Title :
Fingerprint ROI segmentation using fourier coefficients and neural networks
Author :
Branka Stojanovi?;Aleksandar Ne?kovi?;Oge Marques
Author_Institution :
Vlatacom d.o.o, Milutina Milankovi?a 5, 11070 Belgrade, Serbia
Abstract :
This paper presents a novel method for fingerprint ROI (region of interest) segmentation using Fourier coefficients computed over non-overlapping image segments and used to train a neural network. Experimental results, obtained using a publicly available test database of 200 fingerprint image, demonstrate that this method outperforms a pixel-based approach, in all three figures of merit.
Keywords :
"Image segmentation","Fingerprint recognition","Artificial neural networks","Training","Databases","Image matching"
Conference_Titel :
Telecommunications Forum Telfor (TELFOR), 2015 23rd
DOI :
10.1109/TELFOR.2015.7377512