Develop Reference

OpenCV: return only selected area of an image and return the rest as black

I'm trying to select a certain area of an image, and it's already successful. However, there's another problem, the selected area is not in the same place as the source image. Here's the visualization about it:
The left image is the area that I generate. But it's not in the right place as I wanted in the right image.
Here's a simple code that I tried already:
import cv2
import NumPy as np
pic= cv2.imread('set.jpeg')
pic = cv2.resize(pic, dsize=(500, 400), interpolation=cv2.INTER_CUBIC)
gray=cv2.cvtColor(pic,cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray,(5,5),5)
_,thres = cv2.threshold(blur, 100,250, cv2.THRESH_TOZERO)
res = cv2.Canny(thres, 100, 200, L2gradient=True)
circles = cv2.HoughCircles(res,cv2.HOUGH_GRADIENT,1,20,param1=200,param2=15,minRadius=80,maxRadius=100)
crops = []
for i in circles[0,:]:
# draw the outer circle
cv2.circle(pic,(int(i[0]),int(i[1])),int(i[2]),(255,255,255),2)
i = i.astype(int)
crop = res[i[1]-i[2]:i[1]+i[2], i[0]-i[2]:i[0]+i[2]]
crop = np.pad(crop,[(101, ), (151, )], mode='constant')
crops.append(crop)
result = np.concatenate((crops[0],res),axis=1)
cv2.imshow('Hole',result)
cv2.waitKey(0)
cv2.destroyAllWindows()
I want the result like the right image (generate the blue box image only) and return the rest as black (like the left image).
Is there any way to get the result in the right place as I wanted? (Like the right image) Thank you!!

The issue has been solved by creating masks and combine the foreground and background by these lines of code:
import cv2
import numpy as np
pic= cv2.imread('Assets/set.jpeg')
pic = cv2.resize(pic, dsize=(500, 400), interpolation=cv2.INTER_CUBIC)
gray=cv2.cvtColor(pic,cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray,(5,5),5)
_,thres = cv2.threshold(blur, 100,250, cv2.THRESH_TOZERO)
res = cv2.Canny(thres, 100, 250, L2gradient=True)
circles = cv2.HoughCircles(res,cv2.HOUGH_GRADIENT,1,20,param1=200,param2=15,minRadius=80,maxRadius=100)
circles = np.uint16(np.around(circles))
mask = np.full((res.shape[0], res.shape[1]), 1, dtype=np.uint8) # mask is only
clone = pic.copy()
for i in circles[0, :]:
cv2.circle(mask, (i[0], i[1]), i[2], (255, 255, 255), -1)
cv2.circle(clone, (i[0], i[1]), i[2], (255, 255, 255), 1)
# get first masked value (foreground)
fg = cv2.bitwise_or(res, res, mask=mask)
# get second masked value (background) mask must be inverted
mask = cv2.bitwise_not(mask)
background = np.full(res.shape, 255, dtype=np.uint8)
bk = cv2.bitwise_or(background, background, mask=mask)
# combine foreground+background
final = cv2.bitwise_or(fg, bk)
result = np.concatenate((res,final),axis=1)
cv2.imshow('Hole',result)
cv2.waitKey(0)
cv2.destroyAllWindows()
Nothing to be asked anymore and I will close the question. Thank you!!

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:

Changing colours of an area in an image using opencv in python

I have a picture were I want to change all white-ish pixels to grey, but only for a certain area of the image. Example picture, I just want to change the picture outside of the red rectangle, without changing the image within the red rectangle:
I already have the general code, which was part of someone elses Stackoverflow question, that changes the colour of every white pixel instead of only just the one outside of an area.
image = cv.imread("meme 2.jpg")
hsv = cv.cvtColor(image, cv.COLOR_BGR2HSV)
# Define lower and uppper limits of what we call "white-ish"
sensitivity = 19
lower_white = np.array([0, 0, 255 - sensitivity])
upper_white = np.array([255, sensitivity, 255])
# Mask image to only select white
mask = cv.inRange(hsv, lower_white, upper_white)
# Change image to grey where we found brown
image[mask > 0] = (170, 170, 170)
cv.imwrite(file, image)

