VeryPDF

Download and install

VeryPDF PaperTools SDK/COM is a toolkit for developers, you can download it from here, unpack it to the disk, open a command prompt window with Administrator Privilege in Windows system, then you can run following command line to register PaperToolsCom.exe into your system,

PaperToolsCom.exe /regserver

after you registered PaperTools SDK/COM successful, you can compile and run ASP, C#, C++, Javascript, PHP, VB, VB.NET, VBScript, etc. demo projects easily.

VeryPDF PaperTools SDK/COM options

VeryPDF PaperTools SDK/COM is easy to use, and it has these options:

Description: Batch process scanned image files from command line.
Features:
1. Black Lines Removal
2. Dynamic Thresholding
3. Deskew
4. Despeckle
5. Black Border Removal
6. Layout Analysis
7. OCR Scanned Image files to text files
Usage: PaperTools.dll [options] <in-file> [<out-file>]
  -bitcount <int>          : Set color depth when render PDF page to 
                             image data, it can be set 1, 8, 24, default 
                             is 8bit
  -rotate <int>            : Rotate image file
  -threshold <int>         : Lightness threshold that used to convert 
                             image to B&W, from 1 to 255, 0 is auto, 
                             default is -1
  -dither <int>            : Convert the color image to B&W using the 
                             desired method:
          -dither 0: Floyd-Steinberg
          -dither 1: Ordered-Dithering (4x4)
          -dither 2: Burkes
          -dither 3: Stucki
          -dither 4: Jarvis-Judice-Ninke
          -dither 5: Sierra
          -dither 6: Stevenson-Arce
          -dither 7: Bayer (4x4 ordered dithering)
  -width <int>             : Scale output to specific width (proportional 
                             unless height specified)
  -height <int>            : Scale output to specific height (proportional 
                             unless width specified)
  -flip                    : Flip the image vertically
  -mirror                  : Mirror the image horizontally
  -deskew                  : Enable image deskew options
  -skewrange <fp>          : Range in which to search for rotation, from 
                             -degrees to +degrees rotation. (default: 5.0)
  -deskew2                 : Enable image deskew by second arithmetic
  -despeckle               : Enable image despeckle options
  -despeckle2              : Enable image despeckle by second arithmetic
  -specklesize <int>       : Set speckle size for -despeckle2 option, 
                             default is 20 pixel
  -layout                  : Layout Analysis for page automatically
  -boxobjects              : Recognize objects from scanned image file 
                             automatically
  -removelongline <int>    : Remove black lines which length larger than this value
  -removeshortline <int>   : Remove black lines which length less than this value
  -trimmargin              : Trim solid color margins from scanned image file 
                             automatically
  -fuzz <fp>               : Colors within this distance of percentage are 
                             considered equal, from 1.00 to 100.00, default 
                             is 80.00
  -trimcolor <string>      : Trim border by special color,
    -trimcolor FF0000: Red color
    -trimcolor 00FF00: Green color
    -trimcolor 0000FF: Blue color
    -trimcolor HexNum: Other colors
  -removeborder            : Remove black borders from scanned image file 
                             automatically
  -ocr                     : OCR image file to text file automatically
  -lang <string>           : choose the language for OCR engine
  -boxpic                  : Output image file with boxes
  -skip                    : Skip existing output files, don't overwrite it
  -v                       : Print copyright and version info
  -h                       : Print usage information
  -help                    : Print usage information
  --help                   : Print usage information
  -?                       : Print usage information
  -$ <string>              : Input registration key
Example:
   PaperTools.dll -removeshortline 5 X:\test_despeckle.tif D:\out.png
   PaperTools.dll -removeshortline 3 -removelongline 0 X:\test_despeckle.tif 
                  D:\out.png
   PaperTools.dll -removelongline 100 X:\test_black_border1.jpg D:\out.png
   PaperTools.dll -removelongline 200 X:\test_line.png D:\out.png
   PaperTools.dll -removelongline 0 X:\test_line.png D:\out.png
   PaperTools.dll -removelongline 100 X:\test_table_ocr.tif D:\out.png
   PaperTools.dll -removelongline 1000 X:\test_black_border1.jpg D:\out.png
   PaperTools.dll -removelongline 0 X:\test_black_border1.jpg D:\out.png
   PaperTools.dll -removelongline 0 X:\test_skew.tif D:\out.png
   PaperTools.dll -removelongline 0 X:\test_line.png D:\out.png
   PaperTools.dll -removelongline 0 X:\test_table_ocr.tif D:\out.png
   PaperTools.dll -removelongline 30 D:\out014.png D:\out.png
   PaperTools.dll -removelongline 0 D:\out009.png D:\out.png
   PaperTools.dll -removelongline 0 -boxobjects X:\test_negative.png D:\out.png
   PaperTools.dll -deskew -skewrange 45 X:\test_negative.png D:\out.png
   PaperTools.dll -deskew2 X:\test_negative.png D:\out.png
   PaperTools.dll -despeckle X:\test_despeckle.tif D:\out.png
   PaperTools.dll -despeckle2 -specklesize 20 X:\test_despeckle.tif D:\out.png
   PaperTools.dll -removeborder D:\out009.png D:\out.png
   PaperTools.dll -removeborder -fuzz 50 X:\test_despeckle.tif D:\out.png
   PaperTools.dll -removeborder -fuzz 80 X:\test_black_border1.jpg D:\out.png
   PaperTools.dll -trimmargin -fuzz 80 X:\test_black_border1.jpg D:\out.png
   PaperTools.dll -trimmargin X:\test_black_border2.png D:\out.png
   PaperTools.dll -trimmargin -trimcolor FFFFFF -fuzz 100 X:\test_table_ocr.tif 
                  D:\out.png
   PaperTools.dll -ocr -boxpic X:\test_table_ocr.tif D:\out.png
   PaperTools.dll -bitcount 1 X:\test_color.tif D:\out.png
   PaperTools.dll -layout D:\out009.png D:\out.png
   PaperTools.dll -$ XXXXXXXXXXXXXXXXX

