The prototype of SAC
is Here(http://www.icst.pku.edu.cn/cpdp/SAC/SAC.rar).
1.
Start: click the following
icon of TestSAC.exe, and start SAC system
2.
Open
a PDF document: Click on the open-file button in Figure 1, and select a PDF or
CEBX document. Click on open.
Figure 1: Click on
the open-file button
Figure 2: Select a
document and click on the open button.
3.
Paragraph
analysis: Click on “页面分析(使用树)” in the menu, and
select “文本段识别”(Figure 3). The result of
paragraph analysis will be like Figure 4.
Figure 3: how to
use paragraph analysis
Figure 4: the
result of paragraph analysis
4.
Formula
locating: Click on “页面分析(使用树)” in the menu, and
select “公式定位”(Figure 5). The result of
paragraph analysis will be like Figure 6.
Figure 5: how to
use formula locating
Figure 6: the
result of formula locating
5.
A
tool called PDF2HTML, which is based on SAC system and used to convert PDF
document to HTML document is also available. To use it, open the P2HDemo.exe,
click on the path button and select a PDF document (Figure 7). Wait until the
conversion is finished and the result HTML document will be opened using your
default web-browser. The HTML document is located in the same path with the PDF
document.
Figure 7: the
PDF2HTML tool.