Eye Data Classification Using Blinking Amplitude and Iris Pupil Ratio
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for obtaining and analyzing eye data, such as EOG detection and pupil analysis, face challenges with invasiveness, environment-dependent noise, and difficulty in distinguishing iris and pupil colors, especially when lightness is similar, which complicates the detection of emotional and physical fatigue conditions.
Innovation Solution
A classification method using an imaging device, feature extraction unit, and classifier that extracts eye area data, calculates blinking amplitude, and generates a classification model based on the ratio of iris and pupil areas, oscillation width, and blinking patterns to classify emotional or physical conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If EOG detection method is used to obtain eye data, then measurement precision is improved, but device complexity and invasiveness increase due to requiring multiple electrodes placed around the eye
Solution Approach 1:
The patent replaces the mechanical/electrical EOG detection system with an optical imaging system. Instead of using electrodes to detect eye movements, the system uses a camera to capture eye images and processes these images to extract eye movement information and physiological state data, thereby eliminating the need for complex electrode placement while maintaining measurement capability
Solution Approach 2:
The patent creates an optical copy (image) of the eye instead of direct physical measurement. By capturing the eye's visual appearance and analyzing features like pupil position, iris patterns, and eye movement in the captured images, the system infers physiological state without requiring direct contact or invasive measurement
2Measurement precision
If infrared ray imaging is used to distinguish iris and pupil, then measurement precision is improved, but object-affected harmful factors increase due to strong infrared ray affecting the eye
Solution Approach 1:
The patent changes the imaging parameter from infrared radiation to visible light. By using visible light imaging, the system can capture eye details including iris and pupil features without exposing the eye to harmful infrared radiation, thus maintaining measurement precision while eliminating the harmful effect
Solution Approach 2:
The patent uses a standard camera with visible light instead of specialized infrared imaging equipment. This approach provides sufficient imaging quality for eye analysis without the harmful effects of infrared rays, effectively replacing the need for potentially damaging infrared technology
3Adaptability or versatility
If pupil analysis is used to detect emotional and physical conditions, then adaptability is improved, but measurement precision deteriorates due to environment-dependent noise and difficulty in distinguishing similar colors
Solution Approach 1:
The patent segments the eye structure into distinct regions (iris, pupil, sclera) and analyzes each separately. By focusing on the iris pattern recognition and eye movement analysis as distinct features, the system can detect emotional and physical states more accurately while reducing the impact of environmental factors that affect overall pupil appearance
Solution Approach 2:
The patent introduces image processing algorithms as an intermediary between the captured eye image and the final condition assessment. These algorithms enhance the contrast between iris and pupil, filter out environmental noise, and extract meaningful features that indicate emotional and physical states, thereby improving measurement precision
Data Source
AI summary
Person's conditions are classified according to his/her eye data. Person's conditions are classified according to his/her eye data using an imaging device, a feature extraction unit, and a classifier. The imaging device has a function of generating a group of images by continuous image capturing, and the group of images preferably includes an image of an eye area. The eye includes a black area and a white area. The method includes the steps in which the feature extraction unit extracts the eye area from the group of images, extracts a blinking amplitude, detects an image for determining start of eye blinking, stores an image for determining end of eye blinking as first data, and stores an image after a predetermined time elapsed from the first data as second data. The step in which the feature extraction unit extracts the white area from the first data and the second data is included. The classifier can use the white area as learning data.