VL_EXPORT VlDsiftFilter *
vl_dsift_new_basic (int imWidth, int imHeight, int step, int binSize)
{
VlDsiftFilter* self = vl_dsift_new(imWidth, imHeight) ;
VlDsiftDescriptorGeometry geom = *vl_dsift_get_geometry(self) ;
geom.binSizeX = binSize ;
geom.binSizeY = binSize ;
vl_dsift_set_geometry(self, &geom) ;
vl_dsift_set_steps(self, step, step) ;
return self ;
}
void
mexFunction(int nout, mxArray *out[],
int nin, const mxArray *in[])
{
enum {IN_I=0, IN_END} ;
enum {OUT_FRAMES=0, OUT_DESCRIPTORS} ;
int verbose = 0 ;
int opt ;
int next = IN_END ;
mxArray const *optarg ;
float const *data ;
int M, N ;
int step [2] = {1,1} ;
vl_bool norm = 0 ;
vl_bool floatDescriptors = VL_FALSE ;
vl_bool useFlatWindow = VL_FALSE ;
double windowSize = -1.0 ;
double *bounds = NULL ;
double boundBuffer [4] ;
VlDsiftDescriptorGeometry geom ;
VL_USE_MATLAB_ENV ;
geom.numBinX = 4 ;
geom.numBinY = 4 ;
geom.numBinT = 8 ;
geom.binSizeX = 3 ;
geom.binSizeY = 3 ;
/* -----------------------------------------------------------------
* Check the arguments
* -------------------------------------------------------------- */
if (nin < 1) {
vlmxError(vlmxErrNotEnoughInputArguments, NULL) ;
} else if (nout > 2) {
vlmxError(vlmxErrTooManyOutputArguments, NULL) ;
}
if (mxGetNumberOfDimensions (in[IN_I]) != 2 ||
mxGetClassID (in[IN_I]) != mxSINGLE_CLASS ) {
vlmxError(vlmxErrInvalidArgument,
"I must be a matrix of class SINGLE.") ;
}
data = (float*) mxGetData (in[IN_I]) ;
M = mxGetM (in[IN_I]) ;
N = mxGetN (in[IN_I]) ;
while ((opt = vlmxNextOption (in, nin, options, &next, &optarg)) >= 0) {
switch (opt) {
case opt_verbose :
++ verbose ;
break ;
case opt_fast :
useFlatWindow = 1 ;
break ;
case opt_norm :
norm = 1 ;
break ;
case opt_bounds :
if (!vlmxIsPlainVector(optarg, 4)) {
mexErrMsgTxt("BOUNDS must be a 4-dimensional vector.") ;
}
bounds = boundBuffer ;
bounds [0] = mxGetPr(optarg)[0] - 1 ;
bounds [1] = mxGetPr(optarg)[1] - 1 ;
bounds [2] = mxGetPr(optarg)[2] - 1 ;
bounds [3] = mxGetPr(optarg)[3] - 1 ;
break ;
case opt_size :
if (!vlmxIsPlainVector(optarg,-1)) {
vlmxError(vlmxErrInvalidArgument,"SIZE is not a plain vector.") ;
}
if (mxGetNumberOfElements(optarg) == 1) {
geom.binSizeX = (int) mxGetPr(optarg)[0] ;
geom.binSizeY = (int) mxGetPr(optarg)[0] ;
} else if (mxGetNumberOfElements(optarg) == 2) {
geom.binSizeX = (int) mxGetPr(optarg)[1] ;
geom.binSizeY = (int) mxGetPr(optarg)[0] ;
} else {
vlmxError(vlmxErrInvalidArgument,"SIZE is neither a scalar or a 2D vector.") ;
}
if (geom.binSizeX < 1 || geom.binSizeY < 1) {
vlmxError(vlmxErrInvalidArgument,"SIZE value is invalid.") ;
}
break ;
case opt_step :
if (!vlmxIsPlainVector(optarg,-1)) {
vlmxError(vlmxErrInvalidArgument,"STEP is not a plain vector.") ;
}
if (mxGetNumberOfElements(optarg) == 1) {
step[0] = (int) mxGetPr(optarg)[0] ;
step[1] = (int) mxGetPr(optarg)[0] ;
