Hello guys,
Before I start I need to thank our community members.
That was a lot of thoughts and tips tried a few and realized the issue was the model itself, that was a huge data set to be processed and matched so we decided to do something else.
So before starting with the that, there was sweet suprise, thanks todanzima.
The kits have arrived....
It was the Rpi 7" Display, Camera Module and Arduino.
Although I'm having some issues with Camera Module v2.1, working on it, for now we are using Haar Cascade to detect smile anything other than a smile will be sending data over Bluetooth, we are now using a very small model and Rpi runs smooth without no lag. A code snippet of the while block here.
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
faces = faceCascade.detectMultiScale(
gray,
scaleFactor= sF,
minNeighbors=8,
minSize=(55, 55),
flags=cv2.CASCADE_SCALE_IMAGE
)
for (x, y, w, h) in faces:
roi_gray = gray[y:y+h, x:x+w]
roi_color = frame[y:y+h, x:x+w]
smile = smileCascade.detectMultiScale(
roi_gray,
scaleFactor= 1.7,
minNeighbors=22,
minSize=(25, 25),
flags=cv2.CASCADE_SCALE_IMAGE
)
if len(smile):
print("All Good")
else:
print("Send data over BT")
I've removed the feed window. and the output was satisfactory.
I'm trying to bring much more detailing on the mood identification part. Code will be available in our github
Whats next? Its time to unleash the power of Bluetooth and complete the secondary unit.
Cheers and Thanks to everyone! 
Top Comments