Extracting Features from the image manually

Question

I am working on image classification problem. How to find out specific features from the image manually that will help to build a DNN? Consider an image of a man talking on phone while driving for classification as distracted.

Answer 1

You don't do this. Having a good feature extractor is why we take DNNs in the first place

Also: you forgot to look to https://www.kaggle.com/c/state-farm-distracted-driver-detection