Creating a replica of a screenshot with Snipping tool

[Khuram-2521]

I want to make a simple replica of an image taken in Audacity's macro dialog boxes. I have tried creating an image with Pillow that has the text and almost similar background which is apparently similar to the screenshot but not detectable by PyAutoGui on confidence range >= 0.7

Apparently there is an unordered color combination in the picture that involves audacity background and the text, I have tried changing ARGB values to reach 0.6 confidence but no success on pushing it forward. Any help would be really appreciated!

[radarhere]

Could you post a self-contained copy of the code that you are using, including an images that it uses as input?

[radarhere]

from PIL import Image, ImageFont, ImageDraw

def text_to_image(text: str, font_filepath: str) -> None:
    img = Image.new("RGB", (107, 20), "#fff")
    font = ImageFont.truetype(font_filepath, 14)
    draw = ImageDraw.Draw(img)
    
    draw.line((2, 0, 2, 20), "#d0d1d6")
    draw.line((3, 0, 3, 20), "#92929a")

    draw.text((9, -1), text, font=font, fill=(45, 53, 63))
    img.save('prevMacro.PNG')

text_to_image('10 (Macro_10)', '/System/Library/Fonts/Supplemental/Arial.ttf')

This is closer.

[radarhere]

Was that close enough? If not, is there any simple way for us to be able to know when we do hit the mark?

[MasterOz786]

It was similar to the image text, but I think that the background of the Audacity screen is messing things up. The confidence level of detection obtained is still below the mark. Are there any possible way outs?

[radarhere]

I mean, you can open up the original image in Gimp and move parts of the image around until you just have the line and a speckled background

and then write text on top of it

from PIL import Image, ImageFont, ImageDraw

def text_to_image(text: str, font_filepath: str) -> None:
    img = Image.open('background.png')
    font = ImageFont.truetype(font_filepath, 14)
    draw = ImageDraw.Draw(img)
    
    draw.text((9, -1), text, font=font, fill=(45, 53, 63))
    img.save('prevMacro.PNG')

text_to_image('10 (Macro_10)', '/System/Library/Fonts/Supplemental/Arial.ttf')

giving

but I then start to wonder about why you need to do this programmatically in the first place, since the perfect replica would just be the original image itself.

[radarhere]

Was that helpful?

[MasterOz786]

Sorry for the late reply, it was fixed by using tesseract instead.