Motion-Detection | A script that can detect motion from your webcam | Computer Vision library

I have this simple Python code that makes predictions on the emotions of the face (took it from here in case you need to run it), and shows it on the rectangle around the face on the camera. But the problem is it has many noises. For instance, Fearful -- Sad -- -- Sad and such. I want to smooth out the predictions and filter out singled out predictions. How can I make a change that if n number of predictions in a row said Sad, then display it as Sad?

You'll only need to change the last few lines as the initial parts are all for predictions.

What is [0] and (1) in: r = np.random.randint((1), 24000, 1)[0]

Entire github code:

https://github.com/Pawandeep-prog/facial-emotion-detection-webapp/blob/main/facial-detection.py#L230

I want to take a frame from an Open CV webcam stream, produce a JPEG thumbnail and then encode it as Base64 (It will then be sent as an MQTT message, but this is not the problem).

My Python "sendimage" function is:

Found code from Github (https://github.com/atulapra/Emotion-detection) for emotion detection. I want to make some changes in it and want to combine with Tkinter for an easy user interaction. Something like this shown in image below. Here I wrote some code for tk window: