Method and system for automatically prompting distance from human eyes to screen

Abstract

The invention discloses a method and a system for automatically prompting a distance from human eyes to a screen. The method comprises the following steps: (A) collecting an image of a user through a camera; (B) processing the collected image, positioning a human face through a human face detection model, positioning an eyeball pair through an eyeball pair detection model, determining an image eye distance r of the user, calculating the age of the user through an age identifying unit and outputting the user eye distance R according to the age of the user; and (C) calculating the distance (D) from the human eyes to the screen by a formula D=(R*f) / r by combining the image eye distance r, the user eye distance R and the focus distance f, comparing the D with a prompting threshold, if the D is smaller than the prompting threshold, sending out alarm to the user. The system is used for executing the method. By human face identification, eyeball pair identification and age identification, position comparison is carried out through human face identification and eyeball pair identification to increase the accuracy rate of for positioning the eyeball pair; and the prompting function is relatively suitable for adolescents through age identification to play a role in protecting the vision of the user.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition, and in particular relates to a method and a system for automatically prompting the distance between human eyes and a screen. Background technique [0002] In recent years, with the rapid popularization of smart devices (including tablet computers), people's lives have become more and more convenient, but at the same time, the incidence of myopia in my country has increased significantly. According to the information released by the National Health and Family Planning Commission in 2014, there are more than 400 million myopia patients in my country. Among them, teenagers are the "hardest-hit areas" of myopia. The myopia rate of primary school students exceeds 25%, that of junior high school students reaches 70%, and that of high school students exceeds 85%. Studies have shown that watching the electronic screens of smart devices at close range for a long time is an important reason for...

AI Technical Summary

Problems solved by technology

[0003] Existing related technical solutions usually use relatively simple methods to realize the system, such as image morphology Hough transform circle detection method to locate pupils and perspective principle to estimate the distance between the human eye and the screen. Obsolete leads to low alarm accuracy, prone to false alarms and missed alarms. In addition, the existing related technical solutions, regardless of algorithm and threshold, are designed with adults as a reference, that is, they cannot meet the needs of teenagers, and teenagers happen to be short-sighted. high incidence period

This greatly limits the scope and effectiveness of the system

Images