Detecting vertical lines using Hough transforms in opencv - python

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)

To be honest, rather than looking for the lines, I'd instead look for the white boxes.
Preparation
import cv2
import numpy as np
Load the image
img = cv2.imread("digitbox.jpg", 0)
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)
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)
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)
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)
Fill all the masked pixels with white, to erase the frames.
img[mask != 0] = 255
cv2.imwrite('digitbox_step4.png', img)
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)

Related

Draw grid on a gridless (fully or partially) table image

I have an image that contains a table, the table can be in many sizes and the image too, and the table can be fully gridded (with only some blank spot that needs to be filled), it can be with only vertical grid lines and can be only with horizontal grid lines.
I've searched the web for a long time and found no solution that worked for me.
I found the following questions that seem to be suitable for me:
Python & OpenCV: How to add lines to the gridless table
Draw a line on a gridless image Python Opencv
How to repair incomplete grid cells and fix missing sections in image
Python & OpenCV: How to crop half-formed bounding boxes
My code is taken from the answers to the above questions and the "best" result I got from the above question codes is that it drew 2 lines one at the rightmost part and one on the leftmost part.
I'm kind of new to OpenCV and the image processing field so I am not sure how can I fix the above questions codes to suit my needs or how to accomplish my needs exactly, I would appreciate any help you can provide.
Example of an image table:
Update:
To remove the horizontal lines I use exactly the code you can find in here, but the result I get on the example image is this:
as you can see it removed most of them but not all of them, and then when I try to apply the same for the vertical ones (I tried the same code with rotation, or flipping the kernel) it does not work at all...
I also tried this code but it didn't work at all also.
Update 2:
I was able to remove the lines using this code:
def removeLines(result, axis) -> np.ndarray:
img = result.copy()
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
if axis == "horizontal":
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1, 25))
elif axis == "vertical":
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (25, 1))
else:
raise ValueError("Axis must be either 'horizontal' or 'vertical'")
detected_lines = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel, iterations=2)
cnts = cv2.findContours(detected_lines, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
result = img.copy()
for c in cnts:
cv2.drawContours(result, [c], -1, (255, 255, 255), 2)
return result
gridless = removeLines(removeLines(cv2.imread(image_path), 'horizontal'), 'vertical')
Result:
Problem:
After I remove lines, when I try to draw the vertical lines using this code:
# read image
img = old_image.copy() # cv2.imread(image_path1)
hh, ww = img.shape[:2]
# convert to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# average gray image to one column
column = cv2.resize(gray, (ww,1), interpolation = cv2.INTER_AREA)
# threshold on white
thresh = cv2.threshold(column, 248, 255, cv2.THRESH_BINARY)[1]
# get contours
contours = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
# Draw vertical
for cntr in contours_v:
x,y,w,h = cv2.boundingRect(cntr)
xcenter = x+w//2
cv2.line(original_image, (xcenter,0), (xcenter,hh-1), (0, 0, 0), 1)
I get this result:
Update 3:
when I try even thresh = cv2.threshold(column, 254, 255, cv2.THRESH_BINARY)[1] (I tried lowering it 1 by 1 until 245, for both the max value and the threshold value, each time I get a different or similar result but always too much lines or too less lines) I get the following:
Input:
Output:
It's putting too many lines instead of just 1 line in each column
Code:
# read image
img = old_image.copy() # cv2.imread(image_path1)
hh, ww = img.shape[:2]
# convert to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# average gray image to one column
column = cv2.resize(gray, (ww, 1), interpolation = cv2.INTER_AREA)
# threshold on white
thresh = cv2.threshold(column, 254, 255, cv2.THRESH_BINARY)[1]
# get contours
contours = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
for cntr in contours:
x, y, w, h = cv2.boundingRect(cntr)
xcenter = x + w // 2
cv2.line(original_image, (xcenter,0), (xcenter, hh_-1), (0, 0, 0), 1)
Here is one way to get the lines in Python/OpenCV. Average the image down to 1 column. Then threshold and get the contours. Then get the bounding boxes and find the vertical centers. Draw lines at those places.
If you do not want the extra lines, crop your image first to get the inside of the table.
Input:
import cv2
import numpy as np
# read image
img = cv2.imread("table4.png")
hh, ww = img.shape[:2]
# convert to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# average gray image to one column
column = cv2.resize(gray, (1,hh), interpolation = cv2.INTER_AREA)
# threshold on white
thresh = cv2.threshold(column, 248, 255, cv2.THRESH_BINARY)[1]
# get contours
contours = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
# loop over contours and get bounding boxes and ycenter and draw horizontal line at ycenter
result = img.copy()
for cntr in contours:
x,y,w,h = cv2.boundingRect(cntr)
ycenter = y+h//2
cv2.line(result, (0,ycenter), (ww-1,ycenter), (0, 0, 255), 1)
# write results
cv2.imwrite("table4_lines3.png", result)
# display results
cv2.imshow("RESULT", result)
cv2.waitKey(0)
Result:
You wrote that you tried to remove the lines using the code, but it did not work.
It works fine for me in Python/OpenCV.
Read the input
Convert to grayscale
Threshold to show the horizontal lines
Apply morphology open with a horizontal kernel to isolate the horizontal lines
Get their contours
Draw the contours on a copy of the input as white to cover over the black horizontal lines
Save the results
Input:
import cv2
import numpy as np
# read the input
img = cv2.imread('table4.png')
# convert to grayscale
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
# threshold
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
# do morphology to detect lines
horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (25,1))
detected_lines = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, horizontal_kernel, iterations=2)
# get contours
cnts = cv2.findContours(detected_lines, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
# draw contours as white on copy of input
result = img.copy()
for c in cnts:
cv2.drawContours(result, [c], -1, (255,255,255), 2)
# save results
cv2.imwrite('table4_horizontal_lines_threshold.png', thresh)
cv2.imwrite('table4_horizontal_lines_detected.png', detected_lines)
cv2.imwrite('table4_horizontal_lines_removed.png', result)
# show results
cv2.imshow('thresh', thresh)
cv2.imshow('morphology', detected_lines)
cv2.imshow('result', result)
cv2.waitKey(0)
Threshold Image:
Morphology Detected Lines Image:
Result:

