scholar's profile - activity

I want to extract the textual part from a scenic image leaving behind the background. For this, I found different techniques like SWT, MSER etc. Can Anyone tell me which techniques work better? Moreover, from where can i get some coding help regarding this? i m using vs2015 c++

I am able to detect text i.e getting bounding boxes around the text. but i want to segment detected text from background. How can we do that???

is there anyone who can actually help me in running this code... and explain the solution in detail...

sorry but m unable to get u..

i have already downloaded them . wat do u mean by link them to ur sample?? Are u talking about adding extra modules to opencv ??? I am new to dis all.. kindly co-operate

okii got ur point.. thanx alot... i was passing the path of the image only.. but the issue was that in the path a space was there like 'research lab' so it was taking argv[1] upto research only..

dey r there in samples of opencv_contrib .. Any other solution?? wt shd i try ??

yea.. i have tried... but it comes up with same error... Where should these classifiers actually be???

yes i tried dis also but got the same error again..

I am trying to run textdetection.cpp present here OpenCV Error: Bad argument (Default classifier file not found!) in cv::text::ERClassifierNM1::ERClassifierNM1, file C:\opencv_ex\opencv_contrib-master\modules\text\src\erfilter.cpp,

Is there anyone having some idea about this error??? i have already added extra modules in to my opencv

that exception was generated by createfilter .. I am getting this error : OpenCV Error: Bad argument (Default classifier file not found!) in cv::text::ERClassifierNM1::ERClassifierNM1, file C:\opencv_ex\opencv_contrib-master\modules\text\src\erfilter.cpp,

"C:\Users\research lab\Documents\Visual Studio 2015\Projects\XtraModulesDemo\Debug\XtraModulesDemo.exe " this is the value of argv[1]..

output is :

C:\Users\research lab\Documents\Visual Studio 2015\Projects\XtraModulesDemo\Debug\XtraModulesDemo.exe

IMG_W=0 IMG_H=0 OpenCV Error: Assertion failed (scn == 3 || scn == 4) in cv::ipp_cvtColor, file C:\opencv3.1\sources\modules\imgproc\src\color.cpp, line 7456

do u mean i have to copy the path of the image to be read in the field 'command arguments' in both debug and release??? i have tried this, its not reading the image....

int main(int argc, char* argv[])
   {
    cout << endl << argv[0] << endl; 
    Mat image;
if (argc>1)
    image = imread(argv[1]);
else
{
    cout << "    Usage: " << argv[0] << " <input_image> [<gt_word1> ... <gt_wordN>]" << endl;
    return(0);
}

cout << "IMG_W=" << image.cols << endl;
cout << "IMG_H=" << image.rows<<endl;

}

if i have downloaded the code from somewhere lets say its abc.cpp and its having main as :

int main(int argc, char* argv[])
{
    Mat image;
    if (argc>1)
        image = imread(argv[1]);
    else
    {
        cout << "    Usage: " << argv[0] << " <input_image> [<gt_word1> ... <gt_wordN>]" << endl;
        return(0);
    }}


how should i run this code ?? normally from the vs platform??? how to pass the image to be read????

how can we give values to argc or argv??? i have gone thru all the other similar questions here but dint found any solution to my problem??

i am trying o run the file textdetection.cpp file present here .. i tried it with different images but every time an exception is thrown of some memory location like Microsoft C++ exception: cv::Exception at memory location 0x00CEC6BC. why is dis happening ?? any solutions ?? I m stuck wid this text detection from several days... :(

yea i did this also.. but m confused with x86 and x64.. as my system is x64 and i am buliding x64 applications always.. now to give path there must be a folder x64 but its not dere .. only x86 is dere.. i have mentioned all details here http://answers.opencv.org/question/10...

I need to install opencv extra modules.. so I followed the steps given :https://github.com/opencv/opencv_contrib

I did: C:\Users\research lab>cd C:\opencv3.1\build

C:\opencv3.1\build> cmake -DOPENCV_EXTRA_MODULES_PATH=C:\opencv_ex\opencv_contrib-master\modules C:\opencv3.1\sources

I got:-- Configuring done -- Generating done -- Build files have been written to: C:/opencv3.1/build

but when i run : make-j5 i got an error : no targets specified and no makefile found..

I checked my build folder, no MAKEFILE was there . WHY is it happening? does makefile is not being generated or some other issue is there?????

thanks alot for all ur guidance. Now scene is:

-->I have built the .sln file and INSTALL project .. after that when i was updating my property sheet i noticed that no X64 folder is there in the INSTALL folder.. where was i wrong???

--> Secondly, i tried through 'make' also (i downloaed its .exe and added its path in the environment variables and hence it was recognized this time) but now error comes : no targets specified and no makefile found...

--> my cmake gui is also not working (unknown error occurs) .. i tried that too..

WHAT should I do.. with which option i should go.. PLEASE take me out of all this..

i successfully run the first two commands: $ cd <opencv_build_directory> $ cmake -DOPENCV_EXTRA_MODULES_PATH=<opencv_contrib>/modules opencv_source_directory>

i got configuration done, generating done,build files have been written to c:\opencv3.1\build

after that when i wrote make -j5 , I got :make is not recognized as an internal or extrenal command.

opencv3.1 , vs2015, windows10 cmake 3.6.1

its ok.. i have tried that too. now i m stuck with 'make -j5' they say unknown command make... so whts next??

Yea i have already done that.. m talking abt the same code textdetectiob.cpp from samples.. i m getting the same errors about erstat,cv::text , opencv2/text.hpp

can u please tell me how shoul i add 'opencv2/text.hpp' header file ???

:( :( :( :(

from where to get this header file??

How to try them, only samples are there.. Sorry but m not getting u..Actually i want to do text extraction from a scene image.. can u guide me..?

Iwant to implement a simple thresholding algorithm by comparing the pixel values of an image with some threshold and then assign either 0 or 1 to the pixels of output value correspondingly. a part of the code is:

cv::Mat gray , binary; // gray is input and binary is output image.

binary = Mat::zeros(gray.size(), gray.type());

for (int i=0;i<=row;i++)
{
    for (int j = 0; j <= col;j++)
    {

        if ((gray.at<uchar>(i, j) > NiblackThreshold)
        {
            binary.at<uchar>(i, j) = 1;
        }
        else
        {
            binary.at<uchar>(i, j) = 0;
        }

    }

Exceptions is at: template<typename _tp=""> inline _Tp& Mat::at(int i0, int i1) { CV_DbgAssert( dims <= 2 && data && (unsigned)i0 < (unsigned)size.p[0] && (unsigned)(i1DataType<_Tp>::channels) < (unsigned)(size.p[1]channels()) && CV_ELEM_SIZE1(DataType<_Tp>::depth) == elemSize1()); return ((_Tp)(data + step.p[0]i0))[i1]; }

where is the problem?????

I have downloaded the text detection code from github (https://gist.github.com/agasiev/10021533). but it is producing many similar errors like: identifier erstat is undefined identifier computerNMchannels is undefined identifier erfilter is undefined... and many more..

What it is so???? Can any one help me out??