Fingerprint image splicing method based on regression line characteristic and TPS deformation model

Abstract

The invention belongs to the digit image processing technical field, and discloses a fingerprint image splicing method based on regression line characteristics and a TPS deformation model; the methodcomprises the following steps: respectively extracting detail points of two to-be-spliced small area fingerprint images, carrying out registering for the detail points pair after pair, thus obtainingthe detain point pair with the highest similarity fraction; calculating the rotary translation parameter for the primary registering, thus obtaining the primarily spliced fingerprint image; solving arefinement image of the two to-be-spliced small area fingerprint images; using a N neighborhood block method to search a matching regression line of an overlapping area of the refinement image, and searching the matched regression line pair; introducing the TPS deformation model, correcting elastic deformation of the fingerprint image in the regression line pair characteristic layer, and carryingout secondary registering so as to obtain the final result of the secondarily spliced fingerprint image. The method uses the detail points for the primary registering, and uses the N neighborhood block method to search matching regression lines of the overlapping area, thus reducing splicing errors caused by wrongly matched detail points.

Description

technical field [0001] The invention belongs to the technical field of digital image processing, and in particular relates to a fingerprint image splicing method and an automatic fingerprint recognition system based on ridge features and TPS deformation models. Background technique [0002] Among many biometric identifications, fingerprint-based authentication is an important biometric technology, which is widely used in military and civilian fields. Due to the need to fully consider reliability and security in practical applications, fingerprint identification has been used in the past In recent years, it has received more and more attention. Another reason for the popularity of fingerprint recognition is that the price of fingerprint sensors is relatively low, and they can be easily integrated into PC keyboards, mobile phones and various smart cards. In the field of fingerprint identification, fingerprint minutiae is the most distinctive and reliable feature, and it is al...

AI Technical Summary

Problems solved by technology

[0004] 1. The small-area fingerprint image contains a small number of minutiae points, and the traditional minutiae point matching algorithm and splicing algorithm do not introduce ridge features, and the recognition accuracy is not high;

[0005] 2. The traditional minutiae splicing algorithm does not correct the errors caused by the nonlinear distortion and elastic deformation of fingerprints, which makes the splicing effect poor

[0006] To sum up, the existing technology does not take into account the deformation problem in the process of fingerprint collection, and uses minutiae points as the only information for fingerprint registration or stitching, resulting in poor stitching effect. When the stitched image is used as a template for subsequent fingerprint recognition , the recognition rate is low

Images