VeryPDF PaperTools SDK/COM examples

VeryPDF PaperTools SDK/COM package is contain ASP, C#, C++, Javascript, PHP, VB, VB.NET, VBScript, etc. demo projects, you can compile and run them easily.

Sample: C++

void main()
{
    ::CoInitialize(NULL);
    _PaperToolsCom VeryPDFCom;
    try
    {
        VeryPDFCom.CreateDispatch("VeryPDF.PaperToolsCom");
    }
    catch(COleDispatchException* pEx)
    {
        printf("Something is wrong...\n");
        return;
    }

    CString strReturn = "";
    int nFileIndex = 0;
    VeryPDFCom.EnableDebugLog(true);

    string strFolder = GetParentFolder();

    string strInFile = strFolder + "\\sample\\test_table_ocr.tif";
    string strOutFile = strFolder + "\\sample\\output\\_output_" 
           + intToString(nFileIndex) + ".png";
    string strCmd = "-$ XXXXXXXXXXXXXXXXXX -removelongline 0 
           -boxobjects \"" + strInFile + "\" \"" + strOutFile + "\"";
    printf("%s\n", strCmd.c_str());
    strReturn = strReturn + VeryPDFCom.PaperTools(strCmd.c_str());
    printf("Message: %s\n", strReturn);
}

string appPath = Path.GetDirectoryName(Application.ExecutablePath);
System.Type VeryPDFType = System.Type.GetTypeFromProgID("VeryPDF.PaperToolsCom");
VeryPDF.PaperToolsCom VeryPDFCom = (VeryPDF.PaperToolsCom)
        System.Activator.CreateInstance(VeryPDFType);

string appFolder = Path.GetDirectoryName(Application.ExecutablePath);
string strFolder = Directory.GetParent(appFolder).FullName;

string strReturn = "";
int nFileIndex = 0;
VeryPDFCom.EnableDebugLog(true);

string strInFile = strFolder + "\\sample\\test_table_ocr.tif";
string strOutFile = strFolder + "\\sample\\output\\_output_" + 
       nFileIndex.ToString() + ".png";
string strCmd = "-$ XXXXXXXXXXXXXXXXXX -removelongline 0 
       -boxobjects \"" + strInFile + "\" \"" + strOutFile + "\"";
strReturn = strReturn + VeryPDFCom.PaperTools(strCmd);
MessageBox.Show(strReturn);

Dim strFolderDir As String = Application.StartupPath()

Dim VeryPDFCom As Object = CreateObject("VeryPDF.PaperToolsCom")
Dim filesys As Object = CreateObject("Scripting.FileSystemObject")
Dim strFolder As String = filesys.GetParentFolderName(strFolderDir)

Dim strReturn As String = ""
Dim nFileIndex As Integer = 0
VeryPDFCom.EnableDebugLog(1)

Dim strInFile As String = strFolder & "\sample\test_table_ocr.tif"
Dim strOutFile As String = strFolder & "\sample\output\_output_"
    & CStr(nFileIndex) & ".png"
Dim strCmd As String = "-$ XXXXXXXXXXXXXXXXXX -removelongline 0 
    -boxobjects """ & strInFile & """ """ & strOutFile & """"
strReturn = strReturn & VeryPDFCom.PaperTools(strCmd)
MsgBox(strReturn)

set VeryPDFCom = CreateObject("VeryPDF.PaperToolsCom")
Set filesys = CreateObject("Scripting.FileSystemObject")
strFolder = filesys.GetParentFolderName(WScript.ScriptFullName)
strFolder = filesys.GetParentFolderName(strFolder)

strReturn = ""
nFileIndex = 0
VeryPDFCom.EnableDebugLog(1)

strInFile = strFolder & "\sample\test_table_ocr.tif"
strOutFile = strFolder & "\sample\output\_output_" 
         & CStr(nFileIndex) & ".png"
strCmd = "-$ XXXXXXXXXXXXXXXXXX -removelongline 0 -boxobjects """ 
         & strInFile & """ """ & strOutFile & """"
strReturn = strReturn & VeryPDFCom.PaperTools(strCmd)

<?php

$strFolder = realpath(dirname(dirname(__FILE__)));

$nFileIndex = 0;
$VeryPDFComObject = new COM("VeryPDF.PaperToolsCom");

$strInFile = $strFolder . "\\sample\\test_table_ocr.tif";
$strOutFile = $strFolder . "\\sample\\output\\_output_" . $nFileIndex . ".png";
$strCmd = "-$ XXXXXXXXXXXXXXXXXX -removelongline 0 
        -boxobjects \"" . $strInFile . "\" \"" . $strOutFile . "\"";
printf("%s\n", $strCmd);
$strReturn = $strReturn . $VeryPDFComObject->PaperTools($strCmd);
printf("Message: %s\n", $strReturn);

?>

Screenshots