After three years since the last release, the Ocrad 0.28 (Optical Character Recognition) text recognition system, developed under the GNU project, has been released. Ocrad can be used both as a library for integrating OCR functionality into other applications and as a standalone utility that outputs text in UTF-8 or 8-bit encodings based on an input image.
Ocrad uses a feature extraction method for optical recognition. It includes a page layout analyzer that correctly separates columns and blocks of text in printed documents. Recognition is supported only for characters from the 'ascii', 'iso-8859-9', and 'iso-8859-15' encodings (Cyrillic support is not available).
It is noted that the new release includes a significant number of minor fixes and improvements. The most significant change is the support for PNG image formats, implemented using the libpng library, which has greatly simplified work with the program, as previously only PNM format images could be input.
Source: opennet.ru
