Direction field distribution-based fingerprint correction method

Abstract

The invention provides a direction field distribution-based fingerprint correction method, which comprises the following steps of: making statistics on local modes and space distribution in the ridge directions of fingerprints in a cluster learning method, searching for an area similar to a fingerprint mode in a target image in a local mode comparison mode, eliminating the influence of the local modes at irrational positions by combining the spatial position of each local mode, estimating the positions and the directions of the fingerprints, and cutting and correcting the fingerprints according to the information of the positions and the directions. Fingerprints at nonstandard postures are corrected into fingerprints at standard postures to improve fingerprint comparison and query efficiency; all fingerprints can be automatically detected and cut from a background-complex field fingerprint image with a plurality of fingerprints, and the postures of the fingerprints are corrected; and the method has the advantages of high calculation efficiency and high accuracy.

Description

technical field [0001] The invention relates to the field of fingerprint identification, in particular to a fingerprint correction method based on direction field distribution. Background technique [0002] Due to the important properties of fingerprints such as uniqueness, universality and lifetime invariance, the use of fingerprint images for identification has a long history. In the field of public security criminal investigation, since the early 20th century, fingerprints have gradually become one of the most important evidences for law enforcement agencies to arrest and convict criminals. In recent years, the development and maturity of automatic fingerprint recognition technology has made fingerprint recognition widely used in public security criminal investigation, entry and exit, access control systems and authority control of important equipment. [0003] In the field of public security criminal investigation, the main object of fingerprint identification is the fi...

AI Technical Summary

Problems solved by technology

This process is very tedious and time-consuming

On the other hand, when collecting live fingerprints (including various fingerprint recognition applications including public security and civilian use), it is easy to produce fingerprints with non-standard collection postures, that is, the pressed position of the collected fingerprints is not in the center of the image, and the angle is not vertical

To identify these fingerprints with non-standard postures, the fingerprint matching algorithm has to consider various possible spatial transformations, resulting in high computational complexity

[0004] What the present invention aims to solve is the problem of automatic detection and correction of fingerprints under non-standard acquisition postures and complex backgrounds

Existing techniques mainly segment fingerprint regions based on local features such as gray-level variance and gray-level gradient consistency. These features have good performance when the image background is clean, but have little effect when the background is complex, and they can only estimate Whether the local area of ​​the image is a fingerprint, the orientation and center of the entire fingerprint cannot be estimated, and therefore it is impossible to correct a fingerprint with an incorrect pose, and it is impossible to detect a fingerprint from a low-quality crime scene fingerprint

Due to the deficiencies of the existing technology, in the manned fingerprint identification system, the detection and correction of fingerprints are usually done manually by the staff, which is time-consuming and laborious.

In an unattended fingerprint recognition system, fingerprints with incorrect poses can only be solved by fingerprint matching algorithms, which has high computational complexity and easily leads to wrong matches

Images