} else if (mxGetNumberOfElements(optarg) == 2) {
step[0] = (int) mxGetPr(optarg)[1] ;
step[1] = (int) mxGetPr(optarg)[0] ;
} else {
vlmxError(vlmxErrInvalidArgument,"STEP is neither a scalar or a 2D vector.") ;
}
if (step[0] < 1 || step[1] < 1) {
vlmxError(vlmxErrInvalidArgument,"STEP value is invalid.") ;
}
break ;
case opt_window_size :
if (!vlmxIsPlainScalar(optarg) || (windowSize = *mxGetPr(optarg)) < 0) {
vlmxError(vlmxErrInvalidArgument,"WINDOWSIZE is not a scalar or it is negative.") ;
}
break ;
case opt_float_descriptors :
floatDescriptors = VL_TRUE ;
break ;
case opt_geometry :
if (!vlmxIsPlainVector(optarg,3)) {
vlmxError(vlmxErrInvalidArgument, "GEOMETRY is not a 3D vector.") ;
}
geom.numBinY = (int)mxGetPr(optarg)[0] ;
geom.numBinX = (int)mxGetPr(optarg)[1] ;
geom.numBinT = (int)mxGetPr(optarg)[2] ;
if (geom.numBinX < 1 ||
geom.numBinY < 1 ||
geom.numBinT < 1) {
vlmxError(vlmxErrInvalidArgument, "GEOMETRY value is invalid.") ;
}
break ;
default :
abort() ;
}
}
/* -----------------------------------------------------------------
* Do job
* -------------------------------------------------------------- */
{
int numFrames ;
int descrSize ;
VlDsiftKeypoint const *frames ;
float const *descrs ;
int k, i ;
VlDsiftFilter *dsift ;
/* note that the image received from MATLAB is transposed */
dsift = vl_dsift_new (M, N) ;
vl_dsift_set_geometry(dsift, &geom) ;
vl_dsift_set_steps(dsift, step[0], step[1]) ;
if (bounds) {
vl_dsift_set_bounds(dsift,
VL_MAX(bounds[1], 0),
VL_MAX(bounds[0], 0),
VL_MIN(bounds[3], M - 1),
VL_MIN(bounds[2], N - 1));
}
vl_dsift_set_flat_window(dsift, useFlatWindow) ;
if (windowSize >= 0) {
vl_dsift_set_window_size(dsift, windowSize) ;
}
numFrames = vl_dsift_get_keypoint_num (dsift) ;
descrSize = vl_dsift_get_descriptor_size (dsift) ;
geom = *vl_dsift_get_geometry (dsift) ;
if (verbose) {
int stepX ;
int stepY ;
int minX ;
int minY ;
int maxX ;
int maxY ;
vl_bool useFlatWindow ;
vl_dsift_get_steps (dsift, &stepY, &stepX) ;
vl_dsift_get_bounds (dsift, &minY, &minX, &maxY, &maxX) ;
useFlatWindow = vl_dsift_get_flat_window(dsift) ;
mexPrintf("vl_dsift: image size [W, H] = [%d, %d]\n", N, M) ;
mexPrintf("vl_dsift: bounds: [minX,minY,maxX,maxY] = [%d, %d, %d, %d]\n",
minX+1, minY+1, maxX+1, maxY+1) ;
mexPrintf("vl_dsift: subsampling steps: stepX=%d, stepY=%d\n", stepX, stepY) ;
mexPrintf("vl_dsift: num bins: [numBinT, numBinX, numBinY] = [%d, %d, %d]\n",
geom.numBinT,
geom.numBinX,
geom.numBinY) ;
mexPrintf("vl_dsift: descriptor size: %d\n", descrSize) ;
mexPrintf("vl_dsift: bin sizes: [binSizeX, binSizeY] = [%d, %d]\n",
geom.binSizeX,
geom.binSizeY) ;
mexPrintf("vl_dsift: flat window: %s\n", VL_YESNO(useFlatWindow)) ;
mexPrintf("vl_dsift: window size: %g\n", vl_dsift_get_window_size(dsift)) ;
mexPrintf("vl_dsift: num of features: %d\n", numFrames) ;
