Using the following code I can remove horizontal lines in images. See result below.
import cv2
from matplotlib import pyplot as plt
img = cv2.imread('image.png',0)
laplacian = cv2.Laplacian(img,cv2.CV_64F)
sobelx = cv2.Sobel(img,cv2.CV_64F,1,0,ksize=5)
plt.subplot(2,2,1),plt.imshow(img,cmap = 'gray')
plt.title('Original'), plt.xticks([]), plt.yticks([])
plt.subplot(2,2,2),plt.imshow(laplacian,cmap = 'gray')
plt.title('Laplacian'), plt.xticks([]), plt.yticks([])
plt.subplot(2,2,3),plt.imshow(sobelx,cmap = 'gray')
plt.title('Sobel X'), plt.xticks([]), plt.yticks([])
plt.show()
The result is pretty good, not perfect but good. What I want to achieve is the one showed here.
I am using this code.
Source image..
One of my questions is: how to save the Sobel X without that grey effect applied ? As original but processed..
Also, is there a better way to do it ?
EDIT
Using the following code for the source image is good. Works pretty well.
import cv2
import numpy as np
img = cv2.imread("image.png")
img=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
img = cv2.bitwise_not(img)
th2 = cv2.adaptiveThreshold(img,255, cv2.ADAPTIVE_THRESH_MEAN_C,cv2.THRESH_BINARY,15,-2)
cv2.imshow("th2", th2)
cv2.imwrite("th2.jpg", th2)
cv2.waitKey(0)
cv2.destroyAllWindows()
horizontal = th2
vertical = th2
rows,cols = horizontal.shape
#inverse the image, so that lines are black for masking
horizontal_inv = cv2.bitwise_not(horizontal)
#perform bitwise_and to mask the lines with provided mask
masked_img = cv2.bitwise_and(img, img, mask=horizontal_inv)
#reverse the image back to normal
masked_img_inv = cv2.bitwise_not(masked_img)
cv2.imshow("masked img", masked_img_inv)
cv2.imwrite("result2.jpg", masked_img_inv)
cv2.waitKey(0)
cv2.destroyAllWindows()
horizontalsize = int(cols / 30)
horizontalStructure = cv2.getStructuringElement(cv2.MORPH_RECT, (horizontalsize,1))
horizontal = cv2.erode(horizontal, horizontalStructure, (-1, -1))
horizontal = cv2.dilate(horizontal, horizontalStructure, (-1, -1))
cv2.imshow("horizontal", horizontal)
cv2.imwrite("horizontal.jpg", horizontal)
cv2.waitKey(0)
cv2.destroyAllWindows()
verticalsize = int(rows / 30)
verticalStructure = cv2.getStructuringElement(cv2.MORPH_RECT, (1, verticalsize))
vertical = cv2.erode(vertical, verticalStructure, (-1, -1))
vertical = cv2.dilate(vertical, verticalStructure, (-1, -1))
cv2.imshow("vertical", vertical)
cv2.imwrite("vertical.jpg", vertical)
cv2.waitKey(0)
cv2.destroyAllWindows()
vertical = cv2.bitwise_not(vertical)
cv2.imshow("vertical_bitwise_not", vertical)
cv2.imwrite("vertical_bitwise_not.jpg", vertical)
cv2.waitKey(0)
cv2.destroyAllWindows()
#step1
edges = cv2.adaptiveThreshold(vertical,255, cv2.ADAPTIVE_THRESH_MEAN_C,cv2.THRESH_BINARY,3,-2)
cv2.imshow("edges", edges)
cv2.imwrite("edges.jpg", edges)
cv2.waitKey(0)
cv2.destroyAllWindows()
#step2
kernel = np.ones((2, 2), dtype = "uint8")
dilated = cv2.dilate(edges, kernel)
cv2.imshow("dilated", dilated)
cv2.imwrite("dilated.jpg", dilated)
cv2.waitKey(0)
cv2.destroyAllWindows()
# step3
smooth = vertical.copy()
#step 4
smooth = cv2.blur(smooth, (4,4))
cv2.imshow("smooth", smooth)
cv2.imwrite("smooth.jpg", smooth)
cv2.waitKey(0)
cv2.destroyAllWindows()
#step 5
(rows, cols) = np.where(img == 0)
vertical[rows, cols] = smooth[rows, cols]
cv2.imshow("vertical_final", vertical)
cv2.imwrite("vertical_final.jpg", vertical)
cv2.waitKey(0)
cv2.destroyAllWindows()
But if I have this image ?
