Develop Reference

Masked out large irregular shape from image with Python

The objective is to remove large irregular area and maintained only character in the image.
For example, given the following
and the expected masked output
I have the impression this can be achieved as below
import cv2
import numpy as np
from matplotlib import pyplot as plt
dpath='remove_bg1.jpg'
img = cv2.imread(dpath)
img_fh=img.copy()
cv2.bitwise_not(img_fh,img_fh)
ksize=10
kernel = np.ones((ksize,ksize),np.uint8)
erosion = cv2.erode(img_fh,kernel,iterations = 3)
invertx = cv2.bitwise_not(erosion)
masked = cv2.bitwise_not(cv2.bitwise_and(img_fh,invertx))
all_image=[img,invertx,masked]
ncol=len(all_image)
for idx, i in enumerate(all_image):
plt.subplot(int(f'1{ncol}{idx+1}')),plt.imshow(i)
plt.show()
which produce
Clearly, the code above did not produced the expected result.
May I know how to address this issue properly?

To remove the unwanted blob, we must create a mask such that it encloses it completely.
Flow:
Inversely binarize the image (such that you have a white foreground against dark background)
Dilate the image (since the blob makes contact with letter 'A', it has to be isolated )
Find contour with the largest area
Draw the contour on an another 1-channel image and thicken it (dilation)
Pixel Assignment: Pixels containing the dilated blob are made white on the original image
Code:
im = cv2.imread('stained_text.jpg')
im2 = im.copy()
gray = cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)
# inverse binaraization
th = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
Notice the blob region touching the letter 'A'. Hence to isolate it we perform erosion using an elliptical kernel
# erosion
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5,5))
erode = cv2.erode(th, kernel, iterations=2)
# find contours
contours, hierarchy = cv2.findContours(erode, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
# Contour of maximum area
c = max(contours, key = cv2.contourArea)
# create 1-channel image in black
black = np.zeros((im.shape[0], im.shape[1]), np.uint8)
# draw the contour on it
black = cv2.drawContours(black, [c], 0, 255, -1)
# perform dilation to have clean border
# we are using the same kernel
dilate = cv2.dilate(black, kernel, iterations = 3)
# assign the dilated area in white over the original image
im2[dilate == 255] = (255,255,255)
This was just one of the many possible ways on how to proceed. The key thing to note is how to isolate the blob.

Contour around watermark opencv

I want to draw a box around the watermark in my image. I have extracted the watermark and have found the contours. However, the contour is not drawn around the watermark. The contour is drawn across my full image. Kindly help me with the correct code.
The output of contour co-ordinates are:
[array([[[ 0, 0]],
[[ 0, 634]],
[[450, 634]],
[[450, 0]]], dtype=int32)]
The output image is:
My code snippet is as follows:
img = cv2.imread('Watermark/w3.png')
gr = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
bg = gr.copy()
closing = cv2.morphologyEx(bg, cv2.MORPH_CLOSE, kernel) #dilation followed by erosion
#plt.imshow(cv2.subtract(img,opening))
plt.imshow(closing)
_,contours, hierarchy = cv2.findContours(closing, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
print(contours)
print(len(contours))
if len(contours)>0 :
cnt=contours[len(contours)-1]
cv2.drawContours(closing, [cnt], 0, (0,255,0), 3)
plt.imshow(closing)

The function findContours is having difficulty to find your box contour because expects to run over a binary image. From the documentation:
For better accuracy, use binary images. So before finding contours, apply threshold or canny edge detection.
In OpenCV, finding contours is like finding white object from black background. So remember, object to be found should be white and background should be black.
Thus, after cvtColor function apply the threshold making sure you have a black background.
...
img = cv2.imread('sample.png')
gr = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
_, bg = cv2.threshold(gr, 127, 255, cv2.THRESH_BINARY_INV)
...
If you run the findContours over this binary image you will find multiple boxes
To get a single box around the whole text you can search for the number of iterations parameter over the
morphologyEx function that creates one single blob.
...
kernel = np.ones((3,3))
closing = cv2.morphologyEx(bg, cv2.MORPH_CLOSE, kernel, iterations=5)
...
So, after creating the blob apply the findContours you already have and use the minAreaRect to find the rotated rectangle with the minimum area enclosing the set of points passed.
...
contours, hierarchy = cv2.findContours(closing, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
print(len(contours))
for i in range(len(contours)):
rect = cv2.minAreaRect(contours[i])
box = cv2.boxPoints(rect)
box = np.int0(box)
cv2.drawContours(img,[box],0,(127,60,255),2)
cv2.imwrite("output_box.png", img)

How to crop an image along major axis of the blob/contour with a rectangular bounding box using Python

