Genetic & Evolutionary Biometrics: Feature extraction from a Machine Learning perspective

Genetic & Evolutionary Biometrics (GEB) is a newly emerging area of study devoted to the design, analysis, and application of genetic and evolutionary computing to the field of biometrics. In this paper, we present a GEB application called GEFE ML (Genetic and Evolutionary Feature Extraction - M...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2012 Proceedings of IEEE Southeastcon s. 1 - 7
Hlavní autoři: Shelton, J., Alford, A., Small, L., Leflore, D., Williams, J., Adams, J., Dozier, G., Bryant, K., Abegaz, T., Ricanek, K.
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.03.2012
Témata:
Biometrics
Complexity theory
Cross Validation
Estimation of Distribution Algorithm
Feature Extraction
FETs
Genetic & Evolutionary Computation
Iron
Local Binary Pattern
Optimization
Vectors
ISBN:9781467313742, 1467313742
ISSN:1091-0050
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Genetic & Evolutionary Biometrics (GEB) is a newly emerging area of study devoted to the design, analysis, and application of genetic and evolutionary computing to the field of biometrics. In this paper, we present a GEB application called GEFE ML (Genetic and Evolutionary Feature Extraction - Machine Learning). GEFE ML incorporates a machine learning technique, referred to as cross validation, in an effort to evolve a population of local binary pattern feature extractors (FEs) that generalize well to unseen subjects. GEFE ML was trained on a dataset taken from the FRGC database and generalized well on two test sets of unseen subjects taken from the FRGC and MORPH databases. GEFE ML evolved FEs that used fewer patches, had comparable accuracy, and were 54% less expensive in terms of computational complexity.
ISBN:9781467313742
1467313742
ISSN:1091-0050
DOI:10.1109/SECon.2012.6197069