I tried to execute the code above and the result is really poor...
Other images which I am working on are these...
Obtain binary image. Load the image, convert to grayscale, then Otsu's threshold to obtain a binary black/white image.
Detect and remove horizontal lines. To detect horizontal lines, we create a special horizontal kernel and morph open to detect horizontal contours. From here we find contours on the mask and "fill in"
the detected horizontal contours with white to effectively remove the lines
Repair image. At this point the image may have gaps if the horizontal lines intersected through characters. To repair the text, we create a vertical kernel and morph close to reverse the damage
After converting to grayscale, we Otsu's threshold to obtain a binary image
image = cv2.imread('1.png')
gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
Next we create a special horizontal kernel to detect horizontal lines. We draw these lines onto a mask and then find contours on the mask. To remove the lines, we fill in the contours with white
Detected lines
Mask
Filled in contours
# Remove horizontal
horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (25,1))
detected_lines = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, horizontal_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]
for c in cnts:
cv2.drawContours(image, [c], -1, (255,255,255), 2)
The image currently has gaps. To fix this, we construct a vertical kernel to repair the image
# Repair image
repair_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1,6))
result = 255 - cv2.morphologyEx(255 - image, cv2.MORPH_CLOSE, repair_kernel, iterations=1)
Note depending on the image, the size of the kernel will change. You can think of the kernel as (horizontal, vertical). For instance, to detect longer lines, we could use a (50,1) kernel instead. If we wanted thicker lines, we could increase the 2nd parameter to say (50,2).
Here's the results with the other images
Detected lines
Original -> Removed
Detected lines
Original -> Removed
Full code
import cv2
image = cv2.imread('1.png')
gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
# Remove horizontal
horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (25,1))
detected_lines = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, horizontal_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]
for c in cnts:
cv2.drawContours(image, [c], -1, (255,255,255), 2)
# Repair image
repair_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1,6))
result = 255 - cv2.morphologyEx(255 - image, cv2.MORPH_CLOSE, repair_kernel, iterations=1)
cv2.imshow('thresh', thresh)
cv2.imshow('detected_lines', detected_lines)
cv2.imshow('image', image)
cv2.imshow('result', result)
cv2.waitKey()
Related
I'm using opencv library in Python and i have this issue.
I have this image ,that i previously i removed a lot of noise, but in this image there are a lot of irregular shape that i want to remove.
For example :
Im using this image:
For get the start image i use this code:
import cv2
image = cv2.imread("Image.png")
## Heading ##
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1]
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (7, 7))
inverted_thresh = 255 - thresh
dilate = cv2.dilate(inverted_thresh, kernel, iterations=3)
cnts = cv2.findContours(dilate, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
x, y, w, h = cv2.boundingRect(c)
ROI = thresh[y:y + h, x:x + w]
data = pytesseract.image_to_string(ROI, lang='eng', config='--psm 6').lower()
sub = cv2.subtract(~gray, dilate)
# In[4]:
# Sobel Edge Detection
sobelx = cv2.Sobel(src=sub, ddepth=cv2.CV_64F, dx=1, dy=0, ksize=5) # Sobel Edge Detection on the X axis
sobely = cv2.Sobel(src=sub, ddepth=cv2.CV_64F, dx=0, dy=1, ksize=5) # Sobel Edge Detection on the Y axis
sobelxy = cv2.Sobel(src=sub, ddepth=cv2.CV_64F, dx=1, dy=1, ksize=5) # Combined X and Y Sobel Edge Detection
# In[8]:
# Canny Edge Detection
edges = cv2.Canny(image=sub, threshold1=45, threshold2=55) # Display Canny Edge Detection Image
cv2.imshow('Canny Edge Detection', edges)
And i would to get this result
How i can get this result?
