GOCR (JOCR at SF.net)

GOCR is an optical character recognition program, released under the
GNU General Public License. It reads images in many formats  and outputs
a text file. Possible image formats are pnm, pbm, pgm, ppm, some pcx and
tga image files. Other formats like pnm.gz, pnm.bz2, png, jpg, tiff, gif,
bmp will be automatically converted using the netpbm-progs, gzip and bzip2
via unix pipe.
A simple graphical frontend written in tcl/tk and some
sample files are included.
Gocr is also able to recognize and translate barcodes.
You do not have to train the program or store large font bases.
Simply call gocr from the command line and get your results.

To see installation instructions, see the INSTALL file.

How to start? (QUICK START)
---------------------------
Some examples of how you can use gocr:

  gocr -h       			# help
  gocr file.pbm				# minimum options
  gocr -v 1 file.pbm >out.txt 2>out.log # generate text- and log file
  djpeg -pnm -gray text.jpg | gocr -	# using JPEG-files
  gzip -cd text.pbm.gz | gocr -		# using gzipped PBM-files
  giftopnm text.gif | gocr -		# using GIF-files
  gocr -v 1 -v 32 -m 4 file.pbm   	# zoning and out30.bmp output
  xli -geometry 400x400 out30.bmp # see details using xli (recommanded viewer)
  wish gocr.tcl			  # X11-tcl/tk-frontend (development version)
  # see manual pages for more details


How to get image files?
-----------------------
Scan text pages and save it as PGM/PBM/PNM file. Use a program such as
The GIMP or Sane. You can also use netpbm-progs to convert several image 
formats into PGM/PBM/PNM. The tool djpeg can be used to convert jpeg into pgm.
If you have a POSIX compatible system like linux and PNM-tools, gzip and bzip2
are installed, you are lucky and gocr will do conversion 
from [.pnm.gz, .pnm.bz2, .jpg, .jpeg, .bmp, .tiff, .png, .ps, .eps]
to [.pgm] for you. This list can easily be extended editing src/pnm.c.

Gocr also comes with some examples, try: make examples.

Memory limitations
------------------
WARNING!!!

If you use a 300dpi scan of A4 letter, the image is about 2500x3500 pixels and
gocr requires 8.75MB for storing the picture into the memory. Not only that,
but gocr may create a 2nd copy, using a total of 17MB. This is independent
of using b/w or gray-scale images. Be sure that you have enough RAM installed
in your machine! Alternatively you can cut the picture into small pieces.
You can use the pnmcut, from the netpbm package to cut the file. Example:

pnmcut -left 0 -right 2500 -top 0 -height 1000 bigfile.pnm > smallfile.pnm

And then use gocr in the cropped image as usual. Take care: if you chopp the
characters, gocr won't be able to understand that line.

Future versions will take care of this issue automatically.

Limitations
-----------
gocr is still in its early stages. Your images should fit in these requirements
if you want a good output:

- good scans (all chars well seperated, one column, no tables etc, 12pt 300dpi)
  should work well
- fonts 20-60 pixels ( 5pt * 1in/72pt * 300 dpi = 20 dots )
- output of image file for controlling detection

And note that speed is very slow (this will be changed when recognition works 
well)
  12pt 300dpi 1700x950 16lines 700chars 22x28 P90=40s..90s v0.2.3 (gcc -O0)

You can try to optimize the results:
- make good scans/treat image
- try to change the critical gray level (option -l <n>)
- control the result on out10.png, out30.png (option -v 32)
  example: ./gocr -v 32 -m 4 -m 256 -m 56 ~/aac.jpg # only check layout
- enlarge option -d <n> for high resolution images which are noisy
- try different combinations for option -m <n>
- for thousends of documents with same font
  you can use/create a database (-m 2/-m 130)
- use options -d 0 -m 8 on screen shots (font8x12)
- use filter option -C to through out wrong recognized chars (ex: gothic)

What does >> NOT << work at the moment:
- complex layouts (try option -m 4)
- bad scans, noisy/snowy images, FAX-quality images
- serif fonts, italic fonts, slanted fonts
- handwritten texts (this is valid for the next ten years I guess)
   the exisctence of autotrace can shorten this 
- rotated images (but slightly rotated images should be no problem)
- small fonts (fax like) or mix of different font size
- colored images (use gray or black/white)
- Chinese, Arabian, Egyptian, Cyrillic or Klingon fonts

How it works or how it should work?
- put the entire file into RAM (300dpi grayscale recommended)
- remove dust and snow
- detect small angle (lines which are not horizontal)
- detect text boxes (option -m 4)
- detect text-lines
- detect characters
- first step recognition (every character has its own empirical procedure)
  - no neural network or similar general algorithms
- analyze not detected chars by comparison with detected ones
- try to divide overlapping chars
- testwise: compare all letters (like compression of pictures)
- for more details look to the gocr.html documentation

Why the result of the new version are worse compared to the old version?
- the algorithms of gocr are sometimes evolutionary, a fine tuned old
  algorithm will be replased by a completly new algorithm which is more
  general but a bit worse for your problem.
  Please send your sample and give the new algo the chance to become
  better as the old one.

Security
--------
Because gocr only reads and writes files it is quite sure, except the
popen-function which allows you to call gocr with non-pnm-image formats
directly. The popen function can be misused to start other probably 
dangerous programs.
If you care about conversion to pnm format, you can safely disable
popen-function by removing "#define HAVE_POPEN 1" from config.h before
compiling the gocr package.


How can you help gocr?
----------------------
- Send comments, ideas and patches (diff -ru gocr_original/ gocr_changed/).
- If you have a lot of money, spend a bit (paypal). Ok, paypal has changed,
  so please forget about it. Also the importand problem is now the missing
  spare time for coding.
- I always need example files (.pbm.gz or jpeg <100kB) for testing
  the behavior of the ocr engine under different conditions, 
  because scanning does take a lot of time which I do not have.
  But do not send files which are not convertable by commercial ocr programs
  or which are protected from copying and electronic processing by copyright.
  That will help, to get the world's best OCR open source program. :) Thanks!
- Please dont send captchas.
- Send me your results (errors,num_chars,dpi) and if possible results
  and name of professional OCR programs for statistics.
- Read OCR literature, extract the essentials and send a short report
  to me ;).
- If you have a good idea, how to manage some OCR-tasks, tell me!
- Tell your friends about gocr. Tell me about your success. Be happy.


After all, is it gocr or jocr?
------------------------------
The original name of this project is gocr, from GNU Optical Character
Recognition. Another project is using the same name, however; so the
name was changed to jocr. If you have a good idea for a name, please
send it.


Latest news
------------
  http://jocr.sourceforge.net

Authors: (see AUTHORS)