windows - Tuning tesseract command line to OCR prices -
i have small images prices in them following:
but getting empty output file when try command:
tesseract image.png output.txt
are there special commands should use ocr such small images this? also, can specify possible results dollar sign, period, , numbers 0-9?
i have tried "letters" method adding config file, haven't found data on whether dollar sign or period need escaped. in case, getting 0 response simple version of command above.
what version of tesseract using? using following command:
tesseract image.png output -psm 8
i result.
$12705
note dot missing. may able dot pre-processing image using dilation algorithm.
version info: tesseract 3.03.00 (windows 7) leptonica-1.70 (aug 5 2014, 21:29:11) [msc v.1800 dll release x86] libgif 4.1.6(?) : libjpeg 8c : libpng 1.4.3 : libtiff 3.9.4 : zlib 1.2.8
Comments
Post a Comment