Eye Detection Using Grayscale Conversion to Suppress Lens Reflections

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional eye detection techniques face challenges in improving accuracy, especially when dealing with color images of individuals wearing glasses, as reflections from the glasses' lenses can significantly lower detection accuracy.

Innovation Solution

A method involving a computer that acquires a color image, generates a grayscale image by adjusting red, green, and blue component values based on the glasses' characteristics, and detects the eye from this grayscale image to enhance detection accuracy by reducing external light and background reflections.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional eye detection techniques are used on color images of persons wearing glasses, then the detection process is simple, but the detection accuracy deteriorates due to lens reflections

Engineering Contradiction:

Improveeye detection accuracyVSAvoidlens reflection noise

Core Design Contradiction:

Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The patent transforms the color image into a grayscale image by applying specific weighting coefficients to the red, green, and blue color channels. This parameter transformation suppresses the reflection components while preserving the eye region information, thereby improving detection accuracy without requiring additional hardware

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent introduces an intermediate grayscale image as a mediator between the original color image and the final eye detection result. This intermediate representation filters out the harmful reflection noise while maintaining the essential eye features needed for accurate detection

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If specialized lighting devices are used to prevent lens reflections, then the detection accuracy improves, but the device complexity increases

Engineering Contradiction:

Improveeye detection accuracyVSAvoidlighting device complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces the mechanical/optical solution (specialized lighting devices with specific incident angles or polarization filters) with a computational/image processing solution. By using color space transformation and grayscale conversion with optimized coefficients, the system achieves the same reflection suppression effect without additional optical components

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent makes the existing image sensor and processing system multi-functional by enabling it to simultaneously capture color information and suppress reflections through software-based grayscale conversion. This eliminates the need for specialized lighting devices while maintaining detection accuracy

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS11961328B2Eye detecting method, eye detecting device, and non-transitory computer-readable recording medium recording eye detecting program

Publication Date: 2024.04.16 SWALLOW INCUBATE CO LTD

AI summary

An eye detecting device is configured to: acquire a color image including a face of a person taken by an image taking device; generate a grayscale image by multiplying each of a red component value, a green component value, and a blue component value of each pixel of the color image by a predetermined ratio according to characteristics of a lens of glasses that the person wears; detect an eye of the person from the grayscale image; and output eye information on the eye of the person.