Here is one way to do that in Python/OpenCV.
Read the input
Convert to HSV color space
Threshold on desired color to make a mask
Use the mask to change the color of all corresponding pixels in the image
Draw a new rectangular mask for the region where you do not want to change
Invert the new mask for the region where you do want to change
Apply the new mask to the original image
Apply the inverted new mask to the color changed image
Add the two results together to form the final image
Save the results
Input:
import cv2
import numpy as np
# Read image
image = cv2.imread('4animals.jpg')
# Convert to HSV
hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
# Define lower and uppper limits of what we call "white-ish"
sensitivity = 19
lower_white = np.array([0, 0, 255 - sensitivity])
upper_white = np.array([255, sensitivity, 255])
# Create mask to only select white
mask = cv2.inRange(hsv, lower_white, upper_white)
# Change image to grey where we found white
image2 = image.copy()
image2[mask > 0] = (170, 170, 170)
# Create new rectangular mask that is white on black background
x,y,w,h = 33,100,430,550
mask2 = np.zeros_like(image)
cv2.rectangle(mask2, (x,y), (x+w,y+h), (255, 255, 255), -1)
# invert mask
mask2_inv = 255 - mask2
# apply mask to image
image_masked = cv2.bitwise_and(image, mask2)
# apply inverted mask to image2
image2_masked = cv2.bitwise_and(image2, mask2_inv)
# add together
result = cv2.add(image_masked, image2_masked)
# save results
cv2.imwrite('4animals_mask.jpg', mask)
cv2.imwrite('4animals_modified.png', image2)
cv2.imwrite('4animals_mask2.jpg', mask2)
cv2.imwrite('4animals_mask2_inv.jpg', mask2_inv)
cv2.imwrite('4animals_masked.jpg', image_masked)
cv2.imwrite('4animals_modified_masked.jpg', image2_masked)
cv2.imwrite('4animals_result.jpg', result)
cv2.imshow('mask', mask)
cv2.imshow('image2', image2)
cv2.imshow('mask2', mask2 )
cv2.imshow('mask2_inv', mask2_inv)
cv2.imshow('image_masked', image_masked)
cv2.imshow('image2_masked', image2_masked)
cv2.imshow('result', result)
cv2.waitKey(0)
cv2.destroyAllWindows()
Color mask:
Rectangle mask:
Inverted rectangle mask:
Color changed image:
Masked input:
Masked color changed image:
Result:

Here is another simpler method in Python/OpenCV. My previous answer was overly complicated.
Read the input
Convert to HSV color space
Create a mask image by color thresholding
Draw a black rectangle on the previous mask for where you do not want to change the color
Apply the new combined mask to the image to change the color in the desired region
Save the result
Input:
import cv2
import numpy as np
# Read image
image = cv2.imread('4animals.jpg')
# Convert to HSV
hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
# Define lower and uppper limits of what we call "white-ish"
sensitivity = 19
lower_white = np.array([0, 0, 255 - sensitivity])
upper_white = np.array([255, sensitivity, 255])
# Create mask to only select white
mask = cv2.inRange(hsv, lower_white, upper_white)
# Draw new rectangular mask on old mask that is black inside the rectangle and white outside the rectangle
x,y,w,h = 33,100,430,550
mask2 = mask.copy()
cv2.rectangle(mask2, (x,y), (x+w,y+h), 0, -1)
# Change image to grey where we found white for combined mask
result = image.copy()
result[mask2 > 0] = (170, 170, 170)
# save results
cv2.imwrite('4animals_mask.jpg', mask)
cv2.imwrite('4animals_mask2.jpg', mask2)
cv2.imwrite('4animals_result.jpg', result)
cv2.imshow('mask', mask)
cv2.imshow('mask2', mask2 )
cv2.imshow('result', result)
cv2.waitKey(0)
cv2.destroyAllWindows()
Mask from color thresholding:
Modified mask with rectangle drawn over it:
Result:

How to make black background in cv2.putText with Python OpenCV

I have a project of opencv where on the frame I am displaying some text using cv2.putText(). Currently it looks like below:
As you can see on the top left corner, the text is present but its not clearly visible. Is it possible to make background black so that the text will then appear good. Something like below image:
Even if the black background covers till right side of the frame, that is also fine. Below is the code I am using for putting text on frame:
cv2.putText(frame, "Data: N/A", (5, 30), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 0, 255), 1)
cv2.putText(frame, "Room: C1", (5, 60), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 0, 255), 1)
Is there any prebuilt method/library available in opencv which can do this. Can anyone please suggest a good way?

Use this function:
import cv2
def draw_text(img, text,
font=cv2.FONT_HERSHEY_PLAIN,
pos=(0, 0),
font_scale=3,
font_thickness=2,
text_color=(0, 255, 0),
text_color_bg=(0, 0, 0)
):
x, y = pos
text_size, _ = cv2.getTextSize(text, font, font_scale, font_thickness)
text_w, text_h = text_size
cv2.rectangle(img, pos, (x + text_w, y + text_h), text_color_bg, -1)
cv2.putText(img, text, (x, y + text_h + font_scale - 1), font, font_scale, text_color, font_thickness)
return text_size
Then you can invoke the function like this:
image = 127 * np.ones((100, 200, 3), dtype="uint8")
pos = (10, 10)
w, h = draw_text(image, "hello", pos=(10, 10))
draw_text(image, "world", font_scale=4, pos=(10, 20 + h), text_color_bg=(255, 0, 0))
cv2.imshow("image", image)
cv2.waitKey()
note that by default it paints a black background, but you can use a different color if you want.

