Date: a month ago   Category: Hi-Tech

Release of the Tesseract 3.0 OCR system


The release of system of optical recognition of the text of Tesseract 4.0 supporting recognitions of documents in more than 100 languages including Russian and Ukrainian is published. The result can remain as clear text, and in HTML formats, PDF and TSV. Initially the system has been created in 1985-1995 in laboratory of the Hewlett Packard company, in 2005 the code has been open under the license Apache and further developed with the assistance of employees of the Google company. Source texts proyektarasprostranyatsya under the licenses Apache 2.0.

Main improvements in Tesseract 4.0: The new cursor of recognition which is based on use of system of machine learning on the basis of the recurrent neural network LSTM optimized for recognition entirely of lines and allowing to achieve essential increase in accuracy. The old cursor recognizing the text at the level of separate symbols continues to be delivered as an option. The alternative cursor of Cube is removed from code base; The utilities accompanying a new OCR cursor for a training of model of machine learning are added. The ready trained models are published for 123 languages; For a new cursor of recognition modules for optimization of productivity by means of OpenMP and SIMD instructions of AVX2, AVX or SSE4.1 are prepared; Transition to numbering of versions according to the Semantic Versionirovaniye specification meaning use of a notation of X.Y.Z Is carried out (instead of earlier used W.X.Y.Z) in which X changes at modification, breaking the return compatibility, Y changes at expansion of functionality and Z at correction of mistakes. The assembly system is updated. Assembly requires the compiler with support of C 11 now. Unit-tests are added. The assembly mode without old cursor of recognition is added. The reogranization of a tree of source texts is executed. The outdated code is purged;

Is improved processing of multipage TIFF images;

Is improved export to PDF. On materials: www.opennet.ru

URL:




Today

5 days ago

One of the most famous and highly paid Hollywood actors Eddie Murphy became a father for the tenth time. As informs Newsmir.info with reference to the western tabloids, at the actor the son was born....

5 days ago

Late at night on December 7 in Kryvyi Rih on residential district Zarechny-5 the driver of BMW on the Lithuanian numbers apparently did not manage to drive and crashed into a concrete fence of parking...

5 days ago

The secret novel was for the woman an occasion of revenge to the traitor which can be turned into reality now. On Channel One was outlined intense scandal on the shouting subject again. The matter i...

5 days ago

Today, on December 8, approximately at 20:00 on Lyustdorfskaya Road the girl driver of BMW on "eurometal plates" did not manage to drive and crashed into a fence of prison. As reports "Newsmir.info"...

5 days ago

Unpleasant incident occurred on December 6 in the city Raisin of the Kharkiv region. As reported in local police station, about five o'clock in the evening to the 80-year-old woman the friendly woman...

5 days ago

In Hamburg the congress of the German conservatives who elected Annegret Crump-Karrenbaueer Angela Merkel successor on a post of the chairman of CDU came to the end. On Saturday, December 8, in Hamb...

5 days ago

The American company Ford on social network "VKontakte" organized and conducted survey which purpose was identification of the most useful automobile options in winter time for the Russian roads. th...

5 days ago

For most of the people suffering from this or that form of diabetes need to constantly take a blood test from a finger is not the most pleasant procedure - for this reason many teams of developers act...