Develop Reference

**Save Image with added mask in python**

I'm trying to save an image on which I added a white mask on all the interest areas. But for some reason, It doesn't save the final image and it's not returning any error message. How can I save my image with the mask?
import cv2
import numpy as np
image = cv2.imread('C:/Users/Desktop/testim.png')
gray_scale = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# Set threshold level
Dark = 10
coords = np.column_stack(np.where(gray_scale < Dark))
print("xy:\n", coords)
mask = gray_scale < Dark
# Color the pixels in the mask
image[mask] = (255, 255, 255)
cv2.imshow('mask', image)
cv2.waitKey()
#save new image with the added mask to directory
if not cv2.imwrite(r'./mask.png', image):
raise Exception("Could not write image")

I think it relates to several typos in the program. After fixing them everything works quite nicely.
import cv2
import numpy as np
image = cv2.imread('/content/test.png')
gray_scale = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# Set threshold level
Dark = 10
coords = np.column_stack(np.where(gray_scale < Dark))
# print("xy:\n", coords)
mask = gray_scale < Dark
# Color the pixels in the mask
image[mask] = (255, 255, 255)
# cv2.imshow('mask', image)
cv2.waitKey()
if not cv2.imwrite(r'./mask.png', image):
raise Exception("Could not write image")
image before manipulation
image after manipulation

Preprocess images using OpenCV for pytesseract OCR

I want to use OCR (pytesseract) to recognize the text located in images like these:
I have thousands of these arrows. Until now the procedure is as follows: I first resize the image (for another process). Then I crop the image to get rid of the most part of the arrow. Next I draw a white rectangle as a frame to remove further noise but still have distance between text and image borders for better text recognition. I resize the image again to ensure a height of capital letters to ~30 px (https://groups.google.com/forum/#!msg/tesseract-ocr/Wdh_JJwnw94/24JHDYQbBQAJ). Finally I binarize the image with a threshold of 150.
Full code:
import cv2
image_file = '001.jpg'
# load the input image and grab the image dimensions
image = cv2.imread(image_file, cv2.IMREAD_GRAYSCALE)
(h_1, w_1) = image.shape[:2]
# resize the image and grab the new image dimensions
image = cv2.resize(image, (int(w_1*320/h_1), 320))
(h_1, w_1) = image.shape
# crop image
image_2 = image[70:h_1-70, 20:w_1-20]
# get image_2 height, width
(h_2, w_2) = image_2.shape
# draw white rectangle as a frame around the number -> remove noise
cv2.rectangle(image_2, (0, 0), (w_2, h_2), (255, 255, 255), 40)
# resize image, that capital letters are ~ 30 px in height
image_2 = cv2.resize(image_2, (int(w_2*50/h_2), 50))
# image binarization
ret, image_2 = cv2.threshold(image_2, 150, 255, cv2.THRESH_BINARY)
# save image to file
cv2.imwrite('processed_' + image_file, image_2)
# tesseract part can be commented out
import pytesseract
config_7 = ("-c tessedit_char_whitelist=0123456789AB --oem 1 --psm 7")
text = pytesseract.image_to_string(image_2, config=config_7)
print("OCR TEXT: " + "{}\n".format(text))
The problem is that the text located in the arrow is never centered. Sometimes I remove part of the text with the method described above (e.g. in image 50A).
Is there a method in image processing to get rid of the arrow in a more elegant way? For instance using contour detection and deletion? I am more interested in the OpenCV part than the tesseract part to recognize the text.
Any help is appreciated.

If you look at the pictures you will see that there is a white arrow in the image which is also the biggest contour (especially if you draw a black border on the image). If you make a blank mask and draw the arrow (biggest contour on the image) then erode it a little bit you can perform a per element bitwise conjunction of the actual image and eroded mask. If it is not clear look at the bottom code and comments and you will see that it is actually pretty simple.
# imports
import cv2
import numpy as np
img = cv2.imread("number.png") # read image
# you can resize the image here if you like - it should still work for both sizes
h, w = img.shape[:2] # get the actual images height and width
img = cv2.resize(img, (int(w*320/h), 320))
h, w = img.shape[:2]
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) # transform to grayscale
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY+cv2.THRESH_OTSU)[1] # perform OTSU threhold
cv2.rectangle(thresh, (0, 0), (w, h), (0, 0, 0), 2)
contours = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)[0] # search for contours
max_cnt = max(contours, key=cv2.contourArea) # select biggest one
mask = np.zeros((h, w), dtype=np.uint8) # create a black mask
cv2.drawContours(mask, [max_cnt], -1, (255, 255, 255), -1) # draw biggest contour on the mask
kernel = np.ones((15, 15), dtype=np.uint8) # make a kernel with appropriate values - in both cases (resized and original) 15 is ok
erosion = cv2.erode(mask, kernel, iterations=1) # erode the mask with given kernel
reverse = cv2.bitwise_not(img.copy()) # reversed image of the actual image 0 becomes 255 and 255 becomes 0
img = cv2.bitwise_and(reverse, reverse, mask=erosion) # per-element bit-wise conjunction of the actual image and eroded mask (erosion)
img = cv2.bitwise_not(img) # revers the image again
# save image to file and display
cv2.imwrite("res.png", img)
cv2.imshow("img", img)
cv2.waitKey(0)
cv2.destroyAllWindows()
Result:

