“Poor Man” Vote with M-ary Classifiers. Application to Iris Recognition

Abstract

Achieving good performance in biometrics requires matching the capacity of the classifier or a set of classifiers to the size of the available training set. A classifier with too many adjustable parameters (large capacity) is likely to learn the training set without dificulty but be unable to generalize properly to new patterns. If the capacity is too small, the training set might not be learned without appreciable error. There is thus advantage to control the capacity through a variety of methods involving not only the structure of the classifiers themselves, but also the property of the input space. Ths paper proposes an original non parametric method to combine optimaly multiple classifier responses. Highly favorable results have been obtained using the above method.