Eyelid Detection Using Sobel Edge Extraction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing eyelid detection techniques are inefficient due to high processing times and costs, particularly when implemented on low-speed in-vehicle CPUs, and require extensive calculations.

Innovation Solution

An eyelid detection apparatus and method that uses a Sobel filter-based approach to minimize calculations by extracting edge lines and calculating eyelid candidates based on specific thresholds and patterns, enabling efficient detection of eyelid positions in real-time.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If template matching with correlative operation is used for eyelid detection, then detection accuracy is improved, but processing time increases and becomes unsuitable for low-speed in-vehicle CPUs

Engineering Contradiction:
Improveeyelid detection accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent segments the eyelid detection process into distinct stages: edge line extraction using Sobel filter, candidate line selection based on geometric constraints, and final verification. This segmentation allows each stage to use optimized algorithms appropriate to its specific task, reducing overall processing time while maintaining accuracy

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent extracts only the essential features needed for eyelid detection (edge lines and their geometric relationships) rather than performing full template matching. By extracting and processing only critical information, the system achieves fast detection suitable for low-speed CPUs without sacrificing detection accuracy

Inventive Principle:
Principle #2Taking out (Extraction)

2Speed

If dedicated computing units are used for eyelid detection, then processing speed is improved, but system cost increases

Engineering Contradiction:
Improveprocessing speedVSAvoidsystem cost
Core Design Contradiction:
SpeedVSDevice complexity

Solution Approach 1:

The patent designs the eyelid detection algorithm to be universally applicable on general-purpose CPUs without requiring dedicated hardware accelerators. The algorithm uses basic arithmetic operations and simple logical comparisons that can be efficiently executed on any standard processor, making the system cost-effective while maintaining real-time processing capability

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent replaces complex mechanical/computational systems (dedicated computing units) with a streamlined software-based algorithm that uses minimal calculations. The Sobel filter-based edge detection and geometric constraint methods achieve fast processing through algorithmic efficiency rather than hardware power, reducing system cost and complexity

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The solution significantly reduces processing time and costs by accurately detecting eyelid positions with minimal calculations, making it suitable for low-speed CPUs, such as those in vehicles.

Implementation Method 1

the Sobel filter, a first example of an edge-line extracting means, is used to extract edge lines

Methodology Applied
Scientific EffectSobel filter:

Data Source

PatentEP1969994B1Eyelid detection apparatus, eyelid detection method and program therefor
Publication Date: 2013.02.20 AISIN SEIKI KK
  • EP1969994B1 patent drawingFigure 1
  • EP1969994B1 patent drawingFigure 2
  • EP1969994B1 patent drawingFigure 3A~3F

AI summary

An eyelid detection apparatus (50) includes a face-image storing apparatus (22) for storing an image of a face of a subject, an eyelid-candidate extracting apparatus (24) for processing the image stored in the face-image storing apparatus (22) to extract a pair of lines, which becomes a candidate of a combination of a line corresponding to an upper eyelid and a line corresponding to a lower eyelid, a parameter calculating apparatus (24) for calculating a parameter, which indicates a possibility that a part of the image stored in the face-image storing apparatus (22), the part corresponding to the pair of lines extracted by the eyelid-candidate extracting apparatus (24), includes at least one of outer and inner corners of an eye, and an eyelid detecting apparatus (24) for detecting a position of an eyelid of the subject on the basis of the parameter calculated by the parameter calculating apparatus (24).