KeyLemon Blog

Sébastien Marcel - Senior Research Scientist
Sébastien Marcel
Senior Researcher at Idiap Research Institute in Biometric Person Recognition and Man Machine Interfaces. Sébastien is working on face recognition for more than 10 years and will share its expertise in writing posts in this blog. To have more information consult his personal page

Features and Classifiers

In this new post, I will introduce 2 concepts that are key elements in all face processing algorithms: features and classifiers. Let's start with some definitions: Features "In pattern recognition, features are the individual measurable heuristic properties of the phenomena being observed. Choosing discriminating and independent features is key to any pattern recognition algorithm being successful in classification. Features are usually numeric, but structural features such as strings and graphs are used in syntactic pattern recognition." (Wikipedia) Classifiers "A classifier is a sort of a function that provides a tagged class as an ...

What is face recognition ?

In this first post, I just want to clarify the terminology. This is really important otherwise we simply don't know what we are talking about ! Many terms can be found on the web and are used incorrectly. Typically we found ...

Preamble of the new category : Face recognition by an expert

Face recognition has been an active research area for more than 30 years and different systems are now capable of correctly recognizing people's faces under specific environments (near frontal faces and controlled imaging conditions). This explains the presence of more and more face recognition applications for your personal computers. KeyLemon asked Sébastien Marcel to animate a new entry on his blog and hopes that you will find information about face recognition. Sébastien will try to post here on a regular basis some general information but also more detailed information about face ...