A small-area fingerprint comparison method based on deep learning
A deep learning, small-area technology, applied in the field of small-area fingerprint comparison, can solve the problem that the performance of small-area fingerprint comparison cannot meet the actual needs of use.
Active Publication Date: 2020-08-11
HANGZHOU JINGLIANWEN TECH
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] In order to overcome the fact that the performance of the existing fingerprint comparison method for small-area fingerprint comparison cannot meet the actual use requirements, the present invention proposes a small-area fingerprint comparison based on deep learning that is effective for small-area fingerprint comparison and has good reliability. method
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
[0041] The present invention will be further described below in conjunction with the accompanying drawings.
[0042] refer to Figure 1 ~ Figure 4 , a small-area fingerprint comparison method based on deep learning, comprising the following steps:
[0043] 1) Extraction of relevant information about detail feature points of small-area fingerprint images: use traditional algorithms to find the position, direction, quality and other information of detail feature points (endpoints, bifurcation points) in small-area fingerprints;
[0044] 2) ROI interception: according to the detailed feature point position and direction information obtained in step 1), with the feature point as the center, the image is rotated and normalized according to the direction of the feature point, and a small block B with a size of 64×64 is intercepted;
[0045] 3) Convolutional network training: The network model of the convolutional neural network adopts a deep residual network, and uses the Caffe fra...
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
A method for comparing small-area fingerprints based on deep learning, comprising the following steps: 1) finding the orientation and direction information of the feature points in the small-area fingerprint; 2) according to the detailed feature point orientation and orientation information obtained in step 1), With the feature point as the center and the direction of the feature point as the X axis, the image is rotated and normalized, and a small block B of a set size is intercepted; 3) Convolutional network training: the network model of the convolutional neural network adopts deep residual Network, using the Caffe framework to train the training samples; 4) Semantic feature extraction; 5) Fingerprint registration: During the registration process, the user needs to cooperate with the corresponding instructions to register, and the registration template is composed of the feature points of the registered fingerprint image; 6) Fingerprint comparison Pair: The comparison score is determined by the mean of several values with the highest similarity between the image to be matched and the registration template. The present invention proposes a small-area fingerprint comparison method based on deep learning, which is effectively applicable to small-area fingerprint comparison and has good reliability.
Description
technical field [0001] The invention relates to technical fields such as neural network, image processing, pattern recognition, and fingerprint comparison, in particular to a comparison method for small-area fingerprints, which is suitable for identity authentication of smart mobile devices, access control systems, notebooks and other devices. Background technique [0002] With the advancement of science and technology, the traditional identity verification methods relying on citizen ID cards, work permits, and personal passwords have been unable to meet people's increasing needs for security and convenience due to their own shortcomings and deficiencies. And born. Biometric technology belongs to the category of pattern recognition that utilizes the inherent biological and behavioral characteristics of the human body for identity authentication. With the continuous improvement of image processing and pattern recognition technology, fingerprint recognition technology is wide...
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): G06K9/00G06K9/32G06K9/62G06N3/08
CPCG06N3/084G06V40/1347G06V40/1365G06V10/25G06F18/214
Inventor 张永良周冰祝江威姜晓丽
Owner HANGZHOU JINGLIANWEN TECH