Fingerprint recognition method based on SIFT

Abstract

The invention discloses a fingerprint recognition method based on SIFT. The method includes following steps: extracting the main characteristic component of fingerprints in a large sample fingerprint database based on SIFT, producing hash values of the main characteristic component via MD5 harsh, and generating a hash table of all the fingerprints in the database; performing the same processing of the fingerprints logged during identity verification, and enabling the fingerprints to generate an MD5 hash value; and comparing the hash value during verification with the hash table, and searching the fingerprint matched with the hash value in the large sample fingerprint database. According to the fingerprint recognition method based on SIFT, local characteristics in fingerprint images are detected and described via SIFT, key characteristic points are searched in the scale space, descriptors of the key characteristic points are extracted, the main characteristic component is extracted via the descriptors of the fingerprints, and the problem of robustness of fingerprint characteristic extraction caused by factors such as finger deformation and rotation etc. during fingerprint characteristic extraction is solved to some extent.

Description

technical field [0001] The invention relates to a fingerprint identification method, in particular to a fingerprint identification method based on SIFT transformation. Background technique [0002] Fingerprint identification technology has the advantages of no loss, no forgetting, uniqueness, invariance, good anti-counterfeiting performance and convenient use. In the case of candidate identity verification in the business field, fingerprint recognition technology mainly includes two steps: fingerprint feature extraction and fingerprint feature matching. [0003] However, because the human finger is a three-dimensional flexible object, the existing main fingerprint recognition algorithms assume that the human finger is a rigid plane object, but when collecting fingerprints, the force, force direction and collection position will be different each time. , resulting in various deformations of the fingerprint, and a large offset in the relative position of the fingerprint featu...

AI Technical Summary

Problems solved by technology

[0003] However, because the human finger is a three-dimensional flexible object, the existing main fingerprint recognition algorithms assume that the human finger is a rigid plane object, but when collecting fingerprints, the force, force direction and collection position will be different each time. , resulting in various deformations of the fingerprint, causing a large shift in the relative position of the fingerprint feature points, making it difficult to accurately locate each feature point

In addition, the surface of the finger is a three-dimensional curved surface, but the acquired fingerprint image is a two-dimensional plane. This transformation from three-dimensional to plane will also cause the deformation of the fingerprint.

More importantly, the fingerprint deformation caused by the above factors is often uncertain and random, and it is difficult to describe it with a definite mathematical model, which causes serious interference to subsequent fingerprint matching.

[0004] Now common fingerprint identification technology mainly has the following disadvantages: the recall rate of fingerprint feature point extraction is low; the accuracy of fingerprint feature point position parameters is low; the completeness and accuracy of fingerprint feature description are not high; the fingerprint matching speed is slow

Images