programs optical character recognition gocr appear to be open source as a low level of development, rather to put all their performances are rather disappointing. But recently the situation seems to be changed because HP has a new release under the Apache License Professional OCR engine called Tesseract
The development of Tesseract by HP lasted nine years (1985 -1994). Now the development of the program is continuing with a new development team, the source code can be freely downloaded from the servers of Google Code,
tessecart present in the repository of many distros like ubuntu and fedora and opensuse Mandrivia but if you want to install it without test point your browser at the following address Address
http://asv.aso.ecei .tohoku.ac.jp / tesseract /
NB in \u200b\u200bmy tests on opensuse 11, the program can only handle BMP
Name: | Tesseract |
Location: | |
Version: | 1.04b |
Input Format: | tiff |
Accuracy: | 99% |
Easy of Use: | 2/5 |
0 comments:
Post a Comment