}
vl_dsift_process (dsift, data) ;
frames = vl_dsift_get_keypoints (dsift) ;
descrs = vl_dsift_get_descriptors (dsift) ;
/* ---------------------------------------------------------------
* Create output arrays
* ------------------------------------------------------------ */
{
mwSize dims [2] ;
dims [0] = descrSize ;
dims [1] = numFrames ;
if (floatDescriptors) {
out[OUT_DESCRIPTORS] = mxCreateNumericArray
(2, dims, mxSINGLE_CLASS, mxREAL) ;
} else {
out[OUT_DESCRIPTORS] = mxCreateNumericArray
(2, dims, mxUINT8_CLASS, mxREAL) ;
}
dims [0] = norm ? 3 : 2 ;
out[OUT_FRAMES] = mxCreateNumericArray
(2, dims, mxDOUBLE_CLASS, mxREAL) ;
}
/* ---------------------------------------------------------------
* Copy back
* ------------------------------------------------------------ */
{
float *tmpDescr = mxMalloc(sizeof(float) * descrSize) ;
double *outFrameIter = mxGetPr(out[OUT_FRAMES]) ;
void *outDescrIter = mxGetData(out[OUT_DESCRIPTORS]) ;
for (k = 0 ; k < numFrames ; ++k) {
*outFrameIter++ = frames[k].y + 1 ;
*outFrameIter++ = frames[k].x + 1 ;
/* We have an implied / 2 in the norm, because of the clipping
below */
if (norm)
*outFrameIter++ = frames [k].norm ;
vl_dsift_transpose_descriptor (tmpDescr,
descrs + descrSize * k,
geom.numBinT,
geom.numBinX,
geom.numBinY) ;
if (floatDescriptors) {
for (i = 0 ; i < descrSize ; ++i) {
float * pt = (float*) outDescrIter ;
*pt++ = VL_MIN(512.0F * tmpDescr[i], 255.0F) ;
outDescrIter = pt ;
}
} else {
for (i = 0 ; i < descrSize ; ++i) {
vl_uint8 * pt = (vl_uint8*) outDescrIter ;
*pt++ = (vl_uint8) (VL_MIN(512.0F * tmpDescr[i], 255.0F)) ;
outDescrIter = pt ;
}
}
}
mxFree(tmpDescr) ;
}
vl_dsift_delete (dsift) ;
}
}
vector<vector<float> > Encoder::extractMultiDSIFT(Mat normMat, Mat landmarks, int level){
vector<vector<float> > ret;
//hard code max LBP size
int tunedCellSize = 10;
int tunedCols, tunedRows;
int dimension = patchSize / cellSize;
vector<float> dsiftCode;
for (int l = 0; l < level; l++){
int tmpcellSize = cellSize - l;
int tmppatchSize = tmpcellSize*dimension;
for (unsigned int i = 0; i < landmarks.cols; i++){
if (landmarks.at<float>(0, i) > tmppatchSize/2 && landmarks.at<float>(1, i) > tmppatchSize/2 && landmarks.at<float>(0, i) + tmppatchSize/2 < normMat.cols && landmarks.at<float>(1, i) + tmppatchSize/2 < normMat.rows){
Mat roi(normMat, Rect(landmarks.at<float>(0, i) - tmppatchSize/2 , landmarks.at<float>(1, i) - tmppatchSize/2, tmppatchSize, tmppatchSize));
vector<float> data;
for (int j = 0; j < roi.cols; j++){
for (int k = 0; k < roi.rows; k++){
data.push_back((float)roi.at<unsigned char>(k, j)/255);
}
}
//dsift
int numFrames ;
int descrSize ;
VlDsiftKeypoint const *frames ;
float const *descrs ;
VlDsiftFilter *dsift ;
VlDsiftDescriptorGeometry geom ;
geom.numBinX = 2 ;
geom.numBinY = 2 ;
geom.numBinT = 4 ;
geom.binSizeX = 4 ;
