|
« Back
Classifier Combination in Biometrics
There is an increased interest in the combination of biometric matchers for person
verification. Matchers of different modalities can be considered as independent two
class classifiers. This work tries to answer the question of whether the assumption of
classifier independence could be used to improve the combination method. The combination
added error was introduced and used to evaluate performance of various combination methods.
The results show that using independent assumption for score density estimation indeed improves
combination performance. At the same time it is likely that generic classifier like SVM will still
perform better. The magnitudes of experimentally evaluated combination added errors are relatively,
which means the choice of the combination method is really not important.
Publications:
-
Tulyakov and Govindaraju, "Using Independence Assumption to Improve Multi-modal Biometric Fusion", 6th International Conference on Multile Classifer Systems (MCS 2005)[pdf..]
-
Tulyakov and Govindaraju, "Combining Matching Scores in Identification Model", ICDAR 2005[pdf..]
|
|
 Human iris patterns have a high degree of randomness and uniqueness.
|
