I don't know if this is the right place to ask this. Is it possible to run deep learning inside a camera and if so, how? I want to be able to take a picture and then use deep learning techniques to do image recognition by using it against hundreds or thousands or millions of other images. Is the only way to do this by taking a picture, sending it to a cloud or something like that and then input it in some model?
Topic deep-learning
Category Data Science
It is possible to do image/object detection in real time using your camera and specialized libraries like Yolo.
See: https://pjreddie.com/darknet/yolo/
However, you will want to train your recognition model before, using objects/images' labelling. This is the most adapted library if you have to deal with millions of pictures. It requires a good PC and GPU, or a GPU cloud service, to learn fast enough.
On the other hand, if you are limited in your hardware, it is always possible to use tiny-yolo and low hardware setup like rasperry-py.
Geeks Mental is a community that publishes articles and tutorials about Web, Android, Data Science, new techniques and Linux security.