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

Word recognition technology based on eye movement tracking

An eye-tracking and technical technology, applied in character and pattern recognition, instruments, electronic digital data processing, etc., can solve the problems of unable to identify words, unable to recognize and learn words and phrases, etc.

Pending Publication Date: 2021-09-03
朴光宇
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, there are certain deficiencies in the existing eye tracking technology. For example, it can analyze and recognize the target image observed by people's glasses, especially it cannot recognize and determine the words in the text content, which makes it unable to assist people to recognize and learn. Words and phrases, therefore, we propose a word recognition technology based on eye tracking

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] A word recognition technology based on eye tracking, comprising the following steps:

[0025] ((1) Wearing of the instrument: the user first wears the contact head-mounted eye tracker on the head and fixes it, then observes the electronic display to be identified, and keeps the relative position of the instrument and the electronic display at a safe Measuring range;

[0026] (2) Data preprocessing: Draw the relationship diagram between the coordinates (X, Y) of the eye focus point and the text phrase frame, find out the text phrase frame corresponding to the jump point, and filter out the original data of the first-view text phrase frame The text phrase frame corresponding to the jump point;

[0027] (3) Image segmentation: each pixel of each channel of the first visual text phrase is represented by an independent random variable, the values ​​of the random variables are all between o ~ g / Q, and the sum of Q random variables belongs to Set {1, 2, ..., g}, g takes a co...

Embodiment 2

[0037] A word recognition technology based on eye tracking, comprising the following steps:

[0038] (1) Wearing of the instrument: The user first wears the contact head-mounted eye tracker on the head and fixes it, then observes the paper text to be recognized, and keeps the relative position of the instrument and the paper text at a measurable position scope;

[0039] (2) Data preprocessing: Draw the relationship diagram between the coordinates (X, Y) of the eye focus point and the text phrase frame, find out the text phrase frame corresponding to the jump point, and filter out the original data of the first-view text phrase frame The text phrase frame corresponding to the jump point;

[0040] (3) Image segmentation: each pixel of each channel of the first visual text phrase is represented by an independent random variable, the values ​​of the random variables are all between o ~ g / Q, and the sum of Q random variables belongs to Set {1, 2, ..., g}, g takes a constant of 25...

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 word recognition technology based on eye movement tracking, which comprises the following steps: 1) instrument wearing, wherein a user firstly wears a contact head-mounted eye movement tracking instrument on the head and fixes the instrument, then observes a target body needing to be recognized, and keeps the relative position of the instrument and the target body within a measurable range; 2) data preprocessing: drawing a relational graph of eye focus point coordinates (X, Y) and character phrase frames, finding out character phrase frames corresponding to jump points, and screening out the character phrase frames corresponding to the jump points from the original data of the character phrase frames from the first perspective; and 3) image segmentation: representing each pixel of each channel of the first visual character phrase by using an independent random variable, and dividing the image into a plurality of small regions according to different pixels in different places in the image. According to the invention, word recognition can be carried out on the observed character phrases based on an eye movement tracking technology, so that people can be effectively assisted in learning the character phrases.

Description

technical field [0001] The present invention relates to the technical field of eye movement tracking, in particular to a word recognition technology based on eye movement tracking. Background technique [0002] Eye tracking refers to the tracking of eye movements by measuring the position of the gaze point of the eyes or the movement of the eyeballs relative to the head. An eye tracker is a device that can track and measure eyeball position and eye movement information. It is widely used in the research of visual system, psychology, and cognitive linguistics. At present, there are many methods for eye movement tracking. Among them, the most commonly used non-invasive method is to obtain the position of the eye through video shooting equipment. The invasive method includes embedding eye movement measurement coils in the eyes or using microelectrodes to trace electrooculograms. [0003] However, there are certain deficiencies in the existing eye tracking technology. For examp...

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): G06K9/34G06K9/38G06K9/62G06F3/01G06F3/16
CPCG06F3/013G06F3/16G06F18/22
Inventor 朴光宇
Owner 朴光宇
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