Modular Neural Network with Fuzzy Response Integration and Its Optimization Using Genetic Algorithms for Human Recognition Based on Iris, Ear and Voice Biometrics

  • Patricia Melin
Part of the Studies in Computational Intelligence book series (SCI, volume 389)

Abstract

In this chapter we describe the application of a Modular Neural Network (MNN) for iris, ear and voice recognition for a database of 77 persons. The proposed MNN architecture with which we are working consists of three modules; iris, ear and voice [80]. Each module is divided in other three sub modules. Each sub module contains different information, which, the first 26 individuals are considered in module 1, the following 26 individuals in module 2 and the last 25 in module 3. We considered the integration of each biometric measure separately. Later, we proceed to integrate these modules with a fuzzy integrator [59]. Also, we performed optimization of the modular neural networks and the fuzzy integrators using genetic algorithms, and comparisons were made between optimized results and the results without optimization.

Keywords

Genetic Algorithm Membership Function Hide Layer Gradient Descent Adaptive Learning 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Patricia Melin

    There are no affiliations available

    Personalised recommendations