University of Twente Student Theses

Login

Robust estimation of biometric data

Kuijper, Guido (2017) Robust estimation of biometric data.

[img] PDF
433kB
Abstract:This study presents the design of a robust estimator Ĉ to apply on biometric data analysis involving facial recognition. This functional estimates the covariance matrix of a multivariate Gaussian distribution by seperately estimating the matrix elements. It is first mathematically derived, then classified by means of its efficiency at Gaussian distributions and finally applied to both synthetic and real biometric data. The synthetic experiments show the Ĉ-estimator performs in between the sample covariance and the MCD estimator. The test with the real data shows clear improvement of the robust Ĉ-estimator as it was able to link two faces for which the sample covariance estimator was not able to.
Item Type:Essay (Bachelor)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:31 mathematics, 53 electrotechnology
Programme:Electrical Engineering BSc (56953)
Link to this item:https://purl.utwente.nl/essays/73245
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page