If you know min line length of the border, you can easy filter other elements.
import cv2
gray = cv2.imread("Image.png", cv2.IMREAD_GRAYSCALE)
minLineWidth = 397
hKernel = cv2.getStructuringElement(cv2.MORPH_RECT, (minLineWidth, 1))
vKernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1, minLineWidth))
hGray = cv2.morphologyEx(gray, cv2.MORPH_OPEN, hKernel)
vGray = cv2.morphologyEx(gray, cv2.MORPH_OPEN, vKernel)
gray = cv2.bitwise_or(hGray, vGray)
cv2.imshow("gray", gray)
cv2.waitKey()
Result image:
If you don't know min line length, you can use probabilistic hough transform to find all lines. Then you can filter lines by angle and find min repeated line length. After you can apply suggested code or just draw filtered lines.
P.S. Try first of all google your problem. Ex: stackoverflow filter horizontal lines from image. On first link you can find good approaches of your problem.
I am trying to detect cells in bill image:
I have this image
Removed the stamp with this code:
import cv2
import numpy as np
# read image
img = cv2.imread('dummy1.PNG')
# threshold on yellow
lower = (0, 200, 200)
upper = (100, 255, 255)
thresh = cv2.inRange(img, lower, upper)
# apply dilate morphology
kernel = np.ones((9, 9), np.uint8)
mask = cv2.morphologyEx(thresh, cv2.MORPH_DILATE, kernel)
# get largest contour
contours = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
big_contour = max(contours, key=cv2.contourArea)
x, y, w, h = cv2.boundingRect(big_contour)
# draw filled white contour on input
result = img.copy()
cv2.drawContours(result, [big_contour], 0, (255, 255, 255), -1)
cv2.imwrite('removed.png', result)
# show the images
cv2.imshow("RESULT", result)
cv2.waitKey(0)
cv2.destroyAllWindows()
And obtained this image:
Then applied grayscale, inverted, detected vertical and horizontal kernel and merged through this main.py :
# Imports
import cv2
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import csv
try:
from PIL import Image
except ImportError:
import Image
import pytesseract
pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'
#################################################################################################
# Read your file
file = 'removed.png'
img = cv2.imread(file, 0)
img.shape
# thresholding the image to a binary image
thresh, img_bin = cv2.threshold(img, 128, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)
# inverting the image
img_bin = 255 - img_bin
cv2.imwrite(r'C:\Users\marou\Desktop\cv_inverted.png', img_bin)
# Plotting the image to see the output
plotting = plt.imshow(img_bin, cmap='gray')
plt.show()
# Define a kernel to detect rectangular boxes
# Length(width) of kernel as 100th of total width
kernel_len = np.array(img).shape[1] // 100
# Defining a vertical kernel to detect all vertical lines of image
ver_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1, kernel_len))
# Defining a horizontal kernel to detect all horizontal lines of image
hor_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (kernel_len, 1))
# A kernel of 2x2
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (2, 2))
#### Vertical LINES ####
# Use vertical kernel to detect and save the vertical lines in a jpg
image_1 = cv2.erode(img_bin, ver_kernel, iterations=5)
vertical_lines = cv2.dilate(image_1, ver_kernel, iterations=5)
cv2.imwrite(r'C:\Users\marou\Desktop\vertical.jpg', vertical_lines)
# Plot the generated image
plotting = plt.imshow(image_1, cmap='gray')
plt.show()
#### HORTIZONAL LINES ####
# Use horizontal kernel to detect and save the horizontal lines in a jpg
image_2 = cv2.erode(img_bin, hor_kernel, iterations=5)
horizontal_lines = cv2.dilate(image_2, hor_kernel, iterations=5)
cv2.imwrite(r'C:\Users\marou\Desktop\horizontal.jpg', horizontal_lines)
# Plot the generated image
plotting = plt.imshow(image_2, cmap='gray')
plt.show()
# Combining both H and V
# Combine horizontal and vertical lines in a new third image, with both having same weight.
img_vh = cv2.addWeighted(vertical_lines, 0.5, horizontal_lines, 0.5, 0.0)
# Eroding and thesholding the image
img_vh = cv2.erode(~img_vh, kernel, iterations=2)
thresh, img_vh = cv2.threshold(img_vh, 128, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)
cv2.imwrite(r'C:\Users\marou\Desktop\img_vh.jpg', img_vh)
plotting = plt.imshow(img_vh, cmap='gray')
plt.show()
To get this :
Now I am trying to fill the voids in my lines that happened due to the watermark removal, to be able to apply correct OCR.
