I am new to facial recognition. I am working on a project in which I have a training database that only contains one image of the person (no duplication of different expressions/lighting etc, as seems to be the case a lot of places online) and then another image is sent to be compared against this database. I can't control the lighting/pose of the people in these pictures.

We have a school database of images and I am trying to make an app where you could take your picture and it would scan the school database and identify you. Currently I am using a PCA script in MATLAB, but it doesn't seem to work that well as it identifies the wrong person.

So I'm wondering is there a better way to do this given my setup?

没有正确的解决方案

许可以下: CC-BY-SA归因
不隶属于 StackOverflow
scroll top