* NEWS: Here. --- scribo/ChangeLog | 6 +++++ scribo/NEWS | 67 ++++++++++++++++++++++++++++++++++++------------------ 2 files changed, 51 insertions(+), 22 deletions(-) diff --git a/scribo/ChangeLog b/scribo/ChangeLog index 221ddb9..033dce2 100644 --- a/scribo/ChangeLog +++ b/scribo/ChangeLog @@ -1,3 +1,9 @@ +2014-07-02 Roland Levillain <roland(a)lrde.epita.fr> + + Update Scribo's NEWS file. + + * NEWS: Here. + 2012-06-04 Guillaume Lazzara <z(a)lrde.epita.fr> * demo/xml2doc/Makefile.am: Fix installation of ooconvert. diff --git a/scribo/NEWS b/scribo/NEWS index 8d9d9ac..e8418e2 100644 --- a/scribo/NEWS +++ b/scribo/NEWS @@ -1,30 +1,52 @@ -* Scribo 0.1 +* Scribo 2.0a - * Initial release of Scribo, an Olena module for page - segmentation and text extraction in images. It is composed - of a set of functions and data structures and allows to - build dedicated page segmentation toolchains. + * The Scribo distribution now contains a Doxygen + documentation. - * New command line tool providing access document analysis - toolchains. It includes Page segmentation and text - extraction in document image, and text detection in - pictures. + * New logger class. - * New tool to rebuild a document from an XML file to PDF, - HTML, SVG and Open Document. This tool preserves the layout - and extract photos and non text objects from the input - document image. + * Improve text recognition: recognition speed and storage of + the confidence. - * New multi-scale binarization algorithm based on a Sauvola's - algorithm. It has been designed for document - binarization. + * New binarization algorithms: Wolf's, Otsu's, Niblack's and + Kim's. - * New graphical tool to compute and display page segmentation - results. + * Speedup Sauvola's binarization algorithm. - * Include support for PAGE XML outputs. Page segmentation - results are stored in this format which includes text and - objects information. + * Improve OCR result quality and processing time. + + * Add support for Tesseract 3.02. + + * Add the layout analysis algorithm XY-Cut. + + +* Scribo 2.0 September 16, 2011 + + * Initial release of Scribo, an Olena module for page + segmentation and text extraction in images. It is composed + of a set of functions and data structures and allows to + build dedicated page segmentation toolchains. + + * New command line tool providing access document analysis + toolchains. It includes Page segmentation and text + extraction in document image, and text detection in + pictures. + + * New tool to rebuild a document from an XML file to PDF, + HTML, SVG and Open Document. This tool preserves the layout + and extract photos and non text objects from the input + document image. + + * New multi-scale binarization algorithm based on a Sauvola's + algorithm. It has been designed for document + binarization. + + * New graphical tool to compute and display page segmentation + results. + + * Include support for PAGE XML outputs. Page segmentation + results are stored in this format which includes text and + objects information. @@ -36,7 +58,8 @@ End: ---- -Copyright (C) 2010 EPITA Research and Development Laboratory (LRDE) +Copyright (C) 2010, 2011, 2014 EPITA Research and Development +Laboratory (LRDE). This file is part of Olena. -- 1.7.10.4