Face Authentication Using Contour and Reflection Change Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing face authentication systems are vulnerable to impersonation attacks using photographs, and they struggle to detect target switching during authentication, allowing unauthorized access by switching between a photograph and a real person's face.

Innovation Solution

A face authentication method that calculates contour and reflection change degrees between consecutive images to detect target switching, using edge statistics and pixel value statistics to determine if the imaging target has changed, and requires the subject to perform a specified action to confirm authenticity.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If face authentication uses photographs for impersonation attacks, then authentication security deteriorates, but the system cannot distinguish between real faces and photographs

Engineering Contradiction:

Improveauthentication securityVSAvoidimpersonation by photographs

Core Design Contradiction:

ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The system detects changes in color distribution and reflection characteristics between consecutive images. Real faces exhibit natural color variations and reflection patterns that differ from photographs, allowing the system to identify and reject photographic impersonation attempts based on optical property analysis

Inventive Principle:

Principle #32Color changes

Solution Approach 2:

The system analyzes dynamic changes in image characteristics across consecutive frames. By computing contour change degrees and reflection change degrees between sequential images, the system can detect whether the imaging target is a static photograph or a dynamic real face, improving security against photographic impersonation

Inventive Principle:

Principle #15Dynamics

2Ease of operation

If the system accepts photographs for authentication, then ease of operation improves, but security deteriorates due to impersonation

Engineering Contradiction:

Improveauthentication convenienceVSAvoidauthentication security

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The system continuously monitors image characteristics during authentication and provides feedback by comparing contour change degrees and reflection change degrees against threshold values. This feedback mechanism automatically determines whether to accept or reject authentication attempts, maintaining both convenience and security without requiring manual intervention

Inventive Principle:

Principle #23Feedback

3Reliability

If the system detects target switching during authentication, then security improves, but device complexity increases due to additional image processing

Engineering Contradiction:

Improvedetection of target switchingVSAvoidimage processing complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system segments the authentication process into distinct analysis stages: extracting contour information, calculating contour change degree, extracting reflection characteristics, calculating reflection change degree, and making the final determination. This segmentation allows complex switching detection to be performed through multiple simple, manageable processing steps

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs partial image analysis by focusing only on specific features (contour and reflection characteristics) rather than processing the entire image comprehensively. This selective analysis achieves sufficient switching detection capability while reducing overall processing complexity and computational load

Inventive Principle:

Principle #16Partial or excessive action

4Measurement precision

If the system uses multiple image characteristics for authentication, then measurement precision improves, but processing time increases

Engineering Contradiction:

Improveauthentication accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary extraction and analysis of contour and reflection characteristics before making the final authentication determination. By pre-processing these features and computing change degrees in advance, the system can quickly compare against thresholds and make real-time authentication decisions without requiring time-consuming comprehensive analysis

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS12511934B2Face authentication method, storage medium, and face authentication device

Publication Date: 2025.12.30 FUJITSU LTD

AI summary

A face authentication method for a computer to execute a process includes acquiring a plurality of images from a camera; acquiring a contour change degree that represents a difference between a first contour included in an image imaged in a first image and a second contour included in the face image imaged in a second image, the plurality of images including the first image and the second image; acquiring a reflection change degree that represents a difference between first light reflection characteristic of the first image and second light reflection characteristic of the second image; and determining whether imaging targets of the camera has switched, based on the contour change degree and the reflection change degree.