geom.binSizeY = 4 ;
dsift = vl_dsift_new (roi.rows, roi.cols) ;
vl_dsift_set_geometry(dsift, &geom) ;
vl_dsift_set_steps(dsift, 2, 2) ;
vl_dsift_set_flat_window(dsift, 1) ;
numFrames = vl_dsift_get_keypoint_num (dsift) ;
descrSize = vl_dsift_get_descriptor_size (dsift) ;
geom = *vl_dsift_get_geometry (dsift) ;
vl_dsift_process (dsift, &data[0]) ;
frames = vl_dsift_get_keypoints (dsift) ;
descrs = vl_dsift_get_descriptors (dsift) ;
//cout<<"frames: "<<numFrames<<" descrs: "<<descrSize<<" cols: "<<roi.cols<<" rows: "<<roi.rows<<endl;
float tranDescr[128];
for (int f = 0; f < numFrames; f++){
vl_dsift_transpose_descriptor (tranDescr, descrs + descrSize * f, geom.numBinT, geom.numBinX, geom.numBinY) ;
for (int d = 0 ; d < descrSize ; d++) {
tranDescr[d] = VL_MIN(512.0F * tranDescr[d], 255.0F) ;
dsiftCode.push_back(tranDescr[d]);
//cout<<tmpDescr[i]<<" ";
}
}
//if (i != 0 && i != 2){
ret.push_back(dsiftCode);
dsiftCode.clear();
//}
vl_dsift_delete (dsift) ;
}
else{
cout<<"Patch out of bound: "<<landmarks.at<float>(0, i)<<" "<<landmarks.at<float>(1, i)<<endl;
cout<<"landmark: "<<i<<" Cols: "<<tunedCols<<" Rows: "<<tunedRows<<endl;
imwrite("tmp/outOfBound.jpg", normMat);
exit(1);
}
}
}
return ret;
}
/** ------------------------------------------------------------------
** @brief Python entry point
**/
PyObject * vl_dsift_python(
PyArrayObject & pyArray,
int opt_step,
PyArrayObject & opt_bounds,
int opt_size,
bool opt_fast,
bool opt_verbose,
bool opt_norm)
{
// check data type
assert(pyArray.descr->type_num == PyArray_FLOAT);
assert(pyArray.flags & NPY_FORTRAN);
assert(opt_bounds.descr->type_num == PyArray_FLOAT);
int verbose = 0;
int opt;
float const *data;
int M, N;
int step = 1;
int size = 3;
vl_bool norm = 0;
vl_bool useFlatWindow = VL_FALSE;
double *bounds = NULL;
double boundBuffer[4];
/* -----------------------------------------------------------------
* Check the arguments
* -------------------------------------------------------------- */
data = (float*) pyArray.data;
M = pyArray.dimensions[0];
N = pyArray.dimensions[1];
if (opt_verbose)
++verbose;
if (opt_fast)
useFlatWindow = 1;
if (opt_norm)
norm = 1;
if (opt_bounds.nd == 1 && opt_bounds.dimensions[0] == 4) {
double * tmp = (double *) opt_bounds.data;
bounds = boundBuffer;
for (int i = 0; i < 4; i++)
bounds[i] = tmp[i];
}
if (opt_size >= 0)
size = opt_size;
if (opt_step >= 0)
step = opt_step;
// create PyTuple for outputs
PyObject * tuple = PyTuple_New(2);
/* -----------------------------------------------------------------
* Do job
* -------------------------------------------------------------- */
{
int numFrames;
int descrSize;
VlDsiftKeypoint const *frames;
VlDsiftDescriptorGeometry const *geom;
float const *descrs;
int k, i;
VlDsiftFilter *dsift;
dsift = vl_dsift_new_basic(M, N, step, size);
if (bounds) {
