Self-adaptive fingerprint identification method and system based on neural network
A neural network, fingerprint recognition technology, applied in character and pattern recognition, acquisition/organization of fingerprints/palmprints, instruments, etc., can solve the problems of large deformation, lack of feasibility of fingerprint recognition methods, and low fingerprint recognition rate.
Inactive Publication Date: 2020-02-07
东营职业学院
View PDF0 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] The present invention provides a neural network-based self-adaptive fingerprint identification method and system to solve the problem in the prior art that the non-linear deformation of the fingerprint image is radial and the deformation in a certain area is larger. There is a problem of low fingerprint recognition rate due to the lack of feasibility of fingerprint recognition methods
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
[0060] This embodiment: as figure 1 , 2 As shown, an adaptive fingerprint recognition method based on neural network, including:
[0061] Preprocessing the collected fingerprint image, extracting N feature points S101 from the preprocessed fingerprint image;
[0062] Converting the extracted N feature points into N polar coordinate feature points through a polar coordinate conversion function S102;
[0063] Sorting the N polar coordinate feature points according to the feature polar angle increment S103;
[0064]According to the sequence after sorting, the coordinates and directions of the N feature points are input into the neural network S104 in turn, the input neural network is trained S105, and the trained neural network outputs the result of fingerprint matching S106.
[0065] Due to the preprocessing of the collected fingerprint image, N feature points are extracted from the preprocessed fingerprint image; the extracted N feature points are converted into N polar coor...
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 belongs to the technical field of fingerprint identification, in particular to a self-adaptive fingerprint identification method and system based on a neural network. The self-adaptive fingerprint identification method comprises the following steps: sorting N polar coordinate feature points in an ascending way according to a feature polar angle; according to post-sorting sequence, sequentially inputting the coordinates and directions of the N feature points into the neural network; training an input neural network; and outputting a fingerprint matching result by the trained neural network. The self-adaptive fingerprint identification method solves the problem of low fingerprint identification rate caused by lack of feasibility of an existing fingerprint identification methoddue to the fact that the nonlinear deformation of the fingerprint image is radial and the deformation change of the fingerprint image in a certain area is large in the prior art, and has the beneficial technical effect of providing feasibility for improving the fingerprint identification rate.
Description
technical field [0001] The invention belongs to the technical field of fingerprint identification, in particular to a neural network-based self-adaptive fingerprint identification method and system. Background technique [0002] Artificial neural network is a research hotspot in the field of artificial intelligence since the 1980s. It abstracts the human brain neuron network from the perspective of information processing, establishes a simple model, and forms different networks according to different connection methods. In engineering and academia, it is often referred to as neural network or neural network for short. Neural network is A computing model is composed of a large number of nodes (or neurons) connected to each other. Each node represents a specific output function, called the activation function, and the connection between each two nodes represents a weighted value for the signal passing through the connection, called the weight, which is equivalent to the memor...
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 Applications(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/1347G06V40/1365G06F18/214
Inventor 聂仁凯
Owner 东营职业学院