Title :
Fingerprint image enhancement based on nonlinear anisotropic reverse-diffusion equations
Author :
Hao, Yufeng ; Yuan, Chunwei
Author_Institution :
Dept. of Biomedical Eng., Southeast Univ., Nanjing, China
Abstract :
We present an approach based on nonlinear anisotropic reverse diffusion equations (NARDE) to enhance noisy fingerprint images. After studying the nonlinear diffusion equations to denoised images and nonlinear reverse diffusion process in nature, a new scheme is advanced with new selection criteria of optimal stopping time. Experiments were carried out and showed the high efficiency of the noise removing sharpening scheme and the role of selection criteria on noisy fingerprint images.
Keywords :
image denoising; image enhancement; medical image processing; denoised images; image enhancement; noisy fingerprint images; nonlinear anisotropic reverse-diffusion equations; optimal stopping time; Anisotropic magnetoresistance; Diffusion processes; Filtering; Fingerprint recognition; Image enhancement; Image matching; Image processing; Nonlinear equations; Partial differential equations; Wiener filter; Nonlinear anisotropic reverse-diffusion equations; fingerprint images enhancement;
Conference_Titel :
Engineering in Medicine and Biology Society, 2004. IEMBS '04. 26th Annual International Conference of the IEEE
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-8439-3
DOI :
10.1109/IEMBS.2004.1403486