vl_dsift_set_bounds(dsift, VL_MAX(bounds[0], 0), VL_MAX(
bounds[1], 0), VL_MIN(bounds[2], M - 1), VL_MIN(bounds[3], N
- 1));
}
vl_dsift_set_flat_window(dsift, useFlatWindow);
numFrames = vl_dsift_get_keypoint_num (dsift) ;
descrSize = vl_dsift_get_descriptor_size (dsift) ;
geom = vl_dsift_get_geometry(dsift);
if (verbose) {
int stepX;
int stepY;
int minX;
int minY;
int maxX;
int maxY;
vl_bool useFlatWindow;
vl_dsift_get_steps(dsift, &stepX, &stepY);
vl_dsift_get_bounds(dsift, &minX, &minY, &maxX, &maxY);
useFlatWindow = vl_dsift_get_flat_window(dsift);
printf("dsift: image size: %d x %d\n", N, M);
printf(
" bounds: [%d, %d, %d, %d]\n", minY, minX,
maxY, maxX);
printf(" subsampling steps: %d, %d\n", stepY, stepX);
printf(
" num bins: [%d, %d, %d]\n", geom->numBinT,
geom->numBinX, geom->numBinY);
printf(" descriptor size: %d\n", descrSize);
printf(
" bin sizes: [%d, %d]\n", geom->binSizeX,
geom->binSizeY);
printf(" flat window: %s\n", VL_YESNO(useFlatWindow));
printf(" number of frames: %d\n", numFrames);
}
vl_dsift_process(dsift, data);
frames = vl_dsift_get_keypoints(dsift);
descrs = vl_dsift_get_descriptors(dsift);
/* ---------------------------------------------------------------
* Create output arrays
* ------------------------------------------------------------ */
npy_intp dims[2];
dims[0] = descrSize;
dims[1] = numFrames;
// allocate PyArray objects
PyArrayObject * _descriptors = (PyArrayObject *) PyArray_NewFromDescr(
&PyArray_Type, PyArray_DescrFromType(PyArray_UINT8),
2, dims, NULL, NULL, NPY_F_CONTIGUOUS, NULL);
if (norm)
dims[0] = 3;
else
dims[0] = 2;
PyArrayObject * _frames = (PyArrayObject*) PyArray_NewFromDescr(
&PyArray_Type, PyArray_DescrFromType(PyArray_DOUBLE),
2, dims, NULL, NULL, NPY_F_CONTIGUOUS, NULL);
// put PyArray objects in PyTuple
PyTuple_SetItem(tuple, 0, PyArray_Return(_frames));
PyTuple_SetItem(tuple, 1, PyArray_Return(_descriptors));
/* ---------------------------------------------------------------
* Copy back
* ------------------------------------------------------------ */
{
float *tmpDescr = (float*) vl_malloc(sizeof(float) * descrSize);
double *outFrameIter = (double*) _frames->data;
vl_uint8 *outDescrIter = (vl_uint8 *) _descriptors->data;
for (k = 0; k < numFrames; ++k) {
*outFrameIter++ = frames[k].y;
*outFrameIter++ = frames[k].x;
/* We have an implied / 2 in the norm, because of the clipping
below */
if (norm)
*outFrameIter++ = frames[k].norm;
vl_dsift_transpose_descriptor(
tmpDescr, descrs + descrSize * k, geom->numBinT,
geom->numBinX, geom->numBinY);
for (i = 0; i < descrSize; ++i) {
*outDescrIter++ = (vl_uint8) (VL_MIN(
512.0F * tmpDescr[i], 255.0F));
}
}
vl_free(tmpDescr);
}
vl_dsift_delete(dsift);
}
return tuple;
}
vector<vector<float> > Encoder::extractTunedDSIFT(Mat normMat, Mat landmarks){
//eye, eyebrow, eye-band, nose-ver, mouth, left face, right face, jaw, forehead, nose-hor
