[tesseract-ocr] Trouble with Apparently Simple Source Image

2024-02-12 Thread Rob
Hello, I've run into some trouble using Tesseract OCR in a python program doing some screen scraping. I can't quite wrap my head around why this one value is having so much more trouble than the others on the same page, with the same contrast and font. This is the image in question: It has be

Re: [tesseract-ocr] Trouble with Apparently Simple Source Image

2024-02-12 Thread Zdenko Podobny
tesseract I_read_docs_carefully_instead_of_a_lot_of_writing.png - --psm 6 $0.081 Zdenko po 12. 2. 2024 o 18:40 Rob napísal(a): > Hello, > > I've run into some trouble using Tesseract OCR in a python program doing > some screen scraping. I can't quite wrap my head around why this one value > is

Re: [tesseract-ocr] Trouble with Apparently Simple Source Image

2024-02-12 Thread René JM Clais
Hi Rob, I try with my own python program with your picture and I get the following result: $0.081 Is this correct ? I use : custom_config = r' -l eng --psm 6 ' Does it help ? Cheers René Le lun. 12 févr. 2024 à 18:41, Rob a écrit : > Hello, > > I've run into some trouble using Tesseract OCR in

Re: [tesseract-ocr] Re: I need help to develop image to text extraction

2024-02-12 Thread Santhiya C
I had completed the training portion utilising the training tesseract OCR. After annotating the.box file, it did not change the misspelt character for my output extraction. I was followed this article only Training Tesseract-OCR with custom data. | by Sai Ashish | Medium

Re: [tesseract-ocr] Re: I need help to develop image to text extraction

2024-02-12 Thread Santhiya C
Word level extraction only On Tuesday 13 February 2024 at 11:10:03 UTC+5:30 Santhiya C wrote: > I had completed the training portion utilising the training tesseract OCR. > After annotating the.box file, it did not change the misspelt character for > my output extraction. > > I was followed th

[tesseract-ocr] Traineddata files

2024-02-12 Thread Philippe Argouarch
What if there is no traineddata files for a language ? How do I start building a trained data file for the breton language ? -- 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