I would like to crop an image which has a hand drawn highlighted area in orange as shown below,
The result should be a cropped image along the major axis of the blob or contour with a rectangular bounding box, as shown below,
Here's what i have tried,
import numpy as np
import cv2
# load the image
image = cv2.imread("frame50.jpg", 1)
#color boundaries [B, G, R]
lower = [0, 3, 30]
upper = [30, 117, 253]
# create NumPy arrays from the boundaries
lower = np.array(lower, dtype="uint8")
upper = np.array(upper, dtype="uint8")
# find the colors within the specified boundaries and apply
# the mask
mask = cv2.inRange(image, lower, upper)
output = cv2.bitwise_and(image, image, mask=mask)
ret,thresh = cv2.threshold(mask, 50, 255, 0)
if (int(cv2.__version__[0]) > 3):
contours, hierarchy = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
else:
im2, contours, hierarchy = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
if len(contours) != 0:
# find the biggest countour (c) by the area
c = max(contours, key = cv2.contourArea)
x,y,w,h = cv2.boundingRect(c)
ROI = image[y:y+h, x:x+w]
cv2.imshow('ROI',ROI)
cv2.imwrite('ROI.png',ROI)
cv2.waitKey(0)
This does not seem to work most of the time.For some images, the following happens,
I would like to know if there is better way to go about this or how i can fix what i have right now.Note that the highlighted area is hand drawn and can be of any shape but it is closed and not left open and the colour of the highlight is that shade of orange itself in all cases.
And is there a way to only retain content inside the circle and blackout everything outside it?
EDIT1:
I was able to fix the wrong clipping by varying the threshold more. But my main query now is: is there a way to only retain content inside the circle and blackout everything outside it? I can see the mask as show below,
How do I fill this mask and retain content inside the circle and blackout everything outside it, with the same rectangular bounding box?

Have you tried
image[x:x+w, y:y+h]
And could you check bbox with below code
cv2.rectangle(thresh,(x,y),(x+w,y+h),(255,0,0),2)

First of all, it is always better to use an HSV image instead of BGR image for masking(extracting a color). You can do this by the following code.
HSV_Image = cv2.cvtColor(Image, cv2.COLOR_BGR2HSV)
ThreshImage = cv2.inRange(HSV_Image, np.array([0, 28, 191]), np.array([24, 255, 255]))
The range numbers here are found for orange color in this case.
Image is the input image and ThreshImage is the output image with the orange region colored as white and everything else as black.
Now finding the contour in ThreshImage with cv2.RETR_EXTERNAL flag will give only one contour that is the outer boundary of the orange region.
Contours, Hierarchy = cv2.findContours(ThreshImage, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
To crop the orange region:
BoundingRect = cv2.boundingRect(Contours[0])
(x, y, w, h) = BoundingRect
CroppedImage = Image[y:y+h, x:x+w].copy()
"CroppedImage" will store the cropped orange region as desired.
To get contents of only inside the contour:
Bitwise AND operation will be useful here as we already have detected the contour.
First, we have to create a black image of shape the same as that of input image and draw the contour with white color filled in it.
ContourFilledImage = np.zeros(Image.shape, dtype=np.uint8)
cv2.drawContours(ContourFilledImage, Contours, -1, (255, 255, 255), -1)
Now perform a bitwise AND operation on Input Image and "ContourFilledImage"
OnlyInnerData = cv2.bitwise_and(ContourFilledImage, Image)
"OnlyInnerData" image is the desired output image having only the content of inside the circle.

Removing partial borders with openCV

I'm using OpenCV to find tabular data within images so that I can use an OCR on it. So far I have been able to find the table in the image, find the columns of the table, then find each cell within each column. It works pretty well, but I'm having an issue with the cell walls getting stuck in my images and I'm unable to remove them reliably.This is one example that I'm having difficulty with.This would be another example.
I have tried several approaches to get these images better. I have been having the most luck with finding the contours.
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)
kernel = cv2.getStructuringElement(cv2.MORPH_CROSS, (5, 3))
# dilate , more the iteration more the dilation
dilated = cv2.dilate(new_img, kernel, iterations=3)
cv2.imwrite('../test_images/find_contours_dilated.png', dilated)
I have been toying with the kernel size and dilation iterations and have found this to be the best configuration.
Another approach I used was with PIL, but it is only really good if the border is uniform around the whole image, which in my cases it is not.
copy = Image.fromarray(img)
try:
bg = Image.new(copy.mode, copy.size, copy.getpixel((0, 0)))
except:
return None
diff = ImageChops.difference(copy, bg)
diff = ImageChops.add(diff, diff, 2.0, -100)
bbox = diff.getbbox()
if bbox:
return np.array(copy.crop(bbox))
There were a few other ideas that I tried, but none got me very far. Any help would be appreciated.

You could try with finding contours and "drawing" them out. Meaning you can draw a border that will be connected with the "walls" mannualy with cv2.rectangle on the borders of your image (that will combine all contours - walls). The biggest two contours will be outer and inner line of your walls and you can draw the contour white to remove the border. Then apply threshold again to remove the rest of the noise. Cheers!
Example:
import cv2
import numpy as np
# Read the image
img = cv2.imread('borders2.png')
# Get image shape
h, w, channels = img.shape
# Draw a rectangle on the border to combine the wall to one contour
cv2.rectangle(img,(0,0),(w,h),(0,0,0),2)
# Convert to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# Apply binary threshold
_, threshold = cv2.threshold(gray, 180, 255, cv2.THRESH_BINARY_INV)
# Search for contours and sort them by size
_, contours, hierarchy = cv2.findContours(threshold,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
area = sorted(contours, key=cv2.contourArea, reverse=True)
# Draw it out with white color from biggest to second biggest contour
cv2.drawContours(img, ((contours[0]),(contours[1])), -1, (255,255,255), -1)
# Apply binary threshold again to the new image to remove little noises
_, img = cv2.threshold(img, 180, 255, cv2.THRESH_BINARY)
# Display results
cv2.imshow('img', img)
Result:

How to extract rectangles of varying edge intensity from images?

