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

Deep learning-based eye opening and closing state detection method

A state detection and deep learning technology, applied in the field of image processing, can solve problems such as inaccurate eye positioning, wrong judgment of eye opening and closing states, etc., and achieve the effect of meeting real-time requirements, fast operation speed, and easy large-scale promotion

Active Publication Date: 2018-10-02
GUIZHOU UNIV
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in practical applications, these methods are easily interfered by posture changes such as illumination changes, facial expression changes, and face rotations, and problems such as inaccurate eye positioning and wrong judgment of eye opening and closing states occur.

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
  • Deep learning-based eye opening and closing state detection method
  • Deep learning-based eye opening and closing state detection method
  • Deep learning-based eye opening and closing state detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] Embodiment of the present invention: eye opening and closing state detection method based on deep learning:

[0029] The first step: face detection.

[0030] For the input original image, the present invention utilizes the Piotr's Computer Vision Matlab Toolbox toolbox to directly perform face detection. If a face is detected, record the current face area to obtain an image of the face area. If no face is detected in the current input image, end the processing of the current input image and continue to perform face detection on the next frame of input image .

[0031] The second step: positioning of the center of the human eye.

[0032] The invention trains a convolutional neural network model to detect and locate key points of human eyes on face images. The structure diagram of the convolutional neural network model for human eye key point detection is as follows: figure 2 Shown is a convolutional neural network consisting of three convolutional layers, three max ...

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 deep learning-based eye opening and closing state detection method. A single image is directly processed, as long as a face is detected on the image, the position of an eye center point can be detected, and an eye area image is thus obtained. The eye opening and closing state classification accuracy is high, strong robustness is achieved for illumination changes, scene changes, face rotation, tilt and other posture changes, the operating speed is quick, the real-time performance requirements in actual application can be met, the hardware requirements are simple, and large-scale promotion is easy.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for detecting the state of eye opening and closing based on deep learning. Background technique [0002] Eyes are the most important part of the human face and can convey a lot of information. By detecting the open and closed state of the eyes, the blink frequency can be calculated to determine whether a person is in a state of fatigue. Compared with traditional wearable devices that use ECG or EEG, it is more economical and convenient, and is non-invasive to users. In addition, the opening and closing state of the eyes is closely related to human expressions, and the state detection of human eyes can assist related work such as expression recognition. [0003] At present, the methods for eye-opening and closing-eye state detection are mainly divided into detection methods based on feature analysis and detection methods based on pattern classification. The met...

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): G06K9/00G06N3/04
CPCG06V40/165G06V40/171G06N3/045
Inventor 张琳娜岑翼刚黄洁媛
Owner GUIZHOU UNIV
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