I'm developing an AI program that can be used to detect emotions of people's faces in images, and I've stumbled across OpenCV which would be perfect for the face detection stage of the program. The only problem is that I need to be able to access the feature vector that the Local Binary Patterns classifier produces so that I can feed this vector to the AI as input data.
So the process would be:
- Image presented to LBP classifier
- LBP classifier produces feature vector for image
- Feature vector passed to AI for processing
- AI detects emotion using feature vector
Is there any way to do this? It doesn't matter whether this is done in Java or Python, I just need a way of extracting the feature vector.
Alternatively, is there a different way I can process the pixel content of the images of people's faces so that I have data I can pass to an AI?