Image editing using python

Question

I have an image.

I want to erase its background and get a white or transparent background preferably without the black dotes. I am trying PIL in python:

img1 = img.convert("L") 
img1.show() 
img1.save("im1.jpg")

and also

img2 = img.convert("1") 
img2.show() 
img1.save("im1.jpg")

This gives something like this:

Trying with matplotlib:

import matplotlib.pyplot as plt

plt.imshow(img1,cmap=plt.cm.binary)
plt.show()
plt.savefig("im1.jpg")

makes the background black, the original green as grey and the original black dots as white.

Can you suggets what I can try?

usually you won't find much help on solving captchas. they are a fun challenge but if we tell you how to solve them, where is the fun? and if it is not just a fun challenge we would help you circumvent them where people put them in place to keep you out. that's not very ethical. also you should do your won research befor asking for help. I don't see this from your post — Piglet
– Piglet, Commented Jun 29, 2020 at 6:54
@Piglet Well I have tried CNN with emnist and captcha data but they did not help much with my captcha. Now I am trying to build my own dataset to make a CNN but it seems not the perfect answer. — Khabbab Zakaria
– Khabbab Zakaria, Commented Jun 29, 2020 at 7:09
your code only shows that you display the image. there is no effort to do any image processing. suggesting a solution for this image would not help you much as every image will be different. here you could simply extract green pixels. — Piglet
– Piglet, Commented Jun 29, 2020 at 7:51

Sherin Jayanand · Accepted Answer · 2020-06-29 08:27:17Z

1

I agree with @Piglet it is not fun if we tell you how to do it. To get you excited here is something I got when I played around:-

import cv2
import numpy as np
image = cv2.imread('captcha.jpg')
hsv=cv2.cvtColor(image,cv2.COLOR_BGR2HSV)
    # Set minimum and maximum HSV values to display
hMin=0
sMin = 37
vMin = 0
hMax = 179
sMax = 255
vMax = 255

lower = np.array([hMin, sMin, vMin])
upper = np.array([hMax, sMax, vMax])
mask = cv2.inRange(hsv, lower, upper)
result = cv2.bitwise_and(image, image, mask=mask)

cv2.imshow('image', result)
while 1==1:
    k=cv2.waitKey(10)
    if k==27:
        cv2.destroyAllWindows()
        break;

Hope this gets you going...

answered Jun 29, 2020 at 8:27

Sherin Jayanand

2042 silver badges9 bronze badges

Sign up to request clarification or add additional context in comments.

Collectives™ on Stack Overflow

Image editing using python

1 Answer 1

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Related