I tried following the steps in this thread but I can't seem to get it right.
When I try to fill the grid holes :
# Fill individual grid holes
cnts = cv2.findContours(result, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
x,y,w,h = cv2.boundingRect(c)
cv2.rectangle(result, (x, y), (x + w, y + h), 255, -1)
cv2.imshow('result', result)
cv2.waitKey()
I get blank image:
I have outlined an approach to fill the missing lines in the table using the second image as input.
image = cv2.imread(image_path)
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
Now to create a separate mask for the horizontal lines:
h_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (50,1))
# contains only the horizontal lines
h_mask = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, h_kernel, iterations=1)
# performing repeated iterations to join lines
h_mask = cv2.dilate(h_mask, h_kernel, iterations=7)
And a separate mask for the vertical lines:
v_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1,50))
v_mask = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, v_kernel, iterations=1)
Upon combining the above results we get the following:
joined_lines = cv2.bitwise_or(v_mask, h_mask)
The result above is not what you expected, the lines have extended beyond the boundaries of the table. In order to avoid this, I created a separate mask bounding the table region.
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5,5))
dilate = cv2.dilate(thresh, kernel, iterations=1)
Now find the largest contour in the above image and draw it on another binary image to create the mask.
contours, hierarchy = cv2.findContours(dilate, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
c = max(contours, key = cv2.contourArea) # contour with largest area
black = np.zeros((image.shape[0], image.shape[1]), np.uint8)
mask = cv2.drawContours(black, [c], 0, 255, -1) # --> -1 to fill the contour
Using the above image as mask over the joined_lines created further above
fin = cv2.bitwise_and(joined_lines, joined_lines, mask = mask)
Note:
You can perform more iterations over the morphological operations to better join the discontinuous lines
Here's an example image ->
I would like to extract text that has text-decoration/styling of strikethrough.
So for the above image I would like to extract - de location
How would I do this ?
Here's what I have so far using OpenCV and python :
import cv2
import numpy as np
import matplotlib.pyplot as plt
im = cv2.imread(<image>)
kernel = np.ones((1,44), np.uint8)
morphed = cv2.morphologyEx(im, cv2.MORPH_CLOSE, kernel)
plt.imshow(morphed)
This gives me the horizontal lines ->
I am new to image processing and hence having a difficult time isolating only the text that has strikethroughs.
Bonus -> Along with the strikethrough text, I would like to also extract neighboring text so that I can correctly style/mark the strikethrough text information back along with other text.
UPDATE 1 :
Based on the first answer I did the following : -
import cv2
# Load image, convert to grayscale, Otsu's threshold
image = cv2.imread('image.png')
result = image.copy()
gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV +
cv2.THRESH_OTSU)[1]
# Detect horizontal lines
horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT,(40,1))
detect_horizontal = cv2.morphologyEx(thresh, cv2.MORPH_OPEN,
horizontal_kernel, iterations=10)
cnts = cv2.findContours(detect_horizontal, cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
cv2.drawContours(result, [c], -1, (36,255,12), 2)
plt.imshow(result)
I was able to get this image -
I tried playing with the values for the horizontal kernel but no luck.
UPDATE 2:
I modified the above snippet further and got this -
import cv2
import numpy as np
import matplotlib.pyplot as plt
# Load image, convert to grayscale, Otsu's threshold
result = image.copy()
gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
kernel = np.ones((4,2),np.uint8)
erosion = cv2.erode(thresh,kernel,iterations = 1)
dilation = cv2.dilate(thresh,kernel,iterations = 1)
trans = dilation
# plt.imshow(erosion)
# Detect horizontal lines
horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (8,1))
detect_horizontal = cv2.morphologyEx(trans, cv2.MORPH_OPEN, horizontal_kernel, iterations=10)
cnts = cv2.findContours(detect_horizontal, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
cv2.drawContours(result, [c], -1, (36,255,12), 2)
plt.imshow(result)
I was able to get this image -
And this solution applies to my other image types as well -
This is not a 100% accuracy solution (failed to get the de strikethrough text) but I like the performance so far.
