rahulvg's profile - activity

Please check if you have included the path of opencv hpp files in "Project Properties ->Congig Properties --> C/C++ --> Additional Include directories"

Hi, I have been trying to train cascade classifier with 6k positive and 2k negative images.It has been seven days still the training is not finished,though I can see the progress on cmd but I want to know avg time required!

I was working on the skin detection in OpenCV.I am using YCrCb color range for detection.It was working fine for most of the image but in one case it was not working. Image Not Working

So I tried to do some adjustment in the images because you can see that skin color range is not even visible,so I edited the pic in Windows Photos Application in Window 8.In that software I changed "color->Temperature" setting and set the value to 80 or something. The output image was this.

Now the Skin detection works perfectly fine.Can anyone explain me the temperature parameter used in Photos app and what it exactly does?

Hi I am working on face and neck detection.For face its very easy to detect but I want to detect neck and shoulder joint,so I am thinking of training ASM for the neck point detection.Can someone help me with the initial procedure,like how to start training and etc.

0 down vote favorite

Hi I am trying to detect the neck point in an image.I am using asm to detect the feature points of the face but i dont know how to detect the neck.Is there any algo or measurement to detect it?

i think you "if" check should be
if cy >= 75: counter=counter+1;

Why dont you use the haar cascade to detect face which will return you a rectangle per person instead of detecting contours....

I am trying to detect hand using opencv and c++.

I am able to find the contour of the hand(Positive image)with person hand present in the image.Basically I am finding largest contour and consider it as hand contour.Lets say in the given image the hand is not present then i will take any contour and consider it as the hand.

So I started thinking can I use the haar cascade to determine the rectangle of the hand and focus on that area,but I tried searching online for the xml but I think it is not available like face detection.

So given a image how can I determine from the set of contour which one is of hand?

I may be wrong but I think if you are using using image transferred from email or communicator and use the same image as input then this problem occurs.

sorry I am new in coding so not aware of this facts.I will try to improve. can u please try this image http://i.imgur.com/8rhAMbP.jpg

Sorry for wrong formatting..but I am doing nothing new..just read the image and show it..u will see that it is rotated.

//read the image

Mat input = cv::imread("image.jpg", CV_LOAD_IMAGE_COLOR);

//display

imshow("Input Image",input); waitkey(-1);

You will notice the image is inverted

Program :

   Mat input = cv::imread("image.jpg", CV_LOAD_IMAGE_COLOR);

   //If image is larger than 1000*1000 pixels resize the image.


   Size size(700, 800);
Mat output;

if (input.rows > 1000 && input.cols > 1000)
{
    resize(input, output, size);
}
else
{
    output = input;
}

imshow("input image",output);

if u look at output image u will notice that it is rotated. Even if u skip the part of resizing and directly showing the image it will give u rotated image

orignal image : http://i.imgur.com/A4345Wy.jpg

I was trying to load the image..but after imread it is rotating the image by 90 degrees.

thinning algorithm is not working properly input :http://i.imgur.com/ui6wTiJ.jpg Output :http://i.imgur.com/BijtKNF.png

Yeah I used HoughLinesP.Maybe something wrong with the parameters?? cv::HoughLinesP(copiedImg, lines, 1, CV_PI / 180, 70, 30, 10);

Please see picture http://i.imgur.com/ptGGTrB.png Hough Line returns me 28 lines and really its very hard to judge the longest line i.e it can be vertical or horizontal.

If I have two images

Image 1: Aligned properly http://i.imgur.com/ui6wTiJ.jpg Aligned properly

Image 2: Not aligned properly http://i.imgur.com/Z05ZfwR.jpg Not aligned properly

My algorithm compares two images but it needs both the images aligned properly. I was thinking of putting some unique marker at top-left corner but is there another way to align the images properly?