hocr - command line Hebrew OCR tool
example programs for libhocr, a library that help use Hebrew character
hocr [OPTION] [-i] [pnm file]
hocr is an optical character recognition program that can be used from
the command line. It takes input in pbm format, and writes recognized
utf-8 Hebrew text to stdout. Input pbm file must be a binary black and
white pnm file (magic "P4/5"). If the pnm file is a single dash (or no
file given), PNM data is read from stdin.
-h show usage information
read input from file
send output to file instead of stdout
-d use internal dictionary to guess misread fonts.
-n try to guess nikud for fonts.
-s use spaces for tabs.
-t indent indented lines.
output format (html text)
write PPM image with boxes around detected characters to file.
Yaacov Zamir 2005.