Font Size: a A A

Study On The Analyzability Of Fingerprint Morphological Feature Patterns

Posted on:2020-09-02Degree:MasterType:Thesis
Country:ChinaCandidate:L W JinFull Text:PDF
GTID:2428330575991188Subject:Communication and Information System
Abstract/Summary:PDF Full Text Request
Fingerprint recognition technology is the most widely used biometric technology.As the capacity of fingerprint database increases,the accuracy of fingerprint recognition system decreases and the speed decreases.The fingerprint feature extraction algorithm based on morphological operation fails to fully consider the internal relationship between fingerprint morphological features,and the accuracy of different types of fingerprint morphological features obtained is inconsistent,so it cannot be applied to the same fingerprint recognition system.This paper studies the analyzability of fingerprint morphological feature patterns and proposes to extract fingerprint morphological features from the perspective of signal analysis.The method proposed in this paper considers the relationship between fingerprint features and ensures the accuracy of fingerprint morphological features.Fingerprint images are similar to two-dimensional AM-FM signals,and fingerprint images can be analyzed.The phase of the fingerprint signal determines the minutiae and ridge information in the fingerprint image,where the phase gradient is the instantaneous frequency.In the fingerprint image,there is a relationship between different fingerprint morphological features,the direction of the instantaneous frequency is normal to the local orientation of the fingerprint,the magnitude of the instantaneous frequency is equal to the local ridge frequency of the fingerprint,and the singularity in the instantaneous frequency is the same as the minutiae in the fingerprint image.In this paper,the original fingerprint information is retained to ensure the accuracy of fingerprint features extracted.The following steps will be used to extract a variety of reliable fingerprint morphological features.Firstly,the first step is to establish a fingerprint mathematical model;The second step is to use different filters to remove the irrelevant variables in the fingerprint signal;The third step is to use Riesz transform to analyze the phase information;Finally,the instantaneous frequency is constructed to extract various fingerprint morphological features.The method proposed in this paper can not only extract multiple fingerprint morphological features at the same time to ensure the accuracy of fingerprint morphological features,but also reduce the time cost of extracting fingerprint morphological features.
Keywords/Search Tags:fingerprint feature extraction, two dimensional AM-FM signal, signal analysis, Riesz transform
PDF Full Text Request
Related items