Multi-channel human eye closure recognition method based on convolutional neural network

A convolutional neural network and recognition method technology, applied in the field of human eye state recognition, can solve problems such as unreasonable classification of eye states, achieve high recognition accuracy and anti-interference ability, good recognition effect, and good abstraction ability.

Active Publication Date: 2021-11-16
HOHAI UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, it is not reasonable to simply use a classifier to classify eye states

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
  • Multi-channel human eye closure recognition method based on convolutional neural network
  • Multi-channel human eye closure recognition method based on convolutional neural network
  • Multi-channel human eye closure recognition method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] Embodiments of the invention are described in detail below, examples of which are illustrated in the accompanying drawings. The embodiments described below by referring to the figures are exemplary only for explaining the present invention and should not be construed as limiting the present invention.

[0033] The recognition of human eye closure state is affected by factors such as eyelid contour detection, dynamic changes at the moment of blinking, illumination, occlusion, expression, etc. The R, G, B, and infrared images of the human eye captured by the Kinect camera are processed and fused into four-channel images. Image features are obtained through multiple convolutional layers and pooling layers, and finally a fully connected layer outputs the image classification results. Making full use of the various change information of the human eye, the convolutional neural network can control the data more flexibly according to the needs, and the abstraction ability is be...

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 multi-channel human eye closure recognition method based on a convolutional neural network. The method first obtains the R, G, B images of the human eye and a near-infrared image database; then the R, G, B and infrared images of the human eye After processing, it is fused into a four-channel image to make full use of the various change information of the human eye, and it is used as the input of the convolutional nerve; then the image features are obtained through multiple convolutional layers and pooling layer operations; finally, it is output by a fully connected layer Image classification results. In the practical application of the present invention, a Kinect camera is used to obtain multi-channel images of human eyes, and the recognition of human eye states has good robustness, high recognition precision and strong anti-interference ability.

Description

technical field [0001] The invention relates to a multi-channel human eye closure recognition method based on a convolutional neural network, in particular to a human eye state recognition method combining a multi-channel human eye image (R, G, B, infrared image) and a convolutional neural network, belonging to human Eye state recognition technology field. Background technique [0002] Eyes are an important organ for people to obtain information from the outside world. On the contrary, for the outside world, eyes are also the most direct organ that reflects people's mental state awareness. The extremely rich information contained in the human eye prompts people to identify the state of the human eye in different ways, so as to achieve different purposes. [0003] Since the 1960s and 1970s, the recognition of human eye state and the extraction of different human eye features have become the focus of research in the field of machine learning. So far, the main application fie...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/197G06N3/045G06F18/2413
Inventor 刘凡李逸云刘森斌李雪宜辛仰鑫
Owner HOHAI UNIV
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap