Hi!
I’m very impressed that ABINet’s ability to recognize words. I am starting to use it to help identify words in old newspapers when Tesseract cannot accurately identify a word and returns results that have low confidence values. However, I’ve noticed that it ignores capitalization in words and punctuation. Is there a setting that can be used so that they can be included in the recognized text?
Thanks!
Hi! I’m very impressed that ABINet’s ability to recognize words. I am starting to use it to help identify words in old newspapers when Tesseract cannot accurately identify a word and returns results that have low confidence values. However, I’ve noticed that it ignores capitalization in words and punctuation. Is there a setting that can be used so that they can be included in the recognized text? Thanks!