static void
                       _f_do_barnacle_install_properties(GObjectClass
                                        ...
What is it?

Document Analysis and Optical
   Character Recognition
        for GNOME


                   Joaquim Rocha (...
Why is it?

 Paper has a number of problems

No applications for GNU/Linux to do
             a fair job

                ...
Paper problems:
   Security




                        Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
          CC Phot...
Paper problems:
 Preservation




                        Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
   CC Photo by:...
Paper problems:
Data processing




                     Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
     CC Photo by...
Paper problems:
   Ecology




                          Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
        CC Photo...
No fair conversion apps for
          GNU/Linux

apart from OCR engines, but...



                   Joaquim Rocha (Igali...
OCR != Document Conversion

    (it only deals with chars)
 (does not consider the layout)
(does not distinguish contents)...
what you want is

  Document Analysis and
      Recognition

(conversion of documents to an
        electronic format)
   ...
Where are were we at?

   * Some closed solutions
* Only for proprietary systems
        * Various prices
   * still... ar...
How?




       Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
How




      Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
Base concept:

          1. Clip the contents
            2. Classify them
 2.1. They are graphics → Paste on
            ...
So many layouts...




                              Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
          CC Photo b...
Layouts vary with the type of
            document

What works on detecting one, won't
         work on others


         ...
OCRFeeder focus on contents, not
         on layouts!




                    Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM ...
Key concept:

   If a document image can be
divided in windows of 1 (content)
         or 0 (not content),
then it is poss...
Sliding Window Algorithm:

1. A NxN pixel window runs through
 the document top to bottom, left to
                right

...
Sliding Window Algorithm:

2. For every iteration, if there's a
 pixel inside the window which
 contrasts with the backgro...
Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
Sliding Window Algorithm:

It does not check all the pixels so
   there is a better performance




                      ...
Sliding Window Algorithm:

     3. After all windows
   have a value assigned,
the ones with the value 1 are
            g...
Sliding Window Algorithm:

 4. Every time a set of 1s is
  grouped, each window is
   reassigned the value 0


  (these ar...
Sliding Window Algorithm:

 5. When all windows have
 the value 0, the algorithm
      reached the end


                 ...
Block structure:




            Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
Joining Blocks:

Blocks are check with each other
  and joined when appropriate

When no blocks can be joined the
   analy...
Recognition:

System-wide OCR engines are used

 Engines are configured from the
        GUI or XML files

               ...
Engine configuration:

<?xml version="1.0" encoding="UTF-8"?>
<engine>
   <name>Tesseract</name>
   <image_format>TIFF</im...
Classification:


          It is graphics if:

          * Text is empty

  * More than 50% of the chars are
failure char...
Font Size Detection:

“Measures” in pixels the size of
        each text line




 Although it results in different
      ...
Font Size Detection:

The value equal or greater than the
        average is chosen


(results in values equal or close to...
Font Size Detection:

The font size is calculated in inches
      using the resolution (DPI)
(if there's no resultion info...
Exportation to ODT:

     Uses ODFPy

(abstracts ODF creation)
   (just above XML)

                Joaquim Rocha (Igalia)...
User interaction:

   Users can edit everything
and review the algorithm's results

So, UI can work in attended and
      ...
ABBY Finereader test




Nuance Omnipage test




                       Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
Finereader's
                                              results


Omnipage's
results




             Joaquim Rocha (Ig...
Demo time!




         Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
Other features:

   * PDF importation
* Unpaper preprocessor
   * Font style edition
 * Exportation to HTML
* Project savi...
Future:

     * Integrate Ocropus as an
    alternative analysis backend
* More exportation formats: HOCR,
               ...
GNOME:

Development moved to GNOME's
 infrastructure since last month




                    Joaquim Rocha (Igalia) · OCR...
Webpage:
http://live.gnome.org/OCRFeeder

               git:
 http://git.gnome.org/ocrfeeder

          Bugzilla:
       ...
Thank you!

         Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
Upcoming SlideShare
Loading in...5
×

OCRFeeder, documents conversion on GNOME

2,678

Published on

The presentation of OCRFeeder for the GNOME track in FOSDEM 2010.

