can I use plus-minus sign in CharacterSet while reading text with ocr function?

i'm trying to use the the values from screen-captured image with using ocr function.

in that text, there is almost numerical values, plus, minus, commas, and plus-minus sign. (which is ±)

i've added the sign into the function like

res = ocr(img, 'CharacterSet','Test1234567890+-,±');

but no luck.

am I allowed to use that character? if there's any method for that, please let me know.

thanks in advance!

[Angelo Yeo]

Here is my reproduction:

img = imread("image.png");
imshow(img)

txt = ocr(img, "CharacterSet", "123456±+-");
txt.Text

ans = 
    '123+456
     
     '

[제파 양]

that is what I've done exactly same. captured from PPT, input into image and resulting it.

thanks for the great reproduction.

Answer 1

[Angelo Yeo]

That's a very good observation! It's unfortunate that the shipped ocr function doesn't work as you expected.

In some cases, to get accurate recognition results, you must train a custom OCR model. For example, when the text in your images use a proprietary font that is significantly different from any of the available fonts, or when OCR results are not what you expect even after trying the troubleshooting steps. For more details on how to train a custom OCR model, see Train Custom OCR Model.

[제파 양]

oh. Thanks for the workaround.

it will take a bunch of time for the training, however the result can be fruity. i will try.