rockinfresh's profile - activity

@StevenPuttemans, Noted with thanks. Will sudden change in the version affect my previous programs? I just have to update all my include, library directory, etc, only right?

@StevenPuttemans, sorry for the late reply. That is weird, my problem was solved after running in release mode. My system is Windows 8, I am using OpenCV 2.3 and MS Visual Studio C++.

Do you have any idea what could be the reason? So that I can learn and improve myself to help others next time.

Try HoughCircles. Should work(:

Hi,

I am trying to do segmentation of book spines stacked both horizontal and vertically. I have came across a problem when the picture is too big. Only part of the image can be seen in the whole window, the next image shows the source where the hough line is applied to.

this is the original image it is suppose to process:

As you can see in the image above, I cannot view the whole image. Hence, I tried to minimise the window just for this picture using=>

cv::resize(image, image, cv::Size2i(image.cols/6, image.rows/6) ); // resize to 1/6 of the image

which lead to another problem, when the picture is small, it become too small that the straight lines cannot even be detected.

Hence, I tried => cv::resize(image, image, cv::Size2i(750, 400) );

this lead to another problem. While the image above is above to display the whole window, for smaller pictures, my houghline detection becomes more unstable. Please refer to the 2 images below

before I resize

Hough line detection while not perfect, just at least close?

but after i resize, the hough detection becomes worse!!

Do anybody have an idea on how to solve this sizing problem? And also how to improve my Hough Line detection which is pretty unstable now to separate the books? I wish to draw a line in between the stack of books.

Hope to hear from you guys soon. Thanks!!!

Have you tried it in release mode? I didnt use python, but I had the kind of the same problem with VS, and that was what I did to rectify the issue.

@albertofernandez, many thanks. That was the solution. It was also the solution to why I couldn't use imread but have to use cvLoadImage() in the first place. Is there any place where I can learn about the difference between both debug and release mode? Thanks!!!

This are what I used for my haar training previously...

http://docs.opencv.org/doc/user_guide/ug_traincascade.html, http://www.technolabsz.com/2011/08/how-to-do-opencv-haar-training.html and other one which is not a website but my own documentation. Do let me know if u want that, I can try copy paste the whole thing down.

Actually, U can try googling. I think I recall seeing more links before.

Hi all,

I been facing this problem for a long time and still have yet to solve it. As you can see in the image link= http://i.stack.imgur.com/pUZ35.png, the windows name is something like "-ka" BUT my program clearly named the window as "My Image".

I am now already doing more adavance stuff like splitting of image, etc, but my project supervisor asking me about this, yet I do not know the reason behind it. Can anyone help? Thanks.

Hi, I am relatively a greenhorn in the computer vision field too. But I have read about this and played around abit. I believe u can find your answers in this link

http://opencv.willowgarage.com/wiki/Kinect

Hope this helps. Cheers (:

Actually, thanks! It was the imgproc.hpp lib. I don't really know what function belongs to what library! Thanks (:

hi everyone,

I keep having the 2 errors:

1>c:\users\aaron\documents\visual studio 2010\projects\sharpen2d\sharpen2d\sharpen2d\main.cpp(45): error C2039: 'filter2D' : is not a member of 'cv' 1>c:\users\aaron\documents\visual studio 2010\projects\sharpen2d\sharpen2d\sharpen2d\main.cpp(45): error C3861: 'filter2D': identifier not found

Do anybody know why?

My program is as follows:

#include <opencv2\core\core.hpp>
#include <opencv2\highgui\highgui.hpp>
#include <opencv2\features2d\features2d.hpp>
#include <opencv2\calib3d\calib3d.hpp>


void sharpen2D(const cv::Mat &img, cv::Mat &result)
{
    //construct the kernel such that all entries are initialised to 0
    cv::Mat kernel(3,3,CV_32F,cv::Scalar(0));
    //assign the kernels value
    kernel.at<float>(1,1) = 5.0;
    kernel.at<float>(0,1) = -1.0;
    kernel.at<float>(1,0) = -1.0;
    kernel.at<float>(2,1) = -1.0;
    kernel.at<float>(1,2) = -1.0;

    //now filter the image
    cv::filter2D (img, result, img.depth(), kernel);
}


int main(){

    cv::Mat img(cvLoadImage("rendered_lena.png"));

    cv::Mat imgClone= img.clone();

    sharpen2D(img,imgClone); //change the number to reflect the color reduction property

    cv::namedWindow("Results", CV_WINDOW_AUTOSIZE);

    cv::imshow("Results", imgClone);

    cv::waitKey(0);

}

I initially thought it was the include library problem, but apparently it's not. Any idea anybody?