Industrial production surety factor increasing by a system of fingerprint verification

Abstract

The article describes a new method of a fingerprint verification. A research purpose has been a verification of integral transformations applying possibilities with help of Fourier and Fourier-Mellin transformation as a tool for fingerprints images verification. The proposed method does not require broad preprocessing, it eliminates partly inaccurate finger place on a sensor (shift, rotation), it compensates partly fingerprint deformations (scale change, skin elasticity) and lower fingers quality (too dry fingers), it enables automatic processing and evaluation without an operator input. The proposed method, using a registration and comparative criterion of modified phase correlation can take up 91.7 % of the right fingerprints and reject just 8.3 % of them. The fingerprint verification can be used for following and controlling of technological processes; expensive or dangerous equipments, technologies or property protection from illegitimate using or misusage, and for an authentication of entry into buildings.

Robust fingerprint recognition approach based on diagonal slice of polyspectra in the polar space

“…This problem can improve efficiency by using FMT [9] that is based on the properties of the image amplitude spectrum. Elena and Pavol also described a fingerprint verification method with the help of Fourier and FMT without broad preprocessing [12]. But, also the performance is degrades if the query and reference image contains much noise and that too of different types.…”

“…The problem of fingerprint matching has been extensively studied and numerous algorithms have been proposed. These algorithms can be classified as correlation-based [1][2][3][4][5][6][7][8][9][10][11][12][13], minutiae-based [15][16][17][18] and frequency-based [19,20] approaches. Correlation-based matching is the most popular and widely used technique, being the basis of the fingerprint comparison.…”

Low-quality fingerprint recognition using a limited ellipse-band-based matching method

“…The WFMT feature was further processed by a random sampling scheme and binarization scheme to get a fixed-length binary feature vector called BioCode [17]. Elena and Pavol also described a fingerprint verification method with the help of Fourier and Fourier-Mellin transformation without broad preprocessing [18]. In Ref.…”

“…The image-based method usually extracts features directly from the gray-level image of the fingerprint [14][15][16][17][18][19][20]. An efficient image-based method is the phase-based method.…”

Robust fingerprint recognition approach based on diagonal slice of polyspectra in the polar space

“…The problem of fingerprint matching has been extensively studied and numerous algorithms have been proposed. These algorithms can be classified as correlation-based [3,4,5,6,7,9,8,10,11,12,13,14,15], minutiae-based [17,18,19,20] and frequency-based [21,22] approaches. Correlation-based matching is the most popular and widely used technique, being the basis of the fingerprint comparison.…”