我在这里遇到一些问题
// compute average image, eigenvalues, and eigenvectors
cvCalcEigenObjects(nTrainFaces, // nObjects
new PointerPointer(trainingFaceImgArr), // input
new PointerPointer(eigenVectArr), // output
CV_EIGOBJ_NO_CALLBACK, // ioFlags
0, // ioBufSize
null, // userData
calcLimit, pAvgTrainImg, // avg
eigenValMat.data_fl()); // eigVals
任何想法?,我只是在我的IplImage []数组中加载彩色jpg面部,但我坚持这一行代码。
以下是我的示例代码
public void learn(final String trainingFileName) {
int i;
long startTime = System.nanoTime();
trainingFaceImgArr = loadFaceImgArray(trainingFileName);
nTrainFaces = trainingFaceImgArr.length;
L.wtf("trainFaceImgArr length"+trainingFaceImgArr.length);
if (nTrainFaces < 3) {
L.wtf( "Need 3 or more training faces\n"
+ "Input file contains only " + nTrainFaces);
return;
}
// do Principal Component Analysis on the training faces
doPCA();
}
private void doPCA() {
int i;
CvTermCriteria calcLimit;
CvSize faceImgSize = new CvSize();
// set the number of eigenvalues to use
nEigens = nTrainFaces - 1;
L.wtf("allocating images for principal component analysis, using "
+ nEigens + (nEigens == 1 ? " eigenvalue" : " eigenvalues"));
// allocate the eigenvector images
faceImgSize.width(trainingFaceImgArr[0].width());
faceImgSize.height(trainingFaceImgArr[0].height());
eigenVectArr = new IplImage[nEigens];
for (i = 0; i < nEigens; i++) {
eigenVectArr[i] = cvCreateImage(faceImgSize, // size
IPL_DEPTH_32F, // depth
1); // channels
}
// allocate the eigenvalue array
eigenValMat = cvCreateMat(1, // rows
nEigens, // cols
CV_32FC1); // type, 32-bit float, 1 channel
// allocate the averaged image
pAvgTrainImg = cvCreateImage(faceImgSize, // size
IPL_DEPTH_32F, // depth
1); // channels
// set the PCA termination criterion
calcLimit = cvTermCriteria(CV_TERMCRIT_ITER, // type
nEigens, // max_iter
1); // epsilon
L.wtf("computing average image, eigenvalues and eigenvectors");
// compute average image, eigenvalues, and eigenvectors
cvCalcEigenObjects(nTrainFaces, // nObjects
new PointerPointer(trainingFaceImgArr), // input
new PointerPointer(eigenVectArr), // output
CV_EIGOBJ_NO_CALLBACK, // ioFlags
0, // ioBufSize
null, // userData
calcLimit, pAvgTrainImg, // avg
eigenValMat.data_fl()); // eigVals