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