cv2.imread("digitbox.jpg", 0)
   

3. Binarize it, so that both the boxes and the digits are black, rest is white

   _, thresh = cv2.threshold(img, 200, 255, cv2.THRESH_BINARY)
   cv2.imwrite('digitbox_step1.png', thresh)
   

   

4. Find contours. In this example image, it's fine to just look for external contours.

   _, contours, hierarchy = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
   

5. Process the contours, filtering out any with too small an area. Find convex hull of each contour, create a mask of all areas outside the contour. Store the bounding boxes of each found contour, sorted by x coordinate.

   mask = np.ones_like(img) * 255
   
   boxes = []
   
   for contour in contours:
       if cv2.contourArea(contour) > 100:
           hull = cv2.convexHull(contour)
           cv2.drawContours(mask, [hull], -1, 0, -1)
           x,y,w,h = cv2.boundingRect(contour)
           boxes.append((x,y,w,h))
   
   boxes = sorted(boxes, key=lambda box: box[0])
   
   cv2.imwrite('digitbox_step2.png', mask)
   

   

6. Dilate the mask (to shrink the black parts), to clip off any remains the the gray frames.

   mask = cv2.dilate(mask, np.ones((5,5),np.uint8))
   
   cv2.imwrite('digitbox_step3.png', mask)
   

   

7. Fill all the masked pixels with white, to erase the frames.

   img[mask != 0] = 255
   
   cv2.imwrite('digitbox_step4.png', img)
   

   

8. Process the digits as you desire -- i'll just draw the bounding boxes.

   result = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
   
   for n,box in enumerate(boxes):
       x,y,w,h = box
       cv2.rectangle(result,(x,y),(x+w,y+h),(255,0,0),2)
       cv2.putText(result, str(n),(x+5,y+17), cv2.FONT_HERSHEY_SIMPLEX, 0.6,(255,0,0),2,cv2.LINE_AA)
   
   cv2.imwrite('digitbox_step5.png', result)
   

   

---

The whole script in one piece:

import cv2
import numpy as np

img = cv2.imread("digitbox.jpg", 0)

_, thresh = cv2.threshold(img, 200, 255, cv2.THRESH_BINARY)
_, contours, hierarchy = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

mask = np.ones_like(img) * 255
boxes = []

for contour in contours:
    if cv2.contourArea(contour) > 100:
        hull = cv2.convexHull(contour)
        cv2.drawContours(mask, [hull], -1, 0, -1)
        x,y,w,h = cv2.boundingRect(contour)
        boxes.append((x,y,w,h))

boxes = sorted(boxes, key=lambda box: box[0])

mask = cv2.dilate(mask, np.ones((5,5),np.uint8))

img[mask != 0] = 255

result = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)

for n,box in enumerate(boxes):
    x,y,w,h = box
    cv2.rectangle(result,(x,y),(x+w,y+h),(255,0,0),2)
    cv2.putText(result, str(n),(x+5,y+17), cv2.FONT_HERSHEY_SIMPLEX, 0.6,(255,0,0),2,cv2.LINE_AA)

cv2.imwrite('digitbox_result.png', result)