You can try simple Python script:
import cv2
import numpy as np
img = cv2.imread('mmubS.png', cv2.IMREAD_GRAYSCALE)
thresh = cv2.threshold(img, 200, 255, cv2.THRESH_BINARY_INV )[1]
im_flood_fill = thresh.copy()
h, w = thresh.shape[:2]
im_flood_fill=cv2.rectangle(im_flood_fill, (0,0), (w-1,h-1), 255, 2)
mask = np.zeros((h + 2, w + 2), np.uint8)
cv2.floodFill(im_flood_fill, mask, (0, 0), 0)
im_flood_fill = cv2.bitwise_not(im_flood_fill)
cv2.imshow('clear text', im_flood_fill)
cv2.imwrite('text.png', im_flood_fill)
Result:

Python OpenCV: Crop image to contents, and make background transparent

I have the following image:
I want to crop the image to the actual contents, and then make the background (the white space behind) transparent. I have seen the following question: How to crop image based on contents (Python & OpenCV)?, and after looking at the answer, and trying it, I got the following code:
img = cv.imread("tmp/"+img+".png")
mask = np.zeros(img.shape[:2],np.uint8)
bgdModel = np.zeros((1,65),np.float64)
fgdModel = np.zeros((1,65),np.float64)
rect = (55,55,110,110)
cv.grabCut(img,mask,rect,bgdModel,fgdModel,5,cv.GC_INIT_WITH_RECT)
mask2 = np.where((mask==2)|(mask==0),0,1).astype('uint8')
img = img*mask2[:,:,np.newaxis]
plt.imshow(img),plt.colorbar(),plt.show()
But when I try this code, I get the following result:
Which isn't really the result I'm searching for, expected result:

Here is one way to do that in Python/OpenCV.
As I mentioned in my comment, your provided image has a white circle around the cow and then a transparent background. I have made the background fully white as my input.
Input:
import cv2
import numpy as np
# read image
img = cv2.imread('cow.png')
# convert to grayscale
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
# invert gray image
gray = 255 - gray
# threshold
thresh = cv2.threshold(gray,0,255,cv2.THRESH_BINARY)[1]
# apply close and open morphology to fill tiny black and white holes and save as mask
kernel = np.ones((3,3), np.uint8)
mask = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel)
mask = cv2.morphologyEx(mask, cv2.MORPH_OPEN, kernel)
# get contours (presumably just one around the nonzero pixels)
contours = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
cntr = contours[0]
x,y,w,h = cv2.boundingRect(cntr)
# make background transparent by placing the mask into the alpha channel
new_img = cv2.cvtColor(img, cv2.COLOR_BGR2BGRA)
new_img[:, :, 3] = mask
# then crop it to bounding rectangle
crop = new_img[y:y+h, x:x+w]
# save cropped image
cv2.imwrite('cow_thresh.png',thresh)
cv2.imwrite('cow_mask.png',mask)
cv2.imwrite('cow_transparent_cropped.png',crop)
# show the images
cv2.imshow("THRESH", thresh)
cv2.imshow("MASK", mask)
cv2.imshow("CROP", crop)
cv2.waitKey(0)
cv2.destroyAllWindows()
Thresholded image:
Mask:
Cropped result with transparent background:

Given that the background to be converted to transparent has its BGR channels white (like in your image), you can do:
import cv2
import numpy as np
img = cv2.imread("cat.png")
img[np.where(np.all(img == 255, -1))] = 0
img_transparent = cv2.cvtColor(img, cv2.COLOR_BGR2BGRA)
img_transparent[np.where(np.all(img == 0, -1))] = 0
cv2.imshow("transparent.png", img_transparent)
Input image:
Output image:
We can tell the second image is transparent by clicking on it; the transparent background will show up a grey (in Firefox, at least).

