A neural network fingerprint segmentation method
Ademir Marques, Alexander Thome · 2005
In this work a computational segmentation method, applied to the detection of the region of interest on fingerprint images, is proposed. The approach is based on the hypothesis that a small fingerprint fragment resembles a two-dimension sinusoid function. Therefore, its Fourier spectrum must present a well-defined pattern. Since neural networks are very suitable for solving pattern recognition problems, an MLP network is used to discriminate the regions containing fingerprint fragments from the rest of the image. The proposed model is tested over fingerprint images obtained from the NIST special database 27, and the obtained results demonstrate that the approach works reasonably well for images with different noise and contrast levels.