Thanks Rich. I will test out gocr .
On Wed, Nov 5, 2025, 21:40 Rich Shepard <[email protected]> wrote: > On Tue, 4 Nov 2025, VY wrote: > > > The problem that I am facing so far. I use a mediocre Android phone to > > scan/convert the form into a PDF (I use Adobe Scan app) just as a test. > > Then I tried tesseract or some python libs to recognize the words (both > > the printed questions on the form as well as hand-writing words). Both > > tesseract or the python libs can recognize the printed questions but > > handle very poorly on the hand-writing words. I suspect maybe my phone > > camera is not "good enough" even though it is advertised to be 50MP. > > VY, > > I've not used OCR in a very long time yet reading the above brought a > thought to mind so I'm making it public. FWIW, I successfully used gocr for > my scanned-to-text needs. > > I've seen paper forms (e.g., Aetna health insurance reimbursement request) > where all user input is in sets of boxes, one character per box. No cursive > allowed so each character should be more easily identified by the OCR > software. > > HTH, > > Rich >
