Open Access. Powered by Scholars. Published by Universities.®

Physical Sciences and Mathematics Commons

Open Access. Powered by Scholars. Published by Universities.®

Engineering

Old Dominion University

Electrical & Computer Engineering Theses & Dissertations

Theses/Dissertations

Image fusion

Publication Year

Articles 1 - 2 of 2

Full-Text Articles in Physical Sciences and Mathematics

Fusion Of Visual And Thermal Images Using Genetic Algorithms, Sertan Erkanli Apr 2011

Fusion Of Visual And Thermal Images Using Genetic Algorithms, Sertan Erkanli

Electrical & Computer Engineering Theses & Dissertations

Demands for reliable person identification systems have increased significantly due to highly security risks in our daily life. Recently, person identification systems are built upon the biometrics techniques such as face recognition. Although face recognition systems have reached a certain level of maturity, their accomplishments in practical applications are restricted by some challenges, such as illumination variations. Current visual face recognition systems perform relatively well under controlled illumination conditions while thermal face recognition systems are more advantageous for detecting disguised faces or when there is no illumination control. A hybrid system utilizing both visual and thermal images for face recognition …


Neighborhood Defined Feature Selection Strategy For Improved Face Recognition In Different Sensor Modalitie, Satyanadh Gundimada Jan 2007

Neighborhood Defined Feature Selection Strategy For Improved Face Recognition In Different Sensor Modalitie, Satyanadh Gundimada

Electrical & Computer Engineering Theses & Dissertations

A novel feature selection strategy for improved face recognition in images with variations due to illumination conditions, facial expressions, and partial occlusions is presented in this dissertation. A hybrid face recognition system that uses feature maps of phase congruency and modular kernel spaces is developed. Phase congruency provides a measure that is independent of the overall magnitude of a signal, making it invariant to variations in image illumination and contrast. A novel modular kernel spaces approach is developed and implemented on the phase congruency feature maps. Smaller sub-regions from a predefined neighborhood within the phase congruency images of the training …