Python & OpenCV: How to add lines to gridless table

I have the following table:
I want to write a script that creates lines based on the natural breakages on the table text. The result would look like this:
Is there an OpenCV implementation that makes drawing these lines possible? I looked at the answers to the questions here and here, but neither worked. What is the best approach to solving this problem?
Here is one way to get the horizontal lines in Python/OpenCV by counting the number of white pixels in each row of the image to find their center y values. The vertical lines can be added by a similar process.
Input:
import cv2
import numpy as np
# read image
img = cv2.imread("table.png")
hh, ww = img.shape[:2]
# convert to grayscale
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
# threshold gray image
thresh = cv2.threshold(gray, 254, 255, cv2.THRESH_BINARY)[1]
# count number of non-zero pixels in each row
count = np.count_nonzero(thresh, axis=1)
# threshold count at ww (width of image)
count_thresh = count.copy()
count_thresh[count==ww] = 255
count_thresh[count<ww] = 0
count_thresh = count_thresh.astype(np.uint8)
# get contours
contours = cv2.findContours(count_thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
# loop over contours and get bounding boxes and ycenter and draw horizontal line at ycenter
result = img.copy()
for cntr in contours:
x,y,w,h = cv2.boundingRect(cntr)
ycenter = y+h//2
cv2.line(result, (0,ycenter), (ww-1,ycenter), (0, 0, 0), 2)
# write results
cv2.imwrite("table_thresh.png", thresh)
cv2.imwrite("table_lines.png", result)
# display results
cv2.imshow("THRESHOLD", thresh)
cv2.imshow("RESULT", result)
cv2.waitKey(0)
Threshold Image:
Result with lines:
ADDITION
Here is an alternate method that is slightly simpler. It averages the image down to one column rather than counting white pixels.
import cv2
import numpy as np
# read image
img = cv2.imread("table.png")
hh, ww = img.shape[:2]
# convert to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# average gray image to one column
column = cv2.resize(gray, (1,hh), interpolation = cv2.INTER_AREA)
# threshold on white
thresh = cv2.threshold(column, 254, 255, cv2.THRESH_BINARY)[1]
# get contours
contours = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
# loop over contours and get bounding boxes and ycenter and draw horizontal line at ycenter
result = img.copy()
for cntr in contours:
x,y,w,h = cv2.boundingRect(cntr)
ycenter = y+h//2
cv2.line(result, (0,ycenter), (ww-1,ycenter), (0, 0, 0), 2)
# write results
cv2.imwrite("table_lines2.png", result)
# display results
cv2.imshow("RESULT", result)
cv2.waitKey(0)
Result:

