Title :
Hand geometry identification system performance
Author :
Ferrer, Miguel A. ; Fàbregas, Joan ; Faundez, Marcos ; Alonso, Jesus B. ; Travieso, Carlos
Author_Institution :
CeTIC, ULPGC, Spain
Abstract :
The effect of changing the image resolution over a biometric system based on hand geometry is analyzed in this paper. Image resolution is progressively diminished from an initial 120 dpi resolution up to 24 dpi. The robustness of the examined system is analyzed with 2 databases and two identifiers. The first database acquires the images of the hand underneath whereas the second database acquires the images over the hand. The first classifier identifies with a multiclass support vector machine whereas the second classifier identifies with a neural network with error correction output codes. The four experiments show that an image resolution of 72 dpi offers a good trade-off between performance and image resolution for the 15 geometric features used.
Keywords :
biometrics (access control); error correction codes; image classification; image coding; image resolution; neural nets; support vector machines; biometric hand-recognition application; biometric system; error correction output code; hand geometry identification system; image resolution; multiclass support vector machine classifier; neural network classifier; Biometrics; Data analysis; Geometry; Image analysis; Image databases; Image resolution; Robustness; Spatial databases; Support vector machines; System performance; Hand-geometry; biometrics; component; neural networks; resolution;
Conference_Titel :
Security Technology, 2009. 43rd Annual 2009 International Carnahan Conference on
Conference_Location :
Zurich
Print_ISBN :
978-1-4244-4169-3
Electronic_ISBN :
978-1-4244-4170-9
DOI :
10.1109/CCST.2009.5335545