//40x20x2, 40x20x2, 100x40, 40x60, 60x40, 40x60,40x60, 50x20, 100x40, 60x40
vector<vector<float> > ret;
//hard code max LBP size
int tunedCellSize = 10;
int tunedCols, tunedRows;
vector<float> dsiftCode;
for (int l = 0; l <= 2; l++){
for (int i = 0; i < landmarks.cols; i++){
switch (i){
case 0:
case 1:
case 2:
case 3:
tunedCols = 30 + 10*l;
tunedRows = 10 + 10*l;
break;
case 4:
tunedCols = 70 + 20*l;
tunedRows = 30 + 10*l;
break;
case 5:
tunedCols = 30 + 10*l;
tunedRows = 40 + 20*l;
break;
case 6:
tunedCols = 40 + 20*l;
tunedRows = 30 + 10*l;
break;
case 7:
case 8:
tunedCols = 30 + 10*l;
tunedRows = 40 + 20*l;
break;
case 9:
tunedCols = 40 + 10*l;
tunedRows = 20;
break;
case 10:
tunedCols = 60 + 20*l;
tunedRows = 30;
break;
case 11:
tunedCols = 40 + 10*l;
tunedRows = 20 + 10*l;
break;
default:
cout<<"Wrong landmark size: "<<i<<endl;
exit(1);
}
if (landmarks.at<float>(0, i) > tunedCols/2 && landmarks.at<float>(1, i) > tunedRows/2 && landmarks.at<float>(0, i) + tunedCols/2 < normMat.cols && landmarks.at<float>(1, i) + tunedRows/2 < normMat.rows){
Mat roi(normMat, Rect(landmarks.at<float>(0, i) - tunedCols/2 , landmarks.at<float>(1, i) - tunedRows/2, tunedCols, tunedRows));
vector<float> data;
for (int j = 0; j < roi.cols; j++){
for (int k = 0; k < roi.rows; k++){
data.push_back((float)roi.at<unsigned char>(k, j)/255);
}
}
//dsift
int numFrames ;
int descrSize ;
VlDsiftKeypoint const *frames ;
float const *descrs ;
VlDsiftFilter *dsift ;
VlDsiftDescriptorGeometry geom ;
geom.numBinX = 2 ;
geom.numBinY = 2 ;
geom.numBinT = 4 ;
geom.binSizeX = 4 ;
geom.binSizeY = 4 ;
dsift = vl_dsift_new (roi.rows, roi.cols) ;
vl_dsift_set_geometry(dsift, &geom) ;
vl_dsift_set_steps(dsift, 2, 2) ;
vl_dsift_set_flat_window(dsift, 1) ;
numFrames = vl_dsift_get_keypoint_num (dsift) ;
descrSize = vl_dsift_get_descriptor_size (dsift) ;
geom = *vl_dsift_get_geometry (dsift) ;
vl_dsift_process (dsift, &data[0]) ;
frames = vl_dsift_get_keypoints (dsift) ;
descrs = vl_dsift_get_descriptors (dsift) ;
//cout<<"frames: "<<numFrames<<" descrs: "<<descrSize<<" cols: "<<roi.cols<<" rows: "<<roi.rows<<endl;
float tranDescr[128];
for (int f = 0; f < numFrames; f++){
vl_dsift_transpose_descriptor (tranDescr, descrs + descrSize * f, geom.numBinT, geom.numBinX, geom.numBinY) ;
for (int d = 0 ; d < descrSize ; d++) {
tranDescr[d] = VL_MIN(512.0F * tranDescr[d], 255.0F) ;
dsiftCode.push_back(tranDescr[d]);
//cout<<tmpDescr[i]<<" ";
}
}
//if (i != 0 && i != 2){
ret.push_back(dsiftCode);
dsiftCode.clear();
//}
vl_dsift_delete (dsift) ;
}
else{
cout<<"Patch out of bound: "<<landmarks.at<float>(0, i)<<" "<<landmarks.at<float>(1, i)<<endl;
cout<<"landmark: "<<i<<" Cols: "<<tunedCols<<" Rows: "<<tunedRows<<endl;
imwrite("tmp/outOfBound.jpg", normMat);
exit(1);
}
}
}
return ret;
}
