This is ocrad.info, produced by makeinfo version 4.8 from ocrad.texinfo. INFO-DIR-SECTION GNU Packages START-INFO-DIR-ENTRY * Ocrad: (ocrad). The GNU OCR program. END-INFO-DIR-ENTRY  File: ocrad.info, Node: Top, Next: Character Sets, Up: (dir) GNU Ocrad ********* This manual is for GNU Ocrad (version 0.17, 29 June 2007). GNU Ocrad is an OCR (Optical Character Recognition) program based on a feature extraction method. It reads images in pbm (bitmap), pgm (greyscale) or ppm (color) formats and produces text in byte (8-bit) or UTF-8 formats. The pbm, pgm and ppm formats are collectively known as pnm. Ocrad includes a layout analyser able to separate the columns or blocks of text normally found on printed pages. * Menu: * Character Sets:: Input charsets and output formats * Invoking Ocrad:: Command line interface * Image Format Conversion:: How to convert other formats to pnm * Algorithm:: How ocrad does its job * Problems:: Reporting bugs * Concept Index:: Index of concepts Copyright (C) 2003, 2004, 2005, 2006 Antonio Diaz Diaz. Permission is granted to copy, distribute and/or modify this document under the terms of the GNU Free Documentation License, Version 1.2 or any later version published by the Free Software Foundation; with no Invariant Sections, no Front-Cover Texts, and no Back-Cover Texts.  File: ocrad.info, Node: Character Sets, Next: Invoking Ocrad, Prev: Top, Up: Top 1 Character Sets **************** The character set internally used by ocrad is ISO 10646, also known as UCS (Universal Character Set), which can represent over two thousand million characters (2^31). As it is unpractical to try to recognize one among so many different characters, you can tell ocrad what character sets to recognize. You do this with the `--charset' option. If the input page contains characters from only one character set, say `ISO-8859-15', you can use the default `byte' output format. But in a page with `ISO-8859-9' and `ISO-8859-15' characters, you can't tell if a code of 0xFD represents a 'latin small letter i dotless' or a 'latin small letter y with acute'. You should use `--format=utf8' instead. Of course, you may request UTF-8 output in any case. NOTE: Don't believe everything Usamericans tell you. A billion is a million millions (million^2), a trillion is a million million millions (million^3), and so on. Please, respect the meaning of prefixes to make communication among all people possible. Thanks.  File: ocrad.info, Node: Invoking Ocrad, Next: Image Format Conversion, Prev: Character Sets, Up: Top 2 Invoking Ocrad **************** The format for running ocrad is: ocrad [OPTIONS] [FILES] Ocrad supports the following options: `--help' `-h' Print an informative help message describing the options and exit. `ocrad --verbose --help' describes also hidden options. `--version' `-V' Print the version number of ocrad on the standard output and exit. `--append' `-a' Append generated text to the output file instead of overwriting it. `--block=NUMBER' `-b NUMBER' Process only the specified text block, beginning from 1. Is only useful when used in conjunction with layout analysis (see below). `--charset=NAME' `-c NAME' Enable recognition of the characters belonging to the given character set. You can repeat this option multiple times with different names for processing a page with characters from different character sets. If no charset is specified, `iso-8859-15' (latin9) is assumed. Try `--charset=help' for a list of valid charset names. `--crop=LEFT,TOP,RIGHT,BOTTOM' `-p LEFT,TOP,RIGHT,BOTTOM' Crop the input image by the rectangle defined by LEFT, TOP, RIGHT and BOTTOM. The values of LEFT, TOP, RIGHT and BOTTOM may be relative to the image size (0.0 <= value <= 1.0), or absolute (value > 1). Absolute and relative values may be mixed. For example `ocrad --crop 700,960,1,1' will work as expected. The cropping is performed before any other transformation (rotation or mirroring) on the input image, and before scaling, layout analysis and recognition. `--filter=NAME' `-e NAME' Pass the output text through the given postprocessing filter. `--filter=letters' forces every character that resembles a letter to be recognized as a letter. Other characters will be output without change. `--filter=letters_only', same as `--filter=letters', but other characters will be discarded. `--filter=numbers' forces every character that resembles a number to be recognized as a number. Other characters will be output without change. `--filter=numbers_only', same as `--filter=numbers' but other characters will be discarded. Try `--filter=help' for a list of valid filter names. `--force' `-f' Force overwrite of output file. `--format=NAME' `-F NAME' Select the output format. The valid names are `byte' and `utf8'. If no output format is specified, `byte' (8 