Fingerprint Pseudo-nucleus Detection Method Based on Global Information of Orientation Field
A technology of global information and direction field, applied in the acquisition/organization of fingerprints/palmprints, instruments, characters and pattern recognition, etc., can solve the problem of high false detection rate of singular point detection, and achieve the effect of low computational cost
Active Publication Date: 2018-08-10
SHANGHAI ZAIDE INFORMATION SCI & TECH
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] The purpose of the present invention is to solve the problem of high false detection rate of singular point detection in the existing fingerprint identification technology, and proposes a false nuclear point detection method based on the global information of the direction field
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0029] Below in conjunction with embodiment the present invention is further described.
[0030] Such as figure 1 with 2 As shown, the pseudo-nucleus detection method based on the global information of the direction field, specifically includes the following steps:
[0031] Step 1, obtain the pixel-level direction field O of the fingerprint image with the gradient method;
[0032] Step 2. Use the Poincaré index method to extract the position C of each coarse kernel point in the direction field O i (cx i ,cy i );
[0033] Step 3, carry out fingerprint segmentation with short-time Fourier transform method, obtain the foreground area I of fingerprint;
[0034] Step 4. Calculate the main value θ of the argument angle in the opening direction of the coarse kernel point i ,details as follows:
[0035]
[0036] (Formula 2)
[0037] In formula 1, O ref (x, y) represents the reference direction field block of the kernel point, the size is 25×25, calculated by formula 2;...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a fingerprint pseudo-nucleus point detection method based on the global information of the direction field. The specific steps of the present invention are as follows: use the gradient method to obtain the pixel-level direction field O of the fingerprint image; use the Poincaré index method to extract the position of each coarse kernel point in the direction field O; use the short-time Fourier transform method to perform fingerprint Segment to obtain the foreground area I of the fingerprint; use the existing algorithm to calculate the main value of the argument angle θi of the opening direction of the coarse kernel point; In area I, find the corresponding discriminant area Ai; calculate the corresponding discriminant feature Fcore according to the direction field in the Ai area and the main value θi of the opening direction of the coarse core point; calculate the discriminant corresponding to each coarse core point The feature Fcore judges the coarse core points with Fcore<1 as false core points and removes them to get the final result. The present invention utilizes the global information of the direction field to further reduce the false detection rate of nuclear point detection.
Description
technical field [0001] The invention belongs to the technical field of biological feature identification and information security, and in particular relates to a fingerprint pseudo-nucleus point detection method based on the global information of an orientation field. Background technique [0002] As a relatively mature biometric identification technology, fingerprint identification is widely used in financial security, access control, employee attendance and other fields. Although after decades of research, the performance of the automatic fingerprint identification system is becoming more and more perfect, but there are still some difficult problems that have not been solved, and singular point detection is one of them. Singularity points are divided into core points and triangle points, which are important global features of fingerprints and are often used for fingerprint classification and fingerprint template alignment. Misdetection of singular points will directly cau...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00
CPCG06V40/12
Inventor 叶学义刘一锐王秋华夏经文汪云路
Owner SHANGHAI ZAIDE INFORMATION SCI & TECH