int Classifier::getZone(IplImage* frame, double& confidence, FrameAnnotation& fa) {
if (!leftEye || !rightEye || !nose) {
string err = "Classifier::getZone. Location extractors malformed.";
throw (err);
}
// the roi offset
CvPoint offset;
// LOIs
CvPoint leftEyeLocation;
CvPoint rightEyeLocation;
CvPoint noseLocation;
// computing the confidence of the location identification
double leftPSR;
double rightPSR;
double nosePSR;
CvPoint center = fa.getLOI(Annotations::Face);
if (!center.x || !center.y) {
center.x = Globals::imgWidth / 2;
center.y = Globals::imgHeight / 2;
fa.setFace(center);
}
offset.x = offset.y = 0;
IplImage* roi = (roiFunction)? roiFunction(frame, fa, offset, Annotations::Face) : 0;
// all location extractors do identical preprocessing. Therefore, preprocess
// once using say the left eye extractor and re-use it for all three extractors
fftw_complex* preprocessedImage = leftEye->getPreprocessedImage((roi)? roi : frame);
#pragma omp parallel sections num_threads(2)
{
#pragma omp section
{
leftEye->setImage(preprocessedImage);
leftEye->apply();
leftEye->getMaxLocation(leftEyeLocation, leftPSR);
leftEyeLocation.x += offset.x;
leftEyeLocation.y += offset.y;
}
#pragma omp section
{
// get the location of the right eye
rightEye->setImage(preprocessedImage);
rightEye->apply();
rightEye->getMaxLocation(rightEyeLocation, rightPSR);
rightEyeLocation.x += offset.x;
rightEyeLocation.y += offset.y;
}
}
if (roi)
cvReleaseImage(&roi);
center.x = (leftEyeLocation.x + rightEyeLocation.x) / 2;
center.y = leftEyeLocation.y + Globals::noseDrop;
fa.setNose(center);
offset.x = offset.y = 0;
roi = (roiFunction)? roiFunction(frame, fa, offset, Annotations::Nose) : 0;
// free the preprocessed image
fftw_free(preprocessedImage);
// all location extractors do identical preprocessing. Therefore, preprocess
// once using say the left eye extractor and re-use it for all three extractors
preprocessedImage = nose->getPreprocessedImage((roi)? roi : frame);
// get the location of the nose
nose->setImage(preprocessedImage);
nose->apply();
nose->getMaxLocation(noseLocation, nosePSR);
noseLocation.x += offset.x;
noseLocation.y += offset.y;
// free the preprocessed image
fftw_free(preprocessedImage);
fa.setLeftIris(leftEyeLocation);
fa.setRightIris(rightEyeLocation);
fa.setNose(noseLocation);
// we are done with the images at this point. Free roi if not zero
if (roi)
cvReleaseImage(&roi);
// cout << "Confidence (L, R, N) = (" << leftPSR << ", " <<
// rightPSR << ")" << endl;
// extract features vector
vector<double> data;
for (int i = 0; i < nFeatures; i++) {
double value = featureExtractors[i]->extract(&fa);
data.push_back(value);
}
// normalize
normalize(data);
// create SVM Light objects to classify
DOC* doc;
WORD* words = (WORD*)malloc(sizeof(WORD) * (nFeatures + 1));
for (int i = 0; i < nFeatures; i++) {
words[i].wnum = featureExtractors[i]->getId();
words[i].weight = data[i];
}
// SVM Light expects that the features vector has a zero element
// to indicate termination and hence
words[nFeatures].wnum = 0;
words[nFeatures].weight = 0.0;
// create doc
string comment = "Gaze SVM";
doc = create_example(-1, 0, 0, 0.0, create_svector(words, (char*)comment.c_str(), 1.0));
int maxIndex = 0;
confidence = -FLT_MAX;
double dists[Globals::numZones];
// classify using each zone model
#pragma omp parallel for num_threads(Globals::numZones)
for (unsigned int i = 0; i < Globals::numZones; i++) {
if (kernelType == Trainer::Linear)
dists[i] = classify_example_linear(models[i], doc);
else
dists[i] = classify_example(models[i], doc);
}
for (unsigned int i = 0; i < Globals::numZones; i++) {
if (confidence < dists[i]) {
confidence = dists[i];
maxIndex = i + 1;
}
}
free_example(doc, 1);
free(words);
return maxIndex;
}
int main(int argc, char** argv) {
string modelsFileName = "";
string imageFileName = "";
string imageDirectory = "";
int x = Globals::imgWidth / 2;
int y = Globals::imgHeight / 2;
for (int i = 1; i < argc; i++) {
if (!strcmp(argv[i], "-i"))
imageFileName = argv[i + 1];
else if (!strcmp(argv[i], "-d"))
imageDirectory = argv[i + 1];
else if (!strcmp(argv[i], "-m"))
modelsFileName = argv[i + 1];
else if (!strcmp(argv[i], "-c")) {
char* str = argv[i + 1];
char* token = strtok(str, "(),");
if (token)
x = atoi(token);
token = strtok(NULL, "(),");
if (token)
y = atoi(token);
}
else if (!strcmp(argv[i], "-h")) {
cout <<
"Usage: classify -i <imageFileName> -m <modelsFileName>" << endl;
return 0;
}
}
if (modelsFileName == "") {
cout <<
"Usage: classify -i <imageFileName> -m <modelsFileName>" << endl;
return -1;
}
CvPoint center;
center.x = x;
center.y = y;
CvSize size;
size.width = Globals::roiWidth;
size.height = Globals::roiHeight;
double scale = 0.3;
try {
loadModel(modelsFileName);
if (imageFileName != "") {
Preprocess preprocess(size, scale, center, roiFunction);
IplImage* image = cvLoadImage(imageFileName.c_str());
IplImage* imageVector = preprocess.generateImageVector(image);
cout << "Sector " << classify(imageVector) << endl;
cvReleaseImage(&image);
cvReleaseImage(&imageVector);
} else if (imageDirectory != "") {
int counts[5][6];
for (int i = 0; i < 5; i++)
for (int j = 0; j < 6; j++)
counts[i][j] = 0;
string annotationsFileName = imageDirectory + "/annotations.xml";
Annotations annotations;
annotations.readAnnotations(annotationsFileName);
CvPoint& center = annotations.getCenter();
Preprocess preprocess(size, scale, center, roiFunction);
vector<FrameAnnotation*>& frameAnnotations = annotations.getFrameAnnotations();
for (unsigned int i = 0; i < frameAnnotations.size(); i++) {
FrameAnnotation* fa = frameAnnotations[i];
fa->setFace(center);
int expectedZone = fa->getSector();
counts[expectedZone - 1][5]++;
// compose filename and update map
char buffer[256];
sprintf(buffer, "frame_%d.png", fa->getFrameNumber());
string simpleName = buffer;
string fileName = imageDirectory + "/" + simpleName;
IplImage* image = cvLoadImage(fileName.c_str());
IplImage* imageVector = preprocess.generateImageVector(image);
int zone = classify(imageVector);
if (expectedZone == zone)
counts[zone - 1][zone - 1]++;
else
counts[expectedZone - 1][zone - 1]++;
cvReleaseImage(&image);
cvReleaseImage(&imageVector);
}
cout << "Errors by class" << endl;
for (int i = 0; i < 5; i++) {
for (int j = 0; j < 6; j++)
cout << counts[i][j] << "\t";
cout << endl;
}
}
} catch (string err) {
cout << err << endl;
}
return 0;
}
