Fingerprint image computer automatic mending method based on direction fields

Abstract

The invention discloses a fingerprint image computer automatic mending method based on direction fields. The method includes inputting fingerprint images to be mended, and dividing polluted areas; then mending the images; and reversing image processing information based on results processed by modules. According to the method, gray information can be transmitted into areas to be mended along local fixing direction of representation ridge line direction, credible mending fingerprint images are provided, and fake characteristics are effectively reduced. The method serves as a pre-processing method in fingerprint identification systems, so that identification accuracy of fingerprint identification systems is facilitated to be improved. Mending and recovering of fingerprint images are good for case detections and judicial identification, particularly in cases when the quality of fingerprints collected on site in criminal investigation and judicial systems is not good.

Description

technical field [0001] The invention relates to the fields of image processing, pattern recognition and information processing; in particular, it relates to a method for repairing images of fingerprint images and texture images based on direction fields and partial differential equations. technical background [0002] Compared with traditional authentication technology, using fingerprint as identity authentication has obvious advantages. The uniqueness and stability of fingerprint make it an effective means of identity authentication. In recent years, the research on automatic fingerprint identification and authentication has become a hot spot in the field of pattern recognition and biometric authentication. And produced a lot of algorithms and automatic fingerprint identification systems, which have been widely used in banking, insurance, public security and other industries. However, there are still some problems in the current fingerprint recognition algorithm itself: th...

AI Technical Summary

Problems solved by technology

However, the current fingerprint recognition algorithm itself still has some problems: the quality of the input fingerprint image is too high, and some fingerprint images with large noise, weak texture information and incomplete fingerprints cannot be recognized.

[0006] (1) Due to the lack of geometric information of the direction field, the common image repair model cannot give satisfactory repair results for fingerprint images; or although the geometric information of the direction field is introduced, for fingerprint images, when repairing The following different erroneous results will appear: different ridges are connected together; uniform gray values ​​​​are filled in when patching the area to be patched, and ridges and valleys cannot be distinguished; ridges cannot be purposefully connected and many more

[0007] (2) Gabor filtering: Gabor filtering is a commonly used method for fingerprint image preprocessing. It can repair small defects in fingerprint images, but when the length and width of the area to be repaired are much larger than the width of the ridge line, Gabor filtering cannot be effective. repair

Images