hi, im using opencv func for uniform lbp (LUT ) and accuracy of recognition get worth but i read that this will not happen,what am i wrong?
read images
resize each image
lut(images,lookup table,images);
train images detection
yea, cleaning up is always a good idea..
but already from here: you'd have to apply the lut to the LBP image, not the grayscale input !
(which also means, you'd have to interfere with the library code !)
e.g. it should go here here , then also the number of histogram bins should be adapted here from 256 to 59
(this is the actual feature reduction)
i cheked like below
Mat lookup(1,256,CV_32S, uniform); // make a Mat from it
bool x=lookup.isContinuous();
int cnn=lookup.channels();
int y=lookup.total();
int z= lbp_image.depth();
LUT(lbp_image,lookup,lbp_image);// =====> error appear here
Mat p = spatial_histogram(
lbp_image, /* lbp_image */
static_cast<int>(59), /* number of possible patterns */
_grid_x, /* grid size x */
_grid_y, /* grid size y */
true);
x--> true
cnn-->1
y-->256
z-->4
yea, sorry. problem is here <--> (src.depth() == CV_8U || src.depth() == CV_8S)
Asked: 2017-03-13 00:58:24 -0600
Seen: 324 times
Last updated: Mar 13 '17
you'll probably have to show us, what you're doing.
and yes, slight decrease in accuracy is expected.
@berak : i edited it,if you need more details, i must first sort my code :)