Removing small black contours/unwanted contours in Python

I have been at this all day, how to we remove the small back noise in the red circle? I would need it to work on other samples of pictures like this.
The idea I used is to findContours and then add a mask with all the small black noise that is less than a certain area (trial and error).
Removing noise in red ellipse
image = cv2.imread("11_Image_after_noise_removal.png")
# copy image
img = image.copy()
imgray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 127, 255, 0, cv2.THRESH_BINARY)
thresh = 255 - thresh
# Use cv2.CCOMP for two level hierarchy
contours, hierarchy = cv2.findContours(thresh, cv2.RETR_CCOMP,
cv2.CHAIN_APPROX_SIMPLE) # Use cv2.CCOMP for two level hierarchy
cv2.drawContours(img, contours, -1, (0, 255, 0), 1)
cv2.imshow("First detection", img)
# loop through the contours
for i, cnt in enumerate(contours):
# if the contour has no other contours inside of it
if hierarchy[0][i][3] != -1: # basically look for holes
# if the size of the contour is less than a threshold (noise)
if cv2.contourArea(cnt) < 70:
# Fill the holes in the original image
cv2.drawContours(img, [cnt], 0, (0, 0, 0), -1)
# display result
# Visualize the image after the Otsu's method application
cv2.imshow("Image after noise removal", img)
cv2.waitKey(0)
cv2.destroyAllWindows().destroyAllWindows()
You might check the contour area using area = cv.contourArea(cnt) and if it is below some threshold, ignore it.
Here is the OpenCV documentations:
https://docs.opencv.org/4.3.0/dd/d49/tutorial_py_contour_features.html

opencv get bounding box of two squares from image

I want to get the bounding boxes from an image.
I want the coordinates of the two white boxes.
This is an example image:
I tried out
_a, _b, stats, _c = cv2.connectedComponentsWithStats(image, connectivity=8)
and then the boxes are in the stats object.
But I got for the image more then 2 boxes. This is strange.
Maybe somebody has an other solution?
import cv2
# Read image
img = cv2.imread("/Users/sb/Desktop/7n8uq.png", cv2.IMREAD_COLOR)
# Convert to grayscale
img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# Threshold (Produces a binary image)
_, thresh = cv2.threshold(
img_gray, 0, 255, cv2.THRESH_BINARY+cv2.THRESH_OTSU)
cv2.imwrite("thresh.png", thresh)
# Find contours
contours, hierarchy = cv2.findContours(
thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
print("Total number of contours: {}".format(len(contours)))
all_contours_drawn = cv2.drawContours(
img.copy(), contours, -1, (0, 255, 0), 2) # draw all contours
cv2.imwrite("all_contours.png", all_contours_drawn)
box_center_x = []
box_center_y = []
for cnt in contours:
x, y, w, h = cv2.boundingRect(cnt)
box_center_x.append(x+w/2)
box_center_y.append(y+h/2)
print("x-coordinate of boxes: {}".format(box_center_x))
print("y-coordinate of boxes: {}".format(box_center_y))
# Draw box centers
all_box_centers_drawn = img.copy()
for i in range(len(box_center_x)):
cv2.circle(
all_box_centers_drawn,
(int(box_center_x[i]), int(box_center_y[i])),
2, (0 , 0, 255), 2)
cv2.imwrite("box-centers.png", all_box_centers_drawn)
Try using find contours
contours, hierarchy = cv2.findContours(image, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
for i, contour in enumerate(contours[1::]):
bbox = cv2.boundingRect(contour)
find contours example

removing largest contour from an image

I have an image such as this
I am trying to detect and remove the arrow from this image so that I end up with an image that just has the text.
I tried the below approach but it isn't working
image_src = cv2.imread("roi.png")
gray = cv2.cvtColor(image_src, cv2.COLOR_BGR2GRAY)
canny=cv2.Canny(gray,50,200,3)
ret, gray = cv2.threshold(canny, 10, 255, 0)
contours, hierarchy = cv2.findContours(gray, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
largest_area = sorted(contours, key=cv2.contourArea)[-1]
mask = np.ones(image_src.shape[:2], dtype="uint8") * 255
cv2.drawContours(mask, [largest_area], -1, 0, -1)
image = cv2.bitwise_and(image_src, image_src, mask=mask)
The above code seems to give me back the same image WITH the arrow.
How can I remove the arrow?
The following will remove the largest contour:
import numpy as np
import cv2
image_src = cv2.imread("roi.png")
gray = cv2.cvtColor(image_src, cv2.COLOR_BGR2GRAY)
ret, gray = cv2.threshold(gray, 250, 255,0)
image, contours, hierarchy = cv2.findContours(gray, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
mask = np.zeros(image_src.shape, np.uint8)
largest_areas = sorted(contours, key=cv2.contourArea)
cv2.drawContours(mask, [largest_areas[-2]], 0, (255,255,255,255), -1)
removed = cv2.add(image_src, mask)
cv2.imwrite("removed.png", removed)
Note, the largest contour in this case will be the whole image, so it is actually the second largest contour.

Categories

Resources