Ask Your Question

Accuracy of Fisherfaces

asked 2013-12-26 19:46:50 -0600

Jyo gravatar image

I'm working on Gender Classification with Fisherfaces right now, I'll need to add on to include Age Estimation and Emotion Detection. The accuracy of Fisherfaces right now is around 70-75% and I heard that adding more training images would actually help.

I intend to increase the amount of training images, but can I ask if races matter? For example, do I need to include faces of Asians to increase the accuracy of detecting an Asian's gender accurately? If so, are there any recommendations for any face databases with a wide range of unique individuals, different races, ages and emotions?

edit retag flag offensive close merge delete

2 answers

Sort by ยป oldest newest most voted

answered 2013-12-27 04:27:00 -0600

I am not familiar with the fisherfaces method, but it is pretty obvious that using a more diverse training set would help the performance of your application. Each race has its unique features so you'd gain by teaching them to your classifier.

There are dozens of face datasets on the web, but finding one that is labelled with age and gender might not be easy. You might end up having to label a dataset yourself. Start by browsing this website, it has a collection of different face datasets.

Good luck.

edit flag offensive delete link more

answered 2014-02-14 17:44:51 -0600

Fisherfaces (and also Eigenfaces) is a basic algorithm and you can't ask for a good performance from it when doing the gender, age, face, expressions, and race classifications. Even if you have a very big training dataset with images captured under different conditions. So I suggest you to use another approach for that purpose, for example to use a facial feature extraction method, instead of spending time to get a bigger training set.

edit flag offensive delete link more

Question Tools


Asked: 2013-12-26 19:46:50 -0600

Seen: 1,040 times

Last updated: Feb 14 '14