Tesseract Open Source OCR Engine
Tesseract is a free optical character recognition engine originally developed at Hewlett-Packard and currently developed by Google. It is a raw OCR engine - it has no document layout analysis, no output formatting, and no graphical user interface. It only processes a TIFF or BMP image of a single column and creates text from it. It can detect fixed pitch vs proportional text. The engine was in the top 3 in terms of character accuracy in 1995. The source code will read a binary, grey or color image and output text.
Tesseract can process English, French, Italian, German, Spanish, Brazilian, Portuguese and Dutch and can be trained to work in other languages as well.
- Sources inherited from project openSUSE:Leap:42.1
- Download package
-
Checkout Package
osc -A https://api.opensuse.org checkout openSUSE:Leap:42.1:Ports/tesseract-ocr && cd $_ - Create Badge
Refresh
Refresh
Source Files
| Filename | Size | Changed |
|---|---|---|
| 3.04.00.tar.gz | 0002264427 2.16 MB | |
| tesseract-ocr.changes | 0000006503 6.35 KB | |
| tesseract-ocr.spec | 0000003821 3.73 KB |
Latest Revision
Stephan Kulow (coolo)
accepted
request 337049
from
Ismail Dönmez (namtrac)
(revision 3)
- Update to version 3.04.00:
* Added OpenCL support (experimental).
* Many bug fixes.
From version 3.03.00:
* Added new training tool text2image to generate box/tif file
pairs from text and truetype fonts.
* Added support for PDF output with searchable text.
* Removed entire IMAGE class and all code in image directory.
* Tesseract executable: support for output to stdout; limited
support for one page images from stdin (especially on Windows)
* Added Renderer to API to allow document-level processing and
output of document formats, like hOCR, PDF.
* Major refactor of word-level recognition, beam search,
eliminating dead code.
* Refactored classifier to make it easier to add new ones.
* Generalized feature extractor to allow feature extraction from
greyscale.
* Improved sub/superscript treatment.
* Improved baseline fit.
* Added set_unicharset_properties to training tools.
* Many bug fixes.
* More training source data included.
- Added new build requirements cairo-devel, doxygen, libicu-devel
and pango-devel.
- Recommend tesseract-ocr-traineddata-english instead of
tesseract-ocr-traineddata-american (based on new (3.04.00)
tesseract-ocr traineddata files).
Comments 0