Ah, cool... also just noticed article is quite old too.
Definitely want to get to the point of making stuff with shoebot as opposed to changing the shoebot code itself, at which point I might have a play with face detection stuff :)
S++
----- Original Message ----
Sent: Wed, June 16, 2010 7:38:34 AM
Subject: Re: [shoebot-devel] More face detection
Actually face detection and blob detection use two different approaches
in
opencv shoebot library too: if I remember well, face detection uses
already
haar cascade features as explained in the article, while blob
detection
depends on the binary library.
f.
example
size(720,576)
videolib =
ximport("sbopencv")
speed(300)
video = videolib.camera(0,
width=320, height=240)
nofill()
nostroke()
frame =
video.frame()
#push()
#rotate(random(-5,5))
image(None,0,0,data=frame.data)
faces = frame.faces
#print i.x, i.y, i.width, i.height
stroke(1)
strokewidth(1)
fill(1,1,1,0.5)
oval(i.x,i.y,i.width,i.height)
nostroke()
nofill
Il giorno mar,
Nice article on
face detection - seems to use ctypes... maybe we could use this instead of our
binary blob based system ?
- Entirely not sure whats involved
though...
http://blog.jozilla.net/2008/06/27/fun-with-python-opencv-and-face-detection/
S++
_______________________________________________
Shoebot-devel
mailing list
http://lists.tinkerhouse.net/listinfo.cgi/shoebot-devel-tinkerhouse.net
_______________________________________________
Shoebot-devel
mailing list
href="http://lists.tinkerhouse.net/listinfo.cgi/shoebot-devel-tinkerhouse.net"
target=_blank
Post by Stuart Axonhttp://lists.tinkerhouse.net/listinfo.cgi/shoebot-devel-tinkerhouse.net