NAYOSO's profile - activity

Hello I want to create a building detection, but I'm still thinking about the algorithm and I'm wondering is anybody here have another idea than I have. My idea is to differentiate building by color, because of only detecting edges there is also possibility there will be another building behind the targeted building, I also want to detect the building from many angle, but surely there'll be minimum and maximum distance between the user and the building. So what do you guys think about this? is there any other algorithm for this?

Thanks

Thank you for your response! I think this one will work. I'll try it first then I'll accept your answer then thank you :)

@berak hmmm how about feature matching?actually I just want to be sure of the location of the corner of the paper

Hello I want to detect a sheet of paper and I already achieve it by detecting edges and find the largest square possible but the result isn't always good. I want to try another solution even I'm unsure this approach will be better or not. My new approach is to create a kind of marker in every corner of the paper (this will be printed manually on the paper) and detect the location of the marker after that draw a line between every marker then creating a perfect rectangle around the paper. So what's in my mind is to use template matching to detect the marker, and then detect the position of every marker, my question is is there any better method to achieve this approach (using marker)?

Thank You

OK I'll try it! and I'll report to you, thank you mrgloom

Hello I'm trying to find the location of a character (A,B,C,D,E, etc) in a paper from webcam and create a bounding box around it and crop it. How could it be done? I'm thinking of using classifier like for face detection or people detection but is there any character classifier from OpenCV? or is there any other method to do that? my goal is only to detect and crop the bounding box not recognizing the character

Thank You

thank you siegfried!

thank you Vladislav! it works perfectly!

Hello right now I'm trying to capture an grayscale image from the webcam and access it the value of every pixel of the image. At first I used this code

IplImage* processed_frame = (*custom_cb)(frame);  

      if(key==13)
      {
          IplImage *destination = cvCreateImage(cvSize(20,20),processed_frame->depth, processed_frame->nChannels);
          cvResize(processed_frame, destination);

          cvShowImage("frame resize", destination);

          mat=cvCreateMat(destination->height,destination->width,CV_32F );
          for(int i=0;i<mat.rows;i++)
            {
                for(int j=0;j<mat.cols;j++)
                {

                   printf( "(%.f) ",mat.at<float>(i,j) );
                }
              printf("\n");
            }
      }

I'm trying to convert the IplImage to mat and access every pixel of the mat but it always return the same value for every pixel then I'm trying to access the IplImage directly

IplImage* processed_frame = (*custom_cb)(frame);  

      if(key==13)
      {
          IplImage *destination = cvCreateImage(cvSize(20,20),processed_frame->depth, processed_frame->nChannels);
          cvResize(processed_frame, destination);
          for(int i=0;i<20;i++)
            {
                for(int j=0;j<20;j++)
                {

                   printf( "(%.f) ",CV_IMAGE_ELEM(destination,float,i,j) );
                }
              printf("\n");
            }
      }

it gives me various value for every pixel and every image I try to capture but I'm still not sure if I'm doing it right. What I want to ask is why the first code always returning same value and is the second code the right way to get the pixel value?

Thanks

Finally I found a way to this problem I uninstall my eclipse CDT 8.1 and manually install eclipse CDT 8.0.2 there is a bug in the CDT 8.1 -> http://code.google.com/p/android/issues/detail?id=33788 thanks all!

Hello andrey pavlenko thank you for your answer,sorry I didn't know how to comment in your answer but I've tried it and I'm still getting the same error,I'm using windows 7 64 bit Eclipse Juno ADT 20.0 SDK 11 and NDK r8 how about it? I can run the other samples except face detection,sample 3 and sample 4 that use C code,thanks

Hello guys I'm trying to learn about openCV in android I've already following the instruction given http://docs.opencv.org/doc/tutorials/introduction/androidbinarypackage/androidbinarypackageusingwith_NDK.html

but when I'm trying to compile I'm only getting

01:50:14 ** Auto Build of configuration Default for project org.opencv.samples.fd.FdActivity 
** "C:\Android\android-ndk-r8\ndk-build.cmd" 
Install: libdetection_based_tracker.so => libs/armeabi-v7a/libdetection_based_tracker.so

01:50:14 Build Finished (took 184ms)

in the console and I'm also get an error

Errors occurred during the build. Errors running builder 'CDT Builder' on project 
org.opencv.samples.fd.FdActivity. Internal error building project 
org.opencv.samples.fd.FdActivity configuration Default java.lang.NullPointerException Internal 
error building project org.opencv.samples.fd.FdActivity configuration Default 
java.lang.NullPointerException

anyone ever encountered this problem before? please help me to solve this problem

thank you