Published in: Technology
0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total Views
2,678
On Slideshare
0
From Embeds
0
Number of Embeds
2
Actions
Shares
0
Downloads
15
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide

OCRFeeder, documents conversion on GNOME

  1. 1. static void _f_do_barnacle_install_properties(GObjectClass *gobject_class) { OCRFeeder GParamSpec *pspec; /* Party code attribute */ pspec = g_param_spec_uint64 (F_DO_BARNACLE_CODE, "Barnacle code.", "Barnacle code", 0, G_MAXUINT64, G_MAXUINT64 /* default value */, Documents conversion on GNOME G_PARAM_READABLE | G_PARAM_WRITABLE | G_PARAM_PRIVATE); g_object_class_install_property (gobject_class, F_DO_BARNACLE_PROP_CODE, Joaquim Rocha jrocha@igalia.com FOSDEM 2010
  2. 2. What is it? Document Analysis and Optical Character Recognition for GNOME Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  3. 3. Why is it? Paper has a number of problems No applications for GNU/Linux to do a fair job Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  4. 4. Paper problems: Security Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010 CC Photo by: http://www.flickr.com/photos/badwsky/
  5. 5. Paper problems: Preservation Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010 CC Photo by: http://www.flickr.com/photos/98469445@N00/
  6. 6. Paper problems: Data processing Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010 CC Photo by: http://www.flickr.com/photos/hugovk/
  7. 7. Paper problems: Ecology Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010 CC Photo by: http://www.flickr.com/photos/pranavsingh/
  8. 8. No fair conversion apps for GNU/Linux apart from OCR engines, but... Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  9. 9. OCR != Document Conversion (it only deals with chars) (does not consider the layout) (does not distinguish contents) Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  10. 10. what you want is Document Analysis and Recognition (conversion of documents to an electronic format) (first projects in the 80s) Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  11. 11. Where are were we at? * Some closed solutions * Only for proprietary systems * Various prices * still... arguable results Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  12. 12. How? Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  13. 13. How Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  14. 14. Base concept: 1. Clip the contents 2. Classify them 2.1. They are graphics → Paste on document 2.2. They are text → Calculate letter size; paste on document Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  15. 15. So many layouts... Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010 CC Photo by: http://www.flickr.com/photos/uber-tuber/
  16. 16. Layouts vary with the type of document What works on detecting one, won't work on others Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  17. 17. OCRFeeder focus on contents, not on layouts! Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  18. 18. Key concept: If a document image can be divided in windows of 1 (content) or 0 (not content), then it is possible to group all the 1s and outline the contents Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  19. 19. Sliding Window Algorithm: 1. A NxN pixel window runs through the document top to bottom, left to right Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  20. 20. Sliding Window Algorithm: 2. For every iteration, if there's a pixel inside the window which contrasts with the background, then the window gets a 1, otherwise it gets a 0 Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  21. 21. Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  22. 22. Sliding Window Algorithm: It does not check all the pixels so there is a better performance Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  23. 23. Sliding Window Algorithm: 3. After all windows have a value assigned, the ones with the value 1 are grouped Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  24. 24. Sliding Window Algorithm: 4. Every time a set of 1s is grouped, each window is reassigned the value 0 (these are called blocks) Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  25. 25. Sliding Window Algorithm: 5. When all windows have the value 0, the algorithm reached the end Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  26. 26. Block structure: Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  27. 27. Joining Blocks: Blocks are check with each other and joined when appropriate When no blocks can be joined the analysis part is finished Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  28. 28. Recognition: System-wide OCR engines are used Engines are configured from the GUI or XML files Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  29. 29. Engine configuration: <?xml version="1.0" encoding="UTF-8"?> <engine> <name>Tesseract</name> <image_format>TIFF</image_format> <engine_path>/usr/bin/tesseract</engine_path> <arguments>$IMAGE $FILE; cat $FILE.txt; rm $FILE.txt</arguments> </engine> Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  30. 30. Classification: It is graphics if: * Text is empty * More than 50% of the chars are failure chars, punctuation or spaces Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  31. 31. Font Size Detection: “Measures” in pixels the size of each text line Although it results in different sizes... Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  32. 32. Font Size Detection: The value equal or greater than the average is chosen (results in values equal or close to the original font size) Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  33. 33. Font Size Detection: The font size is calculated in inches using the resolution (DPI) (if there's no resultion info, assume 300 DPI) The value is then divided by the DTP (DeskTop Publishing point): 72 Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  34. 34. Exportation to ODT: Uses ODFPy (abstracts ODF creation) (just above XML) Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  35. 35. User interaction: Users can edit everything and review the algorithm's results So, UI can work in attended and unattended ways CLI only works in an unattended mode Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  36. 36. ABBY Finereader test Nuance Omnipage test Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  37. 37. Finereader's results Omnipage's results Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  38. 38. Demo time! Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  39. 39. Other features: * PDF importation * Unpaper preprocessor * Font style edition * Exportation to HTML * Project saving/loading Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  40. 40. Future: * Integrate Ocropus as an alternative analysis backend * More exportation formats: HOCR, txt, PDF * Improved a11y * Better integration with GNOME and other GNOME apps Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  41. 41. GNOME: Development moved to GNOME's infrastructure since last month Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  42. 42. Webpage: http://live.gnome.org/OCRFeeder git: http://git.gnome.org/ocrfeeder Bugzilla: coming soon... Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  43. 43. Thank you! Joaquim Rocha (Igalia) · OCRFeeder · FOSDEM 2010
  1. Gostou de algum slide específico?

    Recortar slides é uma maneira fácil de colecionar informações para acessar mais tarde.

×