I am trying to extract the account number from an image of a cheque. The logic that I have is that, I am trying to find the rectangle that contains the account number, slice the bounding rectangle and then feed the slice into an OCR to get the text out of it.
The problem I am facing is when the rectangle is not very prominent and light colour, I am not able to get the rectangle contour since the edges are not connected totally.
How to overcome this?
Things I tried, but did not work are
I cannot increase the erosion iteration, to erode it more, because then the edges connect with the surrounding black pixels and form a different shape.
Reducing the threshold offset might help, but, it seems inefficient. Since the code has to work with several types of images. I can start with offset 10 and keep incrementing the offset and checking if I found the rectangle or not. This will increase the time a lot for cheques with prominent rectangles that work well at offset 20 or more. And since I don't have a condition to check if the edges of the rectangle are prominent or not, the loop has to be applied in all the cheques.
Keeping the above points in mind. Can someone help me out with a solution to this problem?
Libraries used and versions
scikit-image==0.13.1
opencv-python==3.3.0.10
Code
from skimage.filters import threshold_adaptive, threshold_local
import cv2
Step 1:
image = cv2.imread('cropped.png')
Step 2:
Using adaptive threshold from skimage to remove the background, so that I can get the account number rectangle box. This works fine for the cheques where the rectangle is more pronounced, but when the rectangle edges are thin, or are lighter in colour, the threshold results in
unconnected edges, because of which I am not able to find the contours. I have attached examples of this further down in the question.
account_number_block = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
account_number_block = threshold_adaptive(account_number_block, 251, offset=20)
account_number_block = account_number_block.astype("uint8") * 255
Step 3:
Erode the image a bit to try to connect small disconnections in the edges
kernel = np.ones((3,3), np.uint8)
account_number_block = cv2.erode(account_number_block, kernel, iterations=5)
Find the contours
(_, cnts, _) = cv2.findContours(account_number_block.copy(), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
# cnts = sorted(cnts, key=cv2.contourArea)[:3]
rect_cnts = [] # Rectangular contours
for cnt in cnts:
approx = cv2.approxPolyDP(cnt,0.01*cv2.arcLength(cnt,True),True)
if len(approx) == 4:
rect_cnts.append(cnt)
rect_cnts = sorted(rect_cnts, key=cv2.contourArea, reverse=True)[:1]
Working Example
Step 1: Original Image
Step 2: After thresholding to remove the background.
Step 3: Finding contours to find rectangle box of the account number.
Failure Working example - Light rectangular boundary.
Step 1: Read original image
Step 2: After thresholding to remove the background. Notice that the edges of the rectangle are not connected, because of which I am not able to get the contour out of it.
Step 3: Finding contours to find rectangle box of the account number.

import numpy as np
import cv2
import pytesseract as pt
from PIL import Image
#Run Main
if __name__ == "__main__" :
image = cv2.imread("image.jpg", -1)
# resize image to speed up computation
rows,cols,_ = image.shape
image = cv2.resize(image, (np.int32(cols/2),np.int32(rows/2)))
# convert to gray and binarize
gray_img = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
binary_img = cv2.adaptiveThreshold(gray_img, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY, 9, 9)
# note: erosion and dilation works on white forground
binary_img = cv2.bitwise_not(binary_img)
# dilate the image to fill the gaps
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3,3))
dilated_img = cv2.morphologyEx(binary_img, cv2.MORPH_DILATE, kernel,iterations=2)
# find contours, discard contours which do not belong to a rectangle
(_, cnts, _) = cv2.findContours(dilated_img, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
rect_cnts = [] # Rectangular contours
for cnt in cnts:
approx = cv2.approxPolyDP(cnt,0.01*cv2.arcLength(cnt,True),True)
if len(approx) == 4:
rect_cnts.append(cnt)
# sort contours based on area
rect_cnts = sorted(rect_cnts, key=cv2.contourArea, reverse=True)[:1]
# find bounding rectangle of biggest contour
box = cv2.boundingRect(rect_cnts[0])
x,y,w,h = box[:]
# extract rectangle from the original image
newimg = image[y:y+h,x:x+w]
# use 'pytesseract' to get the text in the new image
text = pt.image_to_string(Image.fromarray(newimg))
print(text)
cv2.namedWindow('Image', cv2.WINDOW_NORMAL)
cv2.imshow('Image', newimg)
cv2.waitKey(0)
cv2.destroyAllWindows()
result: 03541140011724
result: 34785736216