I'm building tesseract 3.01 and magick++ into a program because the command
line versions were too slow. getting everything compiled correctly took
forever but finally I get no errors in my compiler, but as soon as I go to
run my console app I get
PS C:\Users\sirus\Documents\Visual Studio
2013\Projects\ConsoleApplication4\Release> .\ConsoleApplication4.exe
first command
actual_tessdata_num_entries_ <= TESSDATA_NUM_ENTRIES:Error:Assert failed:in
file ..\ccutil\tessdatamanager.cpp, line 48
PS C:\Users\sirus\Documents\Visual Studio
2013\Projects\ConsoleApplication4\Release> l
searching for this online shows that this is what happens when you have to
incorrect language data, but I have tesseract 3.01 and the tesseract 3.01
language data downloaded directly from their google code site.
I'm using visual studio 2013 on windows 8.1 building 32 bit /MD
here is a sample of my source
#include <stdio.h>#include <string>#include <iostream> #include
<iomanip>#include <locale>#include <sstream>#include <string> #include
<Magick++.h>#include "baseapi.h"#include "allheaders.h"using namespace
Magick;using namespace std;using namespace tesseract;#define MaxRGB
((Magick::Quantum)65545)
tesseract::TessBaseAPI tess;
string cmd = "";
string cmd2 = "";
void img_split(){
string tesseract = "\"C:\\Program Files
(x86)\\Tesseract-OCR\\tesseract.exe\" text/";
int rect_y = 141;
string del = "del /s /q text\\*";
system(del.c_str());
for (int x = 1; x < 40; x++){
rect_y += 19;
Image image;
image.read("source.jpg");
Magick::Image* mImage;
Image sub_image(image);
mImage = &sub_image;
//mImage->write("test.jpg");
sub_image.chop(Geometry(1481, rect_y));
sub_image.crop(Geometry(220, 17));
sub_image.quantizeColorSpace(GRAYColorspace);
sub_image.quantizeColors(2);
sub_image.quantizeDither(false);
sub_image.quantize();
sub_image.scale(Geometry(2200,170));
sub_image.antiAlias();
sub_image.compressType(Magick::NoCompression);
//const unsigned char* imagedata = (unsigned char*)mImage;
//tess.SetImage(imagedata, 2200, 170, 1, 17300);
//tess.Recognize(0);
//const char* out = tess.GetUTF8Text();
//cout << "\n\nno idea if this will work: " << out << endl;
sub_image.write("text/" + static_cast<ostringstream*>(&(ostringstream()
<< x))->str() + ".gif");
//cmd2 = tesseract + static_cast<ostringstream*>(&(ostringstream() <<
x))->str() + ".png text/" + static_cast<ostringstream*>(&(ostringstream() <<
x))->str();
//tesseract_ocr(x);
}
}
int main(int argc, char **argv){
cout << "first command\n";
//tess.Init(argv[0], "eng", tesseract::OEM_DEFAULT);
tess.Init(*argv, "eng");
tess.SetPageSegMode(tesseract::PSM_AUTO);
cout << "\ntest" << endl;
InitializeMagick(*argv);
//img_split();
return 0;}
bonus points if you can tell me how to correctly pass the image in
sub_image to tesseract's setimage function (because i'm pretty sure what I
have wont be right either)
--
--
You received this message because you are subscribed to the Google
Groups "tesseract-ocr" group.
To post to this group, send email to [email protected]
To unsubscribe from this group, send email to
[email protected]
For more options, visit this group at
http://groups.google.com/group/tesseract-ocr?hl=en
---
You received this message because you are subscribed to the Google Groups
"tesseract-ocr" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
For more options, visit https://groups.google.com/groups/opt_out.
