|
1 |
| -* Scribo 0.1 |
| 1 | +* Scribo 2.0a |
2 | 2 |
|
3 |
| - * Initial release of Scribo, an Olena module for page |
4 |
| - segmentation and text extraction in images. It is composed |
5 |
| - of a set of functions and data structures and allows to |
6 |
| - build dedicated page segmentation toolchains. |
| 3 | + * The Scribo distribution now contains a Doxygen |
| 4 | + documentation. |
7 | 5 |
|
8 |
| - * New command line tool providing access document analysis |
9 |
| - toolchains. It includes Page segmentation and text |
10 |
| - extraction in document image, and text detection in |
11 |
| - pictures. |
| 6 | + * New logger class. |
12 | 7 |
|
13 |
| - * New tool to rebuild a document from an XML file to PDF, |
14 |
| - HTML, SVG and Open Document. This tool preserves the layout |
15 |
| - and extract photos and non text objects from the input |
16 |
| - document image. |
| 8 | + * Improve text recognition: recognition speed and storage of |
| 9 | + the confidence. |
17 | 10 |
|
18 |
| - * New multi-scale binarization algorithm based on a Sauvola's |
19 |
| - algorithm. It has been designed for document |
20 |
| - binarization. |
| 11 | + * New binarization algorithms: Wolf's, Otsu's, Niblack's and |
| 12 | + Kim's. |
21 | 13 |
|
22 |
| - * New graphical tool to compute and display page segmentation |
23 |
| - results. |
| 14 | + * Speedup Sauvola's binarization algorithm. |
24 | 15 |
|
25 |
| - * Include support for PAGE XML outputs. Page segmentation |
26 |
| - results are stored in this format which includes text and |
27 |
| - objects information. |
| 16 | + * Improve OCR result quality and processing time. |
| 17 | + |
| 18 | + * Add support for Tesseract 3.02. |
| 19 | + |
| 20 | + * Add the layout analysis algorithm XY-Cut. |
| 21 | + |
| 22 | + |
| 23 | +* Scribo 2.0 September 16, 2011 |
| 24 | + |
| 25 | + * Initial release of Scribo, an Olena module for page |
| 26 | + segmentation and text extraction in images. It is composed |
| 27 | + of a set of functions and data structures and allows to |
| 28 | + build dedicated page segmentation toolchains. |
| 29 | + |
| 30 | + * New command line tool providing access document analysis |
| 31 | + toolchains. It includes Page segmentation and text |
| 32 | + extraction in document image, and text detection in |
| 33 | + pictures. |
| 34 | + |
| 35 | + * New tool to rebuild a document from an XML file to PDF, |
| 36 | + HTML, SVG and Open Document. This tool preserves the layout |
| 37 | + and extract photos and non text objects from the input |
| 38 | + document image. |
| 39 | + |
| 40 | + * New multi-scale binarization algorithm based on a Sauvola's |
| 41 | + algorithm. It has been designed for document |
| 42 | + binarization. |
| 43 | + |
| 44 | + * New graphical tool to compute and display page segmentation |
| 45 | + results. |
| 46 | + |
| 47 | + * Include support for PAGE XML outputs. Page segmentation |
| 48 | + results are stored in this format which includes text and |
| 49 | + objects information. |
28 | 50 |
|
29 | 51 |
|
30 | 52 |
|
|
36 | 58 |
|
37 | 59 | ----
|
38 | 60 |
|
39 |
| -Copyright (C) 2010 EPITA Research and Development Laboratory (LRDE) |
| 61 | +Copyright (C) 2010, 2011, 2014 EPITA Research and Development |
| 62 | +Laboratory (LRDE). |
40 | 63 |
|
41 | 64 | This file is part of Olena.
|
42 | 65 |
|
|
0 commit comments