Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Finger-vein image quality evaluation method and system based on convolutional neural network

A technology of convolutional neural network and image quality assessment, which is applied in biological neural network models, neural architectures, acquiring/arranging fingerprints/palmprints, etc.

Active Publication Date: 2017-01-11
重庆金融科技研究院 +1
View PDF3 Cites 74 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

First, it overcomes the shortcomings of traditional finger vein image quality assessment methods relying on intuition or prior knowledge to evaluate image quality, and can evaluate image quality more objectively.

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Finger-vein image quality evaluation method and system based on convolutional neural network
  • Finger-vein image quality evaluation method and system based on convolutional neural network
  • Finger-vein image quality evaluation method and system based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] A method of finger vein image quality assessment based on convolutional neural network, such as figure 1 As shown, the method includes the following steps:

[0066] S1: Annotate the quality of finger vein grayscale images in the database, obtain grayscale images with quality labels, obtain low-quality grayscale images and high-quality grayscale images, and obtain veins of grayscale images with quality labels feature, after encoding, a binary image is obtained;

[0067] S2: Establish the binary image training sample set with quality labels obtained in step S1;

[0068] S3: Establish a grayscale image training sample set with quality labels in step S1;

[0069] S4: Convolutional neural network model for extracting grayscale image depth features; said convolutional neural network model includes: input layer, first convolutional layer, first pooling layer, second convolutional layer, second pooling layer , the third convolutional layer, the first fully connected layer, t...

Embodiment 2

[0077] A method for assessing the quality of finger vein images based on a convolutional neural network. The method is different from Embodiment 1 in that the specific method for annotating the quality of the finger vein grayscale images in the database is as follows:

[0078] S11: Selection of registration template image

[0079] Select any image of a finger, use a mature recognition algorithm to extract and match two finger vein images, and calculate the average distance between the image and the remaining images; select the image corresponding to the minimum average distance as the registration of the finger Template image, other images as test images;

[0080] S12: Annotation of image quality

[0081] Calculate the distance between each test image of the same finger and its registered template image to get the intra-class matching score; calculate the distance between each registered template image to get the inter-class matching score; according to the intra-class matchi...

Embodiment 3

[0111] A method for assessing the quality of finger vein images based on a convolutional neural network. The method differs from Embodiment 1 in that step S2 sets up the specific method of the binary image training sample set with quality labels obtained in step S1 as follows: After labeling all test images according to the labeling method in step S1, select 1155 images of 105 fingers as training images, and the remaining images as test images; in the training set, there are a total of 101 low-quality images and 1054 high-quality images . In the test set, there are 110 and 1045 high-quality and low-quality images, respectively. Since there are fewer low-quality than high-quality samples in the training set, various types of imbalances result; to overcome this problem, use the following method to generate low-quality images; for example, to generate synthetic samples of low-quality image x, first from the training set Choose two low-quality images from x 1 and x 2 . Then, u...

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

No PUM Login to View More

Abstract

The invention provides a finger-vein image quality evaluation method and system based on a convolutional neural network. The method includes: labeling the quality of finger-vein gray images, building a training sample set, and using the training sample set to train the convolutional neural network; inputting one optional gray image and a binary image into trained models, selecting the output of second full connection layers in two convolutional neural network models as the depth feature vectors of the input gray image and the binary image; connecting the two depth feature vectors to form a united expression vector, inputting the united expression vector into a support vector machine for training, and using a probability support vector machine to calculate the quality of a predicted finger-vein image. By the evaluation method and system, finger-vein image quality evaluation precision can be increased to a large extent, and the identification performance of a certification system can be improved.

Description

technical field [0001] The invention belongs to the technical field of biological feature recognition, in particular to a method and system for evaluating the quality of finger vein images based on a convolutional neural network. Background technique [0002] With the rapid development of Internet technology and the increase of information security threats, how to effectively identify identities to protect personal and property safety has become an urgent problem to be solved. Compared with traditional authentication methods such as keys and passwords, biometrics based on physiology and behavior are difficult to be stolen, copied and lost. Therefore, biometric authentication technology has been extensively researched and successfully applied in personal identity authentication. Physiologically based biological modalities can be divided into the following two types: 1 external modalities such as face, fingerprint, palm print and iris; 2 internal biological modalities: finger...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04
CPCG06N3/04G06V40/12G06V40/1365G06F18/214
Inventor 秦华锋何希平姚行艳
Owner 重庆金融科技研究院
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com