bit) is assumed. `--invert' `-i' Invert image levels (white on black). `--layout=MODE' `-l MODE' Enable page layout analysis. The meaning of MODE is: `0' no analysis at all, `1' column separation, `2' full analysis. `-o FILE' Place the output into FILE instead of into the standard output. `--scale=VALUE' `-s VALUE' Scale the input image by VALUE before layout analysis and recognition. If VALUE is negative, the input image is scaled down by -VALUE. `--transform=NAME' `-t NAME' Perform given transformation (rotation or mirroring) on the input image before scaling, layout analysis and recognition. Try `--transform=help' for a list of valid transformation names. `--threshold=VALUE' `-T VALUE' Set binarization threshold for pgm or ppm files or for `--scale' option (only for scaled down images). VALUE should be a rational number between 0 an 1, and may be given as a percentage (50%), a fraction (1/2), or a decimal value (0.5). Image values greater than threshold are converted to white. The default value is 0.5. `--verbose' `-v' Verbose mode. `-x FILE' Write (export) OCR Results File to FILE. `-x -' writes to stdout, overriding text output except if output has been also redirected with the -o option.  File: ocrad.info, Node: Image Format Conversion, Next: Algorithm, Prev: Invoking Ocrad, Up: Top 3 Image Format Conversion ************************* There are a lot of image formats, but ocrad is able to decode only three of them; pbm, pgm and ppm. In this chapter you will find command examples and advice about how to convert image files to a format that ocrad can manage. `.png' Portable Network Graphics file. Use the command `pngtopnm filename.png | ocrad'. In some cases, like the ocrad.png icon, you have to invert the image with the `-i' option: `pngtopnm filename.png | ocrad -i'. `.ps' `.pdf' Postscript or Portable Document Format file. Use the command `gs -sPAPERSIZE=a4 -sDEVICE=pnmraw -r300 -dNOPAUSE -dBATCH -sOutputFile=- -q filename.ps | ocrad'. You may also use the command `pstopnm -stdout -dpi=300 -pgm filename.ps | ocrad', but it seems not to work with pdf files. Also old versions of `pstopnm' don't recognize the `-dpi' option and produce an image too small for OCR. `.tiff' TIFF file. Use the command `tifftopnm filename.tiff | ocrad'. `.jpg' JPEG file. Use the command `djpeg -greyscale -pnm filename.jpg | ocrad'. JPEG is a lossy format and is in general not recommended for text images. `.pnm.bz2' Pnm file compressed with bzip2. Use the command `bunzip2 -c filename.pnm.bz2 | ocrad' `.pnm.gz' Pnm file compressed with gzip. Use the command `gunzip -c filename.pnm.gz | ocrad'  File: ocrad.info, Node: Algorithm, Next: Problems, Prev: Image Format Conversion, Up: Top 4 Algorithm *********** Ocrad is mainly a research project. Many of the algorithms ocrad uses are ad hoc, and will change in successive releases as I myself gain understanding about OCR issues. The overall working of ocrad may be described as follows: 1) read the image. 2) optionally, perform some transformations (crop, rotate, scale, etc). 3) optionally, perform layout detection. 4) remove frames and images. 5) detect characters and group them in lines. 6) recognize characters (very ad hoc; one algorithm per character). 7) correct some errors (transform l.OOO into 1.000, etc). 8) output result. Ocrad recognizes characters by its shape, and the reason it is so fast is that it does not compare the shape of every character against some sort of database of shapes and then chooses the best match. Instead of this, ocrad only compares the shape differences that are relevant to choose between two character categories, mostly like a binary search. As there is no such thing as a free lunch, this approach has some drawbacks. It makes ocrad very sensitive to character defects, and makes difficult to modify ocrad to recognize new characters.  File: ocrad.info, Node: Problems, Next: Concept Index, Prev: Algorithm, Up: Top 5 Reporting Bugs **************** If you find a bug in GNU Ocrad, please send electronic mail to . Include the version number, which you can find by running `ocrad --version'.  File: ocrad.info, Node: Concept Index, Prev: Problems, Up: Top Concept Index ************* [index] * Menu: * algorithm: Algorithm. (line 6) * bugs: Problems. (line 6) * getting help: Problems. (line 6) * image format conversion: Image Format Conversion. (line 6) * input charsets: Character Sets. (line 6) * invoking: Invoking Ocrad. (line 6) * options: Invoking Ocrad. (line 6) * output format: Character Sets. (line 6) * usage: Invoking Ocrad. (line 6) * version: Invoking Ocrad. (line 6)  Tag Table: Node: Top198 Node: Character Sets1368 Node: Invoking Ocrad2511 Node: Image Format Conversion6397 Node: Algorithm7921 Node: Problems9181 Node: Concept Index9465  End Tag Table