What worked to me is:
original_image = cv2.imread(path)
#Converting the bgr image to an image with the alpha channel
original_image = cv2.cvtColor(original_image, cv2.BGR2BGRA)
#Transforming every alpha pixel to a transparent pixel.
original_image[np.where(np.all(original_image == 255, -1))] = 0
And then writing the image.

What's the most simple way to crop a circle thumbnail from an image?

I am trying to crop a centered (or not centered) circle from this image:
I stole this code from the existing questions regarding this topic on stack overflow, something goes wrong though:
import cv2
file = 'dog.png'
img = cv2.imread(file)
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
circle = cv2.HoughCircles(img,
3,
dp=1.5,
minDist=10,
minRadius=1,
maxRadius=10)
x = circle[0][0][0]
y = circle[0][0][1]
r = circle[0][0][2]
rectX = (x - r)
rectY = (y - r)
crop_img = img[rectY:(rectY+2*r), rectX:(rectX+2*r)]
cv2.imwrite('dog_circle.png', crop_img)
Output:
Traceback (most recent call last):
File "C:\Users\Artur\Desktop\crop_circle - Kopie\crop_circle.py", line 14, in <module>
x = circle[0][0][0]
TypeError: 'NoneType' object is not subscriptable
cv2.HoughCircles() seems to produce None instead of a cropped circle array. How do I fix this?

first: HoughCircles is used to detect circles on image, not to crop it.
You can't have circle image. Image is always rectangle but some of pixels can be transparent (alpha channel in RGBA) and programs will not display them.
So you can first crop image to have square and later add alpha channel with information which pixels should be visible. And here you can use mask with white circle on black background. At the end you have to save it as png or tiff because jpg can't keep alpha channel.
I use module PIL/pillow for this.
I crop square region in center of image but you can use different coordinates for this.
Next I create grayscale image with the same size and black background and draw white circle/ellipse.
Finally I add this image as alpha channel to cropped image and save it as png.
from PIL import Image, ImageDraw
filename = 'dog.jpg'
# load image
img = Image.open(filename)
# crop image
width, height = img.size
x = (width - height)//2
img_cropped = img.crop((x, 0, x+height, height))
# create grayscale image with white circle (255) on black background (0)
mask = Image.new('L', img_cropped.size)
mask_draw = ImageDraw.Draw(mask)
width, height = img_cropped.size
mask_draw.ellipse((0, 0, width, height), fill=255)
#mask.show()
# add mask as alpha channel
img_cropped.putalpha(mask)
# save as png which keeps alpha channel
img_cropped.save('dog_circle.png')
img_cropped.show()
Result
BTW:
In mask you can use values from 0 to 255 and different pixels may have different transparency - some of them can be half-transparent to make smooth border.
If you want to use it in HTML on own page then you don't have to create circle image because web browser can round corners of image and display it as circle. You have to use CSS for this.
EDIT: Example with more circles on mask.
from PIL import Image, ImageDraw
filename = 'dog.jpg'
# load image
img = Image.open(filename)
# crop image
width, height = img.size
x = (width - height)//2
img_cropped = img.crop((x, 0, x+height, height))
# create grayscale image with white circle (255) on black background (0)
mask = Image.new('L', img_cropped.size)
mask_draw = ImageDraw.Draw(mask)
width, height = img_cropped.size
mask_draw.ellipse((50, 50, width-50, height-50), fill=255)
mask_draw.ellipse((0, 0, 250, 250), fill=255)
mask_draw.ellipse((width-250, 0, width, 250), fill=255)
# add mask as alpha channel
img_cropped.putalpha(mask)
# save as png which keeps alpha channel
img_cropped.save('dog_2.png')
img_cropped.show()

This answer explains how to apply a mask. First, read in the image:
import cv2
import numpy as np
img = cv2.imread('dog.jpg')
Next create a mask, or a blank image that is the same size as the source image:
h,w,_ = img.shape
mask = np.zeros((h,w), np.uint8)
Then, draw a circle on the mask. Change these parameters based on where the face is:
cv2.circle(mask, (678,321), 5, 255, 654)
Finally, mask the source image:
img = cv2.bitwise_and(img, img, mask= mask)
Here is the mask:
And the output:

The idea is to create a black mask then draw the desired region to crop out in white using cv2.circle(). From there we can use cv2.bitwise_and() with the original image and the mask. To crop the result, we can use cv2.boundingRect() on the mask to obtain the ROI then use Numpy slicing to extract the result. For this example I used the center point derived from the image's width and height
import cv2
import numpy as np
# Create mask and draw circle onto mask
image = cv2.imread('1.jpg')
mask = np.zeros(image.shape, dtype=np.uint8)
x,y = image.shape[1], image.shape[0]
cv2.circle(mask, (x//2,y//2), 300, (255,255,255), -1)
# Bitwise-and for ROI
ROI = cv2.bitwise_and(image, mask)
# Crop mask and turn background white
mask = cv2.cvtColor(mask, cv2.COLOR_BGR2GRAY)
x,y,w,h = cv2.boundingRect(mask)
result = ROI[y:y+h,x:x+w]
mask = mask[y:y+h,x:x+w]
result[mask==0] = (255,255,255)
cv2.imshow('result', result)
cv2.waitKey()

PNG image shows white on transparent areas while overlaying on webcam feed. (OpenCV with Python)

Total newbie to OpenCV. I am trying to place a png image (of sunglasses) over the eyes in a webcam feed. While running the program, the transparent regions of the image is white. Here's the part of my code-
# Create the mask for the glasses
imgGlassesGray = cv2.cvtColor(imgGlasses, cv2.COLOR_BGR2GRAY)
ret, orig_mask = cv2.threshold(imgGlassesGray, 10, 255, cv2.THRESH_BINARY)
#orig_mask = imgGlasses[:,:,3]
# Create the inverted mask for the glasses
orig_mask_inv = cv2.bitwise_not(orig_mask)
# Convert glasses image to BGR
# and save the original image size (used later when re-sizing the image)
imgGlasses = imgGlasses[:,:,0:3]
origGlassesHeight, origGlassesWidth = imgGlasses.shape[:2]
video_capture = cv2.VideoCapture(0)
while True:
ret, frame = video_capture.read()
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray, 1.3, 5)
for (x,y,w,h) in faces:
#cv2.rectangle(frame,(x,y),(x+w,y+h),(255,0,0),2)
roi_gray = gray[y:y+h, x:x+w]
roi_color = frame[y:y+h, x:x+w]
eyes = eye_cascade.detectMultiScale(roi_gray)
for (ex,ey,ew,eh) in eyes:
cv2.rectangle(roi_color,(ex,ey),(ex+ew,ey+eh),(0,255,0),1)
for (ex, ey, ew, eh) in eyes:
glassesWidth = 2*ew
glassesHeight = glassesWidth * origGlassesHeight / origGlassesWidth
# Center the glasses
x1 = ex - (glassesWidth/4)
x2 = ex + ew + (glassesWidth/4)
y1 = ey + eh - (glassesHeight/2)
y2 = ey + eh + (glassesHeight/2)
# Re-calculate the width and height of the glasses image
glassesWidth = x2 - x1
glassesHeight = y2 - y1
# Re-size the original image and the masks to the glasses sizes
# calcualted above
glasses = cv2.resize(imgGlasses, (glassesWidth,glassesHeight), interpolation = cv2.INTER_AREA)
mask = cv2.resize(orig_mask, (glassesWidth,glassesHeight), interpolation = cv2.INTER_AREA)
mask_inv = cv2.resize(orig_mask_inv, (glassesWidth,glassesHeight), interpolation = cv2.INTER_AREA)
# take ROI for glasses from background equal to size of glasses image
roi = roi_color[y1:y2, x1:x2]
# roi_bg contains the original image only where the glasses is not
# in the region that is the size of the glasses.
roi_bg = cv2.bitwise_and(roi,roi,mask = mask_inv)
# roi_fg contains the image of the glasses only where the glasses is
roi_fg = cv2.bitwise_and(glasses,glasses,mask = mask)
# join the roi_bg and roi_fg
dst = cv2.add(roi_bg,roi_fg)
# place the joined image, saved to dst back over the original image
roi_color[y1:y2, x1:x2] = dst
break
There are indentation issues here, but they are right on my program. Also, I'll post the full code if that's required.
This is the image I'm trying to mask and overlay -
Thanks in advance!

You need to load the image as follows to get all 4 channels:
import cv2
imgGlasses = cv2.imread(filename, cv2.CV_LOAD_IMAGE_UNCHANGED)
or
imgGlasses = cv2.imread(filename, -1)
If this doesn't work, you could try setting the colour using this example.