Hi,
If you have done some serious OCR with C# and .Net and (preferably) Tesseract, please PM me.
Quick idea on what I need to do - I need to read the text off of some images - the images are plain white text on black background and the text is not skewed, tiled, etc. so that makes it easier. What makes it not so easy though is that these are not words but rather random symbols, so once you run the OCR, you cannot improve accuracy by say running the text against an English dictionary. Also, you can have two or more capital letters one next to each other and they can "touch," which might make the symbol segmentation more challenging.
I need really good accuracy - as close to 100% as it gets and ideally, the code will have to target .Net 4.5, but even if you have something that targets older version I want to hear from you.
Thank you
If you have done some serious OCR with C# and .Net and (preferably) Tesseract, please PM me.
Quick idea on what I need to do - I need to read the text off of some images - the images are plain white text on black background and the text is not skewed, tiled, etc. so that makes it easier. What makes it not so easy though is that these are not words but rather random symbols, so once you run the OCR, you cannot improve accuracy by say running the text against an English dictionary. Also, you can have two or more capital letters one next to each other and they can "touch," which might make the symbol segmentation more challenging.
I need really good accuracy - as close to 100% as it gets and ideally, the code will have to target .Net 4.5, but even if you have something that targets older version I want to hear from you.
Thank you