vivek0402's profile - activity

Is your gender detection working correctly? what approach did you take? Please answer at following link- http://answers.opencv.org/question/26...

initially i tested with few images and it gave correct answer for many of them but when it was tested with large amount of test images, it gave many wrong results. I am just asking the correct way to detect gender. please suggest the better ways or improvements.

@berak I think it is returning the most matching face. so the result can not be believed. assume I have male face which is matching with any of the female face of training faces up to some extent but not any of the male faces. so it will return female.(This problem is arising for me cz it has recognized many of the male images to female.) I am just asking what modifications should I apply to get better results.

For gender detection, I took 20 faces of men and 20 faces of women and then trained fisherface algorithm with these faces by using id 1 for all male faces and 2 for all female faces. now when I am predicting with any male or female image, it gives correct answer. but here I want to know that Is this approach is right or not. Is there any better way to this?

By Using OpenCv library you can not do this. You will have to recode the algorithm and while computing P.C.A., neglect first three values. then launch it as revised version of Eigen FaceRecognition Algorithm.

please be more clear about what you want.

please be more clear about what you want.

yeah it's working. thanks

Can you please describe how it is done in LBPHFaceRecognizer .

I have trained.xml file saved previously. now I want to add more training data in this file. Is there any method to do that? I have a scenario- I have trained Face recognition algorithm with some faces and saved the data in file trained.xml. now I want to add data of one more person in that file. I tried to train the algorithm with the images of that person saperately but it gives error-

Atleast two classes are required for LDA but only one class is provided.

I have no idea what to do now.

Try System.load("absolute path to your opencv_java248.dll ") instead of System.loadLibrary(). and change java library path to -Djava.library.path="absolute path to your opencv_java248.dll".

have you changed the path of java library i.e.--Djava.library.path="path to your library"?

try System.loadLibrary(relative path). if it is not working then try System.load(absolute path). and in VM option add -Djava.library.path="path of your dll" its working for me.

I am also getting same error. if any one got the solution please post it here.

Finally I got the solution of my problem. The size of my test and training images were 70* 70. I changed the size to 200* 200 and now it is working perfectly. The reason behind it is that EigenFaceRecognizer and FisherFaceRecognizer don't work with image width that are not multiple of 8 or 16(In my case). 70 is not multiple of 8 so it is not working but for image width 200(multiple of 8), it is working fine.

Ok it is working fine with LBPH FaceRecognizer but getting same eeror message for EigenFaceRecognizer.

@berak then how to load it as 1 channel??

@berak Images are already gray scaled. but I tried it again- IplImage imga=new IplImage(); opencv_imgproc.cvCvtColor(img, imga,opencv_imgproc.CV_RGB2GRAY); it gives error- OpenCV Error: Bad argument (Unknown array type) in unknown function,

when I am using LBPfaceRecognizer, it gives error- OpenCV Error: The function/feature is not implemented (Using Original Local Binary Patterns for feature extraction only works on single-channel images (given 16) Please pass the image data as a grayscale image!)

All images are preprocessed, grey scaled and of same size(70*70). I am using open cv-2.4.7.

I am getting error in EigenFaces.predict() method in java cv face recognition. The error is-

OpenCV Error: Image step is wrong (The matrix is not continuous, thus its number of rows can not be changed) in unknown function, file ......\src\opencv\modules\core\src\matrix.cpp, line 802

my code is-

public static void main(String[] args)  {
long size=6;
MatVector imgs=new MatVector(size);
int[] id={0,0,0,0,0,0};

FaceRecognizer fr=opencv_contrib.createEigenFaceRecognizer();
for(int i=0;i<=5;i++)
{
    String url="C:/Users/vivek/Documents/NetBeansProjects/Recognizer2/src/a"+(i+1)+".jpg";
    IplImage img=opencv_highgui.cvLoadImage(url);
    imgs=imgs.put(i,img);

}
fr.train(imgs,id);
IplImage testImage=opencv_highgui.cvLoadImage("C:/Users/vivek/Documents/NetBeansProjects/Recognizer2/src/a3.jpg");
CvMat mat= testImage.asCvMat();
int val=fr.predict(mat);
System.out.println(val);

}

I I am working on Face Recognition by using java library of OpenCv. but on training the algotithm I am getting following debugging error-

OpenCV Error: Assertion failed (0 <= i && i < (int)v.size()) in unknown function, file ......\src\opencv\modules\core\src\matrix.cpp, line 992

Exception in thread "main" java.lang.RuntimeException: ......\src\opencv\modules\core\src\matrix.cpp:992: error: (-215) 0 <= i && i < (int)v.size()

I am using OpenCv 2.4.6, JavaCv.6, netbeans7.3.1, windows8 64 bit. I am using following libraries- OpenCv-2.4.6, Javacpp.jar javacv.jar, opencv-2.4.6.0-windows-x86_64.jar, javacv-windows-x86_64.jar. Here is my code-

static{ System.loadLibrary("opencv_java246"); }
public static void main(String[] args) {
    // TODO code application logic here
  FaceRecognizer fr= opencv_contrib.createEigenFaceRecognizer();
  MatVector imgs=new MatVector(7);
  int []id=new int[7];
  for(int i=1;i<=7;i++)
  {
      String url="C:/Users/vivek/Documents/NetBeansProjects/Recognizer2/a"+i+".jpg";
      CvArr img=opencv_highgui.cvLoadImage(url);
      imgs.put(img);
      id[i-1]=i;
  }
  CvArr test=opencv_highgui.cvLoadImageM("C:/Users/vivek/Documents/NetBeansProjects/Recognizer2/a7.jpg");
  fr.train(imgs,id);
  System.out.println(fr.predict(test));

I am stuck here please describe briefly what's the problem.

I am using open cv 2.4.6 and java cv 0.6. for face recognition. I wanted to know the no. of algorithms present for face recognition. but in my code it returns 0. here is my code-

StringVector algo=new StringVector();
    Algorithm.getList(algo);
    System.out.println(algo.size());

If I am creating object for any face recognition algorithm, it returns null.does it mean No algorithm's present for face recognition? What's wrong here.

I am using java library of open cv 2.4.7. I don't know how to use its FaceRecognizer class. when I looked at the definition of this class I found this.

Ptr_FaceRecognizer createEigenFaceRecognizer(int num_components = 0, double threshold = DBL_MAX)

Return type 'Ptr_FaceRecognizer' is not supported, skipping the function.

is there any other method to use this algorithm? As I am very new in the field of open cv so Please suggest the way to perform face recognition by using open cv java library.

I have pre processed faces. please describe the efficient way to make training set from these pre processed faces. I have 10 pre processed face per person. thank You.

I got what the problem was. actually the center of face about which the face was rotated was calculated wrongly.

@StevenPuttemans I am actually accepting only those faces in which both eyes are detected.