The Shape of Computer Vision

A focal length classifier

Double Gauss lens designs 1964–1977. Image credit Wikimedia Commons CC BY-SA 3.0

Does machine vision apprehend the world through a specific lens? And if so, which one? In this project I set out to design a deep learning classifier that is purposefully blind to what photographs are of; a type of machine vision that cares nothing about recognising objects, people or scenes, and is instead programmed to learn only about how photographs were made, more specifically the lenses used in their making.

Related