DEVELOPMENT OF MACHINE LEARNING METHOD WITH BIOMETRIC PROTECTION WITH NEW FILTRATION METHODS

Biometric images were processed and filtered by a newly developed Ateb-Gabor wavelet filter. Identification of biometric was performed machine learning methods. The Gabor filter based on Ateb functions is effective for filtering because it contains generalizations trigonometric functions. Developed transform function. It shown that the function depends seven parameters, each which makes significant changes in results images. A study performed. graphical dependences are constructed. introduction transforms reduces complexity calculations simplifying reducing time. algorithms calculating evaluated. allows you to change intensity entire image, certain ranges, thus areas image. this property should have, minions be contrasting clear. have ability two rational which, turn, will allow more flexible control filtering. properties investigated, as well possibility changing amplitude function, oscillation frequency numerical values ​​of By using parameters can get much wider range shapes sizes, expands number possible options. You also implement once filtering, taking into account direction minutes reliably determine sharpness edges, rather than batocrates. reliability tested basis NIST Special Database 302, good filtration shown. This confirmed comparison experiment between Wavelet-Gabor measurement PSNR signal-to-noise ratio.