There's no prebuilt method but a simple appraoch is to use cv2.rectangle + cv2.putText. All you need to do is to draw the black rectangle on the image followed by placing the text. You can adjust the x,y,w,h parameters depending on how large/small you want the rectangle. Here's an example:
Input image:
Result:
import cv2
import numpy as np
# Load image, define rectangle bounds
image = cv2.imread('1.jpg')
x,y,w,h = 0,0,175,75
# Draw black background rectangle
cv2.rectangle(image, (x, x), (x + w, y + h), (0,0,0), -1)
# Add text
cv2.putText(image, "THICC flower", (x + int(w/10),y + int(h/2)), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (255,255,255), 2)
# Display
cv2.imshow('image', image)
cv2.waitKey()

Here is one way to do that in Python OpenCV.
Read the input
Create an image of your desired background color that is the same size as the input
Draw your text on the background image
Get the bounding rectangle for the text region
Copy the text region from the background color image to a copy of the input image
Save the results
Input:
import cv2
import numpy as np
# load image
img = cv2.imread("zelda1.jpg")
# create same size image of background color
bg_color = (0,0,0)
bg = np.full((img.shape), bg_color, dtype=np.uint8)
# draw text on bg
text_color = (0,0,255)
cv2.putText(bg, "Data: N/A", (5,30), cv2.FONT_HERSHEY_COMPLEX_SMALL, 0.75, text_color, 1)
# get bounding box
# use channel corresponding to color so that text is white on black background
x,y,w,h = cv2.boundingRect(bg[:,:,2])
print(x,y,w,h)
# copy bounding box region from bg to img
result = img.copy()
result[y:y+h, x:x+w] = bg[y:y+h, x:x+w]
# write result to disk
cv2.imwrite("zelda1_background_text.jpg", bg)
cv2.imwrite("zelda1_text.jpg", result)
# display results
cv2.imshow("TEXT", bg)
cv2.imshow("RESULT", result)
cv2.waitKey(0)
cv2.destroyAllWindows()
Text on background color image:
Text on input image:
P.S. You can adjust the bounding rectangle (x,y,w,h) values to add some padding if you want when you do the crop.

import cv2 \
import numpy as np
#### Load image, define rectangle bounds
image = cv2.imread(r'C:\Users\Bharath\Downloads\test.jpg')
#### overlay space
x,y,w,h = 40,30,300,60
#### alpha, the 4th channel of the image
alpha = 0.3
overlay = image.copy()
output = image.copy()
##### corner
cv2.rectangle(overlay, (x, x), (x + w, y + h), (0,0,0), -1)
##### putText
cv2.putText(overlay, "HELLO WORLD..!", (x + int(w/10),y + int(h/1.5)), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (255,255,255), 2)
#### apply the overlay
cv2.addWeighted(overlay, alpha, output, 1 - alpha,0, output)
##### Display
cv2.imshow("Output", output)\
cv2.waitKey(0)
`
input
output

Mask out ROI without changing the image size

I got some image of a cattle farm. Each image supposes to cover only two pen (small cattle room). However, the camera also covers neighboring pens. I need to get rid of the areas of the neighboring pens.
Input Image -
The Output image -
I have tried the following command and it does the job. However, it shrinks the size of the image and makes the output of the size of the bounding box generated in line 2. The output becomes smaller than the original image. In this case, the original image is 2560x1440 but the output is 2536x1406.
import cv2
import numpy as np
import matplotlib.pyplot as plt
frame = cv2.imread("input.jpg")
# pts - location of the 4 corners of the roi
pts = np.array([[6, 1425],[953, 20 ],[1934, 40 ], [2541,1340]])
rect = cv2.boundingRect(pts)
x, y, w, h = rect
croped = frame[y:y + h, x:x + w].copy()
pts = pts - pts.min(axis=0)
mask = np.zeros(croped.shape[:2], np.uint8)
cv2.drawContours(mask, [pts], -1, (255, 255, 255), -1, cv2.LINE_AA)
frame_roi = cv2.bitwise_and(croped, croped, mask=mask)
cv2.imwrite("output.jpg", frame_roi)
However, I need the output image to be the same size as the input image and anything out of the ROI to be black/white (shown below, it's a different picture though). Both the white or black masked region will work (the above output has black and hand edited image below has white). Is there a way of doing that with opencv or any other library?

The error was in this line
mask = np.zeros(croped.shape[:2], np.uint8)
which should be the exact same size as your original/input image. So changing that to the original shape should give the correct output image.
mask = np.zeros(original_image.shape, np.uint8)
Here's the shape of the output image
(1440L, 2560L, 3L)
import cv2
import numpy as np
original_frame = cv2.imread("1.jpg")
frame = original_frame.copy()
# pts - location of the 4 corners of the roi
pts = np.array([[6, 1425],[953, 20],[1934, 40], [2541,1340]])
(x,y,w,h) = cv2.boundingRect(pts)
pts = pts - pts.min(axis=0)
mask = np.zeros(original_frame.shape, np.uint8)
cv2.drawContours(mask, [pts], -1, (255, 255, 255), -1, cv2.LINE_AA)
result = cv2.bitwise_and(original_frame, mask)
cv2.imshow('mask', mask)
cv2.imshow('result', result)
cv2.imwrite('result.png', result)
print(result.shape)
cv2.waitKey(0)