Flags parameter in the detectMultiScale function [closed]
Can someone explain to me what does the flags parameter do in the detectMultiScale function?
For example:
face = faceCascade.detectMultiScale(
gray_image,
scaleFactor = scaleFactor,
minNeighbors = min_neighbors,
minSize = (min_size, min_size),
flags = cv2.CASCADE_SCALE_IMAGE
)I could not find the flags in the documentation.
Note: I'm using OpenCV 3.1.0.
Thanks
What don't you understand in doc (C++) ?
It is not used for a new cascade.
It only says:
flags Parameter with the same meaning for an old cascade as in the function cvHaarDetectObjects. It is not used for a new cascade.
Which
flagscan I use? What does eachflagdo?@sturkmen, what is a 'new cascade'? I don't get it.
I understand that you can set this value to 0 if you use a new format for cascade classifier. I think source code is here
Flags for old cascade classifier are here
https://github.com/opencv/opencv/issu...
Ok, I see that the
flagsparameter is only being used by the Old Format Cascade, but I still don't know if I'm using the 'old format cascade' or the 'new format cascade'. I'm using OpenCV 3.1.0 with Python 2.7. Thanks for the help.you can find old format cascades here. you can use them if you want and with those cascades flags are still meaningful. but with new cascades flags change nothing.
Thanks @sturkmen, so, these are the 'new format cascades'?