annarose's profile - activity

SURF features..

If we move away from camera it shows some false prediction. But if we close to camera it give correct predictions. So it Is the problem of my training sets or it is not possible to grab some sort of distance using svm?

ok..but what labels are given for negative images? because +ve images are labeled as 1,2,3...

Is it possible to grab some sort of distance to the decision plane using opencv-svm?

In my system, I want to show known faces are "known" otherwise it is "Unknown". I don't know whether it is possible by using one multi-class svm. That's why am using multiple svm.

Now I am using multiple SVM with SURF features for face recognition. For example I have 3 types of images and each type I called as class1,calss2 and class3. So I build SVM1 as combination of class1 and class2 where class1 images are labeled as +1 and class2 images labeled as -1 like that SVM2 is the combination of class2 and class3 where class2 images are labeled as +1 and class3 images labeled as -1 and SVM3 is the combination of class3 and class1 where class3 images are labeled as +1 and class1 images labeled as -1. So at the time of prediction if the given image is in any of the class then that particular SVM return +1 and I concluded that image s "known", if all SVM return -1 then it is "Unknown". But now my problem is, if the given image is not in the training set then also SVM return +1 and identified as known one.Actually it get drops my system accuracy level. Is there any problem in my approach? why I got false results? Please help me.

Thank you..It works fine.

I post my code..This is that link http://answers.opencv.org/question/44...

I want to display my image on right side of the screen within the rectangle. So for that I wrote the following code.

Rect dstRC(10,20,100,100);//The region I want to display image
Mat dstROI = frame(dstRC);
img1.copyTo(dstROI);//My image is img1.Copy to desired location
rectangle(frame1, dstRC, CV_RGB(255,0,0), 3, CV_AA);

But it shows only an empty rectangle.Why?

I got some idea from the link that you provide. I tried lot but it doesn't give the desired output.

I want to display each detected image on the right side of the display screen.For example like this. .

How to do it in opencv? We can't use another imshow.Then how make it possible?

Thank you..I solved my error. As you said, my problem is in trainData Mat and trainLabels Mat.

I gave +1 for positive images and -1 for negative images. Few examples are shown below. /home/arya/Images/OutputImage/im1.pgm;1 /home/arya/Images/OutputImage/im2.pgm;1 /home/arya/Images/OutputImage/im3.pgm;1 /home/arya/Images/OutputImage/im4.pgm;1 /home/arya/Images/OutputImage/im5.pgm;1 /home/arya/Images/OutputImage/im46.pgm;-1 /home/arya/Images/OutputImage/im47.pgm;-1 /home/arya/Images/OutputImage/im48.pgm;-1 /home/arya/Images/OutputImage/im49.pgm;-1 /home/arya/Images/OutputImage/im50.pgm;-1 /home/arya/Images/OutputImage/im51.pgm;-1 /home/arya/Images/OutputImage/im52.pgm;-1

Now I train SVM with SURF feature for face recognition. During training I got an error like this:

OpenCV Error: Sizes of input arguments do not match (Response array must contain as many elements as the total number of samples) in cvPreprocessCategoricalResponses, file /home/arya/stuff/opencv/opencv-2.4.7/modules/ml/src/inner_functions.cpp, line 671 terminate called after throwing an instance of 'cv::Exception' what(): /home/arya/stuff/opencv/opencv-2.4.7/modules/ml/src/inner_functions.cpp:671: error: (-209) Response array must contain as many elements as the total number of samples in function cvPreprocessCategoricalResponses

I don't understand what this error exactly mean by.Could anyone explain me why I got error like this?