Date: 7 months 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 The outdated code is purged;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

just now

On June 26 in the Feodosiya literary and memorial museum of A.S. Green rewarding of winners and opening of an exhibition of works of participants of a creative Internet competition in the novel by the writer of "Jesse and Morgiana" will take place. The press service of the museum reports about it. "A competition was organized by the Feodosiya lit...

just now

At my order talented group of players. is appointed by the New head coach of the national team of Scotland Steve Clark. the Expert replaced on the trainer's bridge of Alex McLeish, reports "Today"...

just now

Consuming 350 grams of fish a week from which 200 grams are a fat fish, it is possible to extend life for years. Along with it doctors advise to reduce consumption of red meat. the Food and Chemical...

just now

Power engineering specialists of DTEK "Dneproblenergo" passed from threats to active actions, and on May 21 limited supply of electricity to objects of the Aulsky conduit in this connection interruptions in giving of drinking water to consumers of a right-bank part of Dnieper are expected. About this "Newsmir.info" learned from the message of the...

just now

The Honda company began to collect preorders for the new electric Honda-e hatchback. Now it is only about four European countries - Norway, Germany, France and Great Britain. While dealers only collec...

just now

Married couple from the Spanish city of Granada two years lived with 80 thousand live bees in a bedroom wall, transfers korrespondent.net. Spaniards heard an unclear rumble from a wall in the bedroo...

just now

Kiev will buy modern medical ventilators. The city will spend 12 million hryvnias for the medical equipment. will take place on July 25 3 auctions in the tender for different types of devices. In to...

just now

Marvelous history - police officers, running away from prosecution by the official car, threw out money in a window. But villains were detained and strictly punished. Directly, as in New Year's storie...