Hi Gunsuka,
These images may need some morphological operations
on them before you can OCR using tesseract. However, you may use Amazon
Rekognition to get faster and better results. In case you are fine, I will
provide you the code. Meanwhile I ran through these examples and was able
to get 90- 95% accurate results.
Regards,
Ananth
On Monday, 30 August 2021 at 00:13:57 UTC-5 Gunsuka wrote:
> I wanted to build something that could open a photo and extract the text,
> OCR seems like the perfect task.
>
> The photos can come from various sources, but are photos of license
> plates. I'm attaching a couple of examples.
>
> So far I can't get Tesseract to identify anything, not even a single
> character.
>
> I know Tesseract is working as if I feed it sample files, or snippets of
> website text that will work but this type of image, zero, zip, nadda.
>
> Is there any hope for this type of image?
>
>
>
>
--
You received this message because you are subscribed to the Google Groups
"tesseract-ocr" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to tesseract-ocr+unsubscr...@googlegroups.com.
To view this discussion on the web visit
https://groups.google.com/d/msgid/tesseract-ocr/becad729-8540-4856-9756-194402f2cde2n%40googlegroups.com.
