How To Count Lines In Image With Python, Opencv

I want to count paper,So I think about using the line detection. I have tried some methods like Canny, HoughLines,FLD. But I only get the processed photo, I have no idea how to cou

Solution 1:

I think you could count the number of lines (papers) based on how many straight lines do you have. My idea is that

1. You should calculate the distances for all points that you get from HoughLinesP by using np.linalg.norm(point1 - point2)for more details.
2. Then you could adjust the proper distance that used to identify the lines to ignore the noise (small) lines. I recommend using min_line_length in HoughLinesP.
3. Count the number of distances (lines) that are bigger than the proper distance.

This is the code that I used for your image :

# After you apply Hough on edge detected image
lines = cv.HoughLinesP(img, rho, theta, threshold, np.array([]),
                    min_line_length, max_line_gap)

# calculate the distances between points (x1,y1), (x2,y2) :

distance = []
for line in lines:
    distance.append(np.linalg.norm(line[:,:2] - line[:,2:]))

print('max distance:',max(distance),'\nmin distance:',min(distance))

# Adjusting the best distance 
bestDistance=1110

numberOfLines=[]
count=0for x in distance:
    if x>bestDistance:
        numberOfLines.append(x)
        count=count+1print('Number of lines:',count)

Output:

max distance:1352.8166912039487min distance:50.0Number of lines:17