[tesseract-ocr] Low Quality image but little no Noise

2022-09-15 Thread Shester Msouobu
Hey ! I have a set of lot quality images tesseract can't well read. Though there is literally no noise on there. Any help ? Example [image: images1871.png] Tesseract output "Cerra)" -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsu

Re: [tesseract-ocr] Low Quality image but little no Noise

2022-09-15 Thread Zdenko Podobny
Did you try documentation? Zdenko št 15. 9. 2022 o 11:43 Shester Msouobu napísal(a): > Hey ! I have a set of lot quality images tesseract can't well read. Though > there is literally no noise on there. Any help ? > > Example > > [image: images1871.png] > > Tesseract output > "Cerra)" > > -- >

Re: [tesseract-ocr] Low Quality image but little no Noise

2022-09-15 Thread vc Jayan
Hi I think its due to the inverse binary issue. Black textbooks in white background is needed to detect and read. On Thu, 15 Sep, 2022, 3:13 pm Shester Msouobu, wrote: > Hey ! I have a set of lot quality images tesseract can't well read. Though > there is literally no noise on there. Any help ?

[tesseract-ocr] Seems like the dictionary isn't used

2022-09-15 Thread צביקה הרמתי
Hi. 1. I've an image that's written in a "Science Fiction" style font, where 'E' is written similarly to '='. Therefore, the attached image is recognized as "AR= YOU SURE YOU WANT TO QuIT >" However, since Tesseract is using an English dictionary, I'd expect it to understand that "ARE" is much

[tesseract-ocr] Tessarct changed behaviour inside docker

2022-09-15 Thread Gabriel Sousa
Hi there, I'm new to this group, and also new to using Tesseract in general. We use py-tesseract for a few data extraction, not many cases, at the company I work for and for no apparent reason, tesseract text extraction stopped working from one deploy to another. It should extract a word such