Open AccessOptimization method for non-cooperative iris recognition task using Daugman integro-differential operator
Author(s) -
Ivan Petrov,
Н. Н. Минакова
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1615/1/012007
Subject(s) - operator (biology) , differential (mechanical device) , differential operator , mathematics , differential evolution , iris (biosensor) , computer science , mathematical optimization , artificial intelligence , mathematical analysis , biometrics , biology , physics , genetics , repressor , transcription factor , gene , thermodynamics
We considered the issues arising when Daugman’s integrodifferential operator is used to localize iris edges. Daugman’s integro-differential operator is a widely common method to localize the iris, however, problems of the operator optimization poorly presented in the literature. The article considers existing methods of optimization of the operator applied at the iris recognition step. Based on the provided research we proposed using Nelder-Mead and Differential Evolution methods to optimize the integro-differential operator. The problems of the iris localization and their solving methods were considered. The article focuses attention on non-cooperative iris recognition. The very general boundary conditions based on iris’s anatomy which are not dependent on captured image properties were defined. The results of the comparative analysis of the accuracy and performance of selected optimization methods of Daugman’s integrodifferential operator were presented at the experimental results chapter. It was found that the Differential evolution optimization method gives fine performance and correctness. It was concluded that the Differential evolution is expedient as Daugman’s integro-differential operator optimization method.