{"id":39,"date":"2020-08-11T10:03:39","date_gmt":"2020-08-11T14:03:39","guid":{"rendered":"https:\/\/www.macloo.com\/ai\/?p=39"},"modified":"2020-08-24T12:07:45","modified_gmt":"2020-08-24T16:07:45","slug":"how-machines-see","status":"publish","type":"post","link":"https:\/\/www.macloo.com\/ai\/2020\/08\/11\/how-machines-see\/","title":{"rendered":"How machines \u2018see\u2019"},"content":{"rendered":"\n

I am fascinated by image recognition. I read about how ImageNet changed the whole universe of machine “vision” in 2009 in the excellent book Artificial Intelligence: A Guide for Thinking Humans<\/a>, but I’m not going to discuss ImageNet in this post. (I will get to it eventually.)<\/p>\n\n\n\n

To think about how a machine sees<\/em> requires us first to think about human eyes vs. cameras. The machine doesn’t have a biological eyeball and an optic nerve and a brain. The machine might <\/em>have one or more cameras to allow it to take in visual information.<\/p>\n\n\n\n

Whether the machine has cameras or not, the images it receives are the same: digital images, made up entirely of pixels. This is true even if the visual inputs are video. The machine will need to sample that video, taking discrete frames from it to process and analyze.<\/p>\n\n\n\n

So the first thing to absorb, as you begin to understand how a machine sees, is that it receives a grid of pixels. If it’s video, then there are a lot of separate grids. If it’s one still image, there is one grid. And how does the machine process that grid? It analyzes the differences<\/em> between groups<\/em> of pixels.<\/p>\n\n\n\n

This 4-minute video, from an artist and programmer named Gene Kogan<\/a>, helped me a lot.<\/p>\n\n\n\n

\n