A vein recognition method based on a reinforcement learning algorithm optimized convolution neural network

A convolutional neural network and vein recognition technology, applied in the field of vein recognition, can solve problems such as difficulties

Inactive Publication Date: 2018-12-18
MELUX TECH CO LTD
View PDF8 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, there is still very little experience in network structure design that can be referred to in the field of vein recognition technology, and it is difficult to perform further optimization on the basis of the original model.

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
  • A vein recognition method based on a reinforcement learning algorithm optimized convolution neural network
  • A vein recognition method based on a reinforcement learning algorithm optimized convolution neural network
  • A vein recognition method based on a reinforcement learning algorithm optimized convolution neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] Taking palm vein recognition as an example, palm veins have more application advantages than finger veins and dorsal hand veins, such as: (1) Palm veins have a more complex texture structure, richer vein texture information, and uniqueness; ( 2) The collection of palm veins is more convenient and friendly, and the light source design is easier and more reliable. The current vein recognition algorithm is mainly based on feature points and texture features for comparison. The feature points mainly refer to some prominent key points in the vein pattern, which have a strong degree of recognition, such as endpoints, bifurcation points, and intersection points. Wait.

[0040] Such as figure 1 Shown is the basic flowchart of implementing the technical solution of the present invention. In this embodiment, a vein recognition method based on a reinforcement learning algorithm to optimize a convolutional neural network includes the following implementation steps:

[0041] (1) ...

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 discloses a vein recognition method based on a reinforcement learning algorithm optimized convolution neural network, which utilizes the reinforcement learning algorithm to optimize theconvolution neural network to construct a vein recognition model. The vein recognition model includes a network exploration model based on reinforcement learning algorithm and a multi-layer convolution network evaluation model. The network exploration model includes an encoder, a linear layer, a nonlinear layer, a Softmax classification layer, a decoder and a reward evaluation module. The convolution network evaluation model includes a data input preprocessing layer, multiple normal convolution module layers and multiple compression convolution module layers spaced apart, a global pooling layer and a full connection layer, and finally outputs vein eigenvector. The vein recognition method based on a reinforcement learning algorithm optimized convolution neural network can get the highest evaluation model, so as to obtain a higher recognition accuracy.

Description

technical field [0001] The invention relates to the technical field of vein recognition, in particular to a vein recognition method based on a reinforcement learning algorithm to optimize a convolutional neural network. Background technique [0002] With the rapid development of the field of artificial intelligence, the use of computer vision and deep learning technology has achieved more and more outstanding performance in various recognition fields. Compared with traditional recognition methods, it has achieved better results in various directions such as image, language, and text. Effect. Currently, deep learning algorithms for image recognition are mainly convolutional neural networks. The convolutional neural network can learn high-level abstract features in various images through pre-learning. These features have a strong ability to distinguish, even small differences in images can be distinguished. Especially in feature extraction, convolutional neural network has b...

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
CPCG06V40/10G06N3/045G06F18/2415G06F18/214
Inventor 余孟春谢清禄张朝青
Owner MELUX TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products