Now, I am struggling with how to check if the neighboring pixels are black or white to isolate the strikethrough.
one way you can achieve this is:
Binarise the image (https://docs.opencv.org/master/d7/d4d/tutorial_py_thresholding.html)
Find horizontal lines (Horizontal Line detection with OpenCV)
For each line, check if the top and bottom pixels are white or not
If there are non white top and bottom pixels, that region corresponds to strikethrough
Do a connected component of the image (connected component labeling in python)
Check the label corresponding to the lines detected previously and mask that label to get the strike-through texts.
You can use a strikethrough property such as thickness. The thickness of the strikethrough line is less than the underline. It can be select by morphology and restore the connected components by morphological reconstruction.
import cv2
img = cv2.imread('juFpe.png', cv2.IMREAD_GRAYSCALE)
thresh = cv2.threshold(img, 0, 255, cv2.THRESH_BINARY_INV )[1]
kernel = cv2.getStructuringElement(cv2.MORPH_RECT,(1,5))
kernel2=cv2.getStructuringElement(cv2.MORPH_RECT,(8,8))
detect_thin = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
detect_thin = cv2.morphologyEx(detect_thin, cv2.MORPH_DILATE, kernel2)
marker=cv2.compare(detect_thin, thresh,cv2.CMP_LT) # thin lines
while True: #morphological reconstruction
tmp=marker.copy()
marker=cv2.dilate(marker, kernel2)
marker=cv2.min(thresh, marker)
difference = cv2.subtract(marker, tmp)
if cv2.countNonZero(difference) == 0:
break
cv2.imwrite('lines.png', marker)
Result:
I'm trying to get the corners of this rectangle:
.
I tried using cv2.cornerHarris(rectangle, 2, 3, 0.04), but the left edges are not showed due to image brightness, I guess. So I tried applying a threshold before using cornerHarris, but the image produced showed a lot of vertices along the edges, not being possible to filter the corners.
I know that I need to filter it before using cornerHarris, but I don't know how. Could someone help me with this problem?
Ps. I've already tried to use blur, but it also doesn't work.
import cv2
import numpy as np
import matplotlib.pyplot as plt
rectangle = cv2.imread('rectangle.png', cv2.IMREAD_GRAYSCALE)
rectangle = np.where(rectangle > np.mean(rectangle), 255, 0).astype(np.uint8)
dst_rectangle = cv2.cornerHarris(rectangle, 2, 3, 0.04)
dst_rectangle = cv2.dilate(dst_rectangle, None)
mask = np.where(dst_rectangle > 0.01*np.max(dst_rectangle), 255, 0).astype(np.uint8)
points = np.nonzero(mask)
plt.imshow(dst_rectangle, cmap='gray')
plt.plot(points[1], points[0], 'or')
plt.show()
I would approach it differently by getting the corners of the rotated bounding box of the contour after adaptive thresholding. Here is my code in Python/OpenCV.
Input:
import cv2
import numpy as np
# read image
img = cv2.imread("rectangle.png")
# convert img to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
gray = 255-gray
# do adaptive threshold on gray image
thresh = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY, 17, 1)
thresh = 255-thresh
# apply morphology
kernel = np.ones((3,3), np.uint8)
morph = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
morph = cv2.morphologyEx(morph, cv2.MORPH_CLOSE, kernel)
# separate horizontal and vertical lines to filter out spots outside the rectangle
kernel = np.ones((7,3), np.uint8)
vert = cv2.morphologyEx(morph, cv2.MORPH_OPEN, kernel)
kernel = np.ones((3,7), np.uint8)
horiz = cv2.morphologyEx(morph, cv2.MORPH_OPEN, kernel)
# combine
rect = cv2.add(horiz,vert)
# thin
kernel = np.ones((3,3), np.uint8)
rect = cv2.morphologyEx(rect, cv2.MORPH_ERODE, kernel)
# get largest contour
contours = cv2.findContours(rect, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
for c in contours:
area_thresh = 0
area = cv2.contourArea(c)
if area > area_thresh:
area = area_thresh
big_contour = c
# get rotated rectangle from contour
rot_rect = cv2.minAreaRect(big_contour)
box = cv2.boxPoints(rot_rect)
box = np.int0(box)
print(box)
# draw rotated rectangle on copy of img
rot_bbox = img.copy()
cv2.drawContours(rot_bbox,[box],0,(0,0,255),2)
# write img with red rotated bounding box to disk
cv2.imwrite("rectangle_thresh.png", thresh)
cv2.imwrite("rectangle_outline.png", rect)
cv2.imwrite("rectangle_bounds.png", rot_bbox)
# display it
cv2.imshow("IMAGE", img)
cv2.imshow("THRESHOLD", thresh)
cv2.imshow("MORPH", morph)
cv2.imshow("VERT", vert)
cv2.imshow("HORIZ", horiz)
cv2.imshow("RECT", rect)
cv2.imshow("BBOX", rot_bbox)
cv2.waitKey(0)
Thresholded Image:
Rectangle Region Extracted:
Rotated Bounding Box on Image:
Rotated Bounding Box Corners:
[[446 335]
[163 328]
[168 117]
[451 124]]
ADDITION:
Here is a slightly shorter version of the code, which is achievable by adding some gaussian blurring before thresholding.
import cv2
import numpy as np
# read image
img = cv2.imread("rectangle.png")
# convert img to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
gray = 255-gray
# blur image
blur = cv2.GaussianBlur(gray, (3,3), 0)
# do adaptive threshold on gray image
thresh = cv2.adaptiveThreshold(blur, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY, 75, 2)
thresh = 255-thresh
# apply morphology
kernel = np.ones((5,5), np.uint8)
rect = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
rect = cv2.morphologyEx(rect, cv2.MORPH_CLOSE, kernel)
# thin
kernel = np.ones((5,5), np.uint8)
rect = cv2.morphologyEx(rect, cv2.MORPH_ERODE, kernel)
# get largest contour
contours = cv2.findContours(rect, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
for c in contours:
area_thresh = 0
area = cv2.contourArea(c)
if area > area_thresh:
area = area_thresh
big_contour = c
# get rotated rectangle from contour
rot_rect = cv2.minAreaRect(big_contour)
box = cv2.boxPoints(rot_rect)
box = np.int0(box)
for p in box:
pt = (p[0],p[1])
print(pt)
# draw rotated rectangle on copy of img
rot_bbox = img.copy()
cv2.drawContours(rot_bbox,[box],0,(0,0,255),2)
# write img with red rotated bounding box to disk
cv2.imwrite("rectangle_thresh.png", thresh)
cv2.imwrite("rectangle_outline.png", rect)
cv2.imwrite("rectangle_bounds.png", rot_bbox)
# display it
cv2.imshow("IMAGE", img)
cv2.imshow("THRESHOLD", thresh)
cv2.imshow("RECT", rect)
cv2.imshow("BBOX", rot_bbox)
cv2.waitKey(0)
Thresholded Image:
Rectangle Region Extracted:
Rotated Bounding Box on Image:
Rotated Bounding Box Corners:
(444, 335)
(167, 330)
(170, 120)
(448, 125)
Here's a simple approach:
Obtain binary image. We load the image, grayscale, Gaussian blur, then adaptive threshold.
Morphological operations. We create a rectangular kernel and morph open to remove the small noise
Find distorted rectangle contour and draw onto a mask. Find contours, determine rotated bounding box, and draw onto a blank mask
Find corners. We use the Shi-Tomasi Corner Detector already implemented as cv2.goodFeaturesToTrack which is supposedly shows better results compared to the Harris Corner Detector
Here's a visualization of each step:
Binary image
Morph open
Find rotated rectangle contour and draw/fill onto a blank mask
Draw rotated rectangle and corners to get result
Corner coordinates
(448.0, 337.0)
(164.0, 332.0)
(452.0, 123.0)
(168.0, 118.0)
Code
import cv2
import numpy as np
# Load image, grayscale, Gaussian blur, adaptive threshold
image = cv2.imread("1.png")
mask = np.zeros(image.shape, dtype=np.uint8)
gray = 255 - cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (3,3), 0)
thresh = cv2.adaptiveThreshold(blur, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY_INV, 51, 3)
# Morph open
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3,3))
opening = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel, iterations=1)
# Find distorted rectangle contour and draw onto a mask
cnts = cv2.findContours(opening, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
rect = cv2.minAreaRect(cnts[0])
box = cv2.boxPoints(rect)
box = np.int0(box)
cv2.drawContours(image,[box],0,(36,255,12),2)
cv2.fillPoly(mask, [box], (255,255,255))
# Find corners on the mask
mask = cv2.cvtColor(mask, cv2.COLOR_BGR2GRAY)
corners = cv2.goodFeaturesToTrack(mask, maxCorners=4, qualityLevel=0.5, minDistance=150)
for corner in corners:
x,y = corner.ravel()
cv2.circle(image,(x,y),8,(255,120,255),-1)
print("({}, {})".format(x,y))
cv2.imshow("thresh", thresh)
cv2.imshow("opening", opening)
cv2.imshow("mask", mask)
cv2.imshow("image", image)
cv2.waitKey(0)
You can try with an adaptive threshold. Then you may either use cornerHarris if you only need corners, or depending on what you need to do next, you could also find useful findContours, which returns a list of bounding boxes
I was able to locate 3 out of the 4 points, the 4th point can be found easily given the other three points since it's rectangle. Here is my solution:
import cv2
import numpy as np
img = cv2.imread('6dUIr.png',1)
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
#smooth the image
kernel = np.ones((5,5),np.float32)/25
gray = cv2.filter2D(gray,-1,kernel)
#histogram equalization
clahe = cv2.createCLAHE(clipLimit=1.45, tileGridSize=(4,4))
cl1 = clahe.apply(gray)
#find edges
edges = cv2.Canny(cl1,4,100)
#find corners
dst = cv2.cornerHarris(edges,2,3,0.04)
#result is dilated for marking the corners, not important
dst = cv2.dilate(dst,None)
# Threshold for an optimal value, it may vary depending on the image.
img[dst>0.25*dst.max()]=[0,0,255]
cv2.imshow('edges', edges)
cv2.imshow('output', img)
# cv2.imshow('Histogram equalized', img_output)
cv2.waitKey(0)
The code has many hard coded thresholds but it's a good start.
I am trying to detect lines on a table tennis board, but there is allot of "noise" detected off the board (sides) and on the board as well.
There is also the issue of getting rid of the brand/wording on the table.
Basically want detect the white lines on the green table.
I have been looking at some examples, but being new to OpenCV doesn't help :-)
import cv2
import numpy as np
img = cv2.imread("table.jpg")
imgS = cv2.resize(img, (960, 1024))
#
# # Convert to grayscale first beforeget edges of the image
kernel_size = 5
gray = cv2.cvtColor(imgS, cv2.COLOR_BGR2GRAY)
blur_gray = cv2.GaussianBlur(gray,(kernel_size, kernel_size), 0)
# get edges of the image
edges = cv2.Canny(blur_gray, 75, 150)
lines = cv2.HoughLinesP(edges, 1, np.pi/180, 50, maxLineGap=100)
# print(lines)
# draw "lines"
for line in lines:
x1, y1, x2, y2 = line[0]
# print(line[0])
# Draw the line on original image (img) and set color to blue and thickness 2
cv2.line(imgS, (x1, y1), (x2, y2), (0, 255,0), 2)
cv2.imshow("Edges", edges)
cv2.imshow("img", imgS)
cv2.waitKey(0)
cv2.destroyAllWindows()
Here's an approach
Convert image to grayscale and Gaussian blur
Canny edge detection
Create mask to keep white line contours
Perform morphological transformations with a vertical kernel to isolate vertical lines
Perform morphological transformations with a horizontal kernel to isolate horizontal lines
Detect lines with cv2.HoughLinesP()
Iterate through mask and find contours
Draw contours onto original image
Canny edge detection
Next we use a special vertical kernel using cv2.getStructuringElement() to filter out horizontal lines and extract only the vertical lines
vertical_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1,3))
remove_horizontal = cv2.morphologyEx(canny, cv2.MORPH_OPEN, vertical_kernel)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5,5))
dilate_vertical = cv2.morphologyEx(remove_horizontal, cv2.MORPH_CLOSE, kernel, iterations=5)
We do the same thing with a horizontal kernel to extract only horizontal lines
horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3,1))
remove_vertical = cv2.morphologyEx(canny, cv2.MORPH_OPEN, horizontal_kernel)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (9,9))
dilate_horizontal = cv2.morphologyEx(remove_vertical, cv2.MORPH_CLOSE, kernel, iterations=3)
We combine the two to get the resulting mask
Finally we find contours on the mask and draw it on the original image. Here's the result
import cv2
import numpy as np
image = cv2.imread('1.jpg')
image = cv2.resize(image, (960, 1024))
mask = np.zeros(image.shape, np.uint8)
gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (3,3), 0)
canny = cv2.Canny(blur, 150, 255, 1)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5,5))
# Find Vertical Lines
# ------
vertical_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1,3))
remove_horizontal = cv2.morphologyEx(canny, cv2.MORPH_OPEN, vertical_kernel)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5,5))
dilate_vertical = cv2.morphologyEx(remove_horizontal, cv2.MORPH_CLOSE, kernel, iterations=5)
minLineLength = 10
maxLineGap = 150
lines = cv2.HoughLinesP(dilate_vertical,1,np.pi/180,100,minLineLength,maxLineGap)
for line in lines:
for x1,y1,x2,y2 in line:
cv2.line(mask,(x1,y1),(x2,y2),(255,255,255),3)
cv2.imwrite('vertical_mask.png', mask)
# ------
# Find Horizontal Lines
# ------
horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3,1))
remove_vertical = cv2.morphologyEx(canny, cv2.MORPH_OPEN, horizontal_kernel)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (9,9))
dilate_horizontal = cv2.morphologyEx(remove_vertical, cv2.MORPH_CLOSE, kernel, iterations=3)
minLineLength = 10
maxLineGap = 300
horizontal_mask = np.zeros(image.shape, np.uint8)
lines = cv2.HoughLinesP(dilate_horizontal,1,np.pi/180,100,minLineLength,maxLineGap)
for line in lines:
for x1,y1,x2,y2 in line:
cv2.line(mask,(x1,y1),(x2,y2),(255,255,255),3)
cv2.line(horizontal_mask,(x1,y1),(x2,y2),(255,255,255),3)
cv2.imwrite('horizontal_mask.png', horizontal_mask)
# ------
mask = cv2.cvtColor(mask, cv2.COLOR_BGR2GRAY)
cnts = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
cv2.drawContours(image, [c], -1, (36,255,12), 2)
cv2.imwrite('remove_vertical.png', remove_vertical)
cv2.imwrite('remove_horizontal.png', remove_horizontal)
cv2.imwrite('dilate_horizontal.png', dilate_horizontal)
cv2.imwrite('mask.png', mask)
cv2.imwrite('image.png', image)
cv2.waitKey()
Notes: Other potential strategies and thoughts
Use color thresholding and cv2.inRange() to isolate the white lines.
To filter out the net, you can use a modified version of the above method but instead of using cv2.HoughLinesP(), use Numpy slicing to extract only the top/bottom halves and only search for lines using the top 1/4 and bottom 1/4 of image. Maybe something like this
top_half = remove_vertical[0:int(image.shape[0] * .25), 0:image.shape[1]]
bottom_half = remove_vertical[int(image.shape[0] * .75):image.shape[0], 0:image.shape[1]]
Strategy to isolate only the middle line
Convert image to grayscale and Gaussian blur
Canny edge detection
Perform morphological transformations with a vertical kernel
Dilate to enhance contour
Find contours and filter using contour area
Canny edge detection
Next we use a special vertical kernel using cv2.getStructuringElement() to filter out horizontal lines and extract only the vertical lines
vertical_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1,9))
remove_horizontal = cv2.morphologyEx(canny, cv2.MORPH_OPEN, vertical_kernel)
Finally we dilate to enhance contours and filter using a minimum threshold area. Here's the result
import cv2
image = cv2.imread('1.jpg')
image = cv2.resize(image, (960, 1024))
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (7,7), 0)
canny = cv2.Canny(blur, 120, 255, 1)
vertical_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1,9))
remove_horizontal = cv2.morphologyEx(canny, cv2.MORPH_OPEN, vertical_kernel)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3,3))
dilate = cv2.morphologyEx(remove_horizontal, cv2.MORPH_CLOSE, kernel)
cnts = cv2.findContours(dilate, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
area = cv2.contourArea(c)
if area > 50:
cv2.drawContours(image, [c], -1, (36,255,12), 3)
cv2.imwrite('result.png', image)
cv2.imwrite('canny.png', canny)
cv2.imwrite('remove_horizontal.png